No entries match these filters. Clear filters
Claude Code v2.1.283 adds prompt-audit, model management settings, gateway hints, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. /otel telemetry hooks.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.283 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.283
└──▷ TRY IT
Enable prompt grouping in your gateway to identify requests belonging to a single user prompt.
copy
$ export CLAUDE_CODE_GATEWAY_HINT_HEADERS=1
Audit your local configuration files for prompting patterns written for older models that may no longer be effective.
copy
$ /doctor prompt-audit
Adds x-claude-code-prompt-id header grouping for LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateways, controlled by the CLAUDE_CODE_GATEWAY_HINT_HEADERS=1 environment variable Not checked yet Adds /doctor prompt-audit and /checkup prompt-audit subcommands to audit CLAUDE.md files, skills, agents, and commands for outdated prompting patterns Not checked yet Adds availableModelsMatch managed setting (e.g., exact ) and deniedModels managed setting to block specific models in managed environments Not checked yet Adds MCP tool, WebFetch, and WebSearch output capture to OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. spans when OTEL_LOG_TOOL_CONTENT=1 is set Not checked yet Adds opt-in load_test_mode block to the Claude apps gateway config for load testing without sending upstream requests Not checked yet
+1 more
show less
Adds mantle upstream provider to the Claude apps gateway for Amazon Bedrock's Mantle endpoint Not checked yet
6 details in Everything
New telemetry filtering and Chrome/MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. coexistence controls in Claude Code v2.1.282
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.282 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.282
Adds maxProseWidth config key to cap AI prose width while preserving table/code block formatting. Not checked yet Adds /status and claude doctor commands to list ignored or disabled telemetry variables from settings files. Not checked yet Adds allowClaudeInChromeWithManagedMcp managed setting to permit claude --chrome operation alongside exclusive MCP configurations. Not checked yet Adds store.readiness_grace_seconds gateway configuration to maintain /readyz health during brief Postgres outages. Not checked yet
4 details in Everything
Claude Code v2.1.281 adds Claude apps gateway configs (assume_role, guardrail, telemetry.resource_attributes), MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. URL-mode elicitation, and plugin validation checks.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.281 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.281
Adds blockReadsOutsideWorkingDirectories and disableBypassPermissionsMode to desktop policy blocks for newer Claude Desktop keys in the Claude apps gateway. Not checked yet Adds assume_role support on Claude apps gateway Bedrock upstreams to call Bedrock as an assumed IAM IAM Identity and Access Management — a framework of policies and services for controlling who can authenticate to systems and what resources they are authorized to use, letting cyber tools enforce least-privilege and audit access. role via STS STS AWS Security Token Service, an Amazon Web Services API that issues short-lived credentials for IAM roles, letting cyber tools authenticate to AWS without storing long-term secrets. across AWS accounts. Not checked yet Adds guardrail: {id, version} configuration on Claude apps gateway Bedrock upstreams to apply Amazon Bedrock guardrails to every request. Not checked yet Adds telemetry.resource_attributes to the Claude apps gateway config to attach fixed labels to telemetry for Claude Desktop and /login sessions. Not checked yet Adds "attribution": false support in settings.json to hide all commit and PR attribution across CLI versions. Not checked yet
+2 more
show less
Enables MCP URL-mode elicitation on 2026-07-28 protocol connections, allowing servers to trigger browser-based flows without leaving a waiting dialog. Not checked yet Adds validation checks for MCP servers in claude plugin validate, reporting silently dropped .mcp.json entries, undeclared ${user_config.*} references, and insecure URLs. Not checked yet
7 details in Everything
v2.1.280 adds Claude Opus 5.5 support, mouse controls in fullscreen lists, and a configurable MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. description length limit
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.280 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.280
└──▷ USE IT
Configure MCP servers with descriptions longer than the default limit.
shell
copy
export CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH=4096
Interact with skills using a mouse in fullscreen mode.
📍 In fullscreen mode, use the mouse wheel to scroll the /skills list or click skill state options in /plugin.
Use the new Opus 5.5 model for a session.
shell
copy
claude -m claude-opus-5-5
Adds claude-opus-5-5 as the new default Opus model with 1M context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. Not checked yet Enables mouse wheel scrolling for /skills list and click interaction for skill state options in /plugin within fullscreen mode Not checked yet Introduces CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH environment variable to override the 2,048-character cap on MCP tool descriptions and server instructions Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! Reverts ctrl+l / cmd+k in fullscreen mode clearing the transcript view (behavior added in 2.1.260)! Changes default model on Pro and Team Standard plans from Sonnet to Opus! Restricts effort levels saved before /effort became per-model so they no longer apply to newly released models such as Opus 5.5
Adds AGENTS.md project instruction fallback, CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY proxy env var, and optional headers: map for gateway upstreams.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.277 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.277
└──▷ USE IT
Use AGENTS.md as the fallback project instruction file when no CLAUDE.md exists.
shell
copy
echo '# Agent Instructions' > AGENTS.md
claude
AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead; change it under Project instructions in /config (not yet on Bedrock, Vertex or Foundry) Not checked yet CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY=1 for Claude apps gateways whose only egress is a forward proxy: every outbound request hands the proxy the hostname instead of resolving it locally Not checked yet Optional headers: map on Claude apps gateway upstreams, to send static headers to a proxy you run in front of a provider Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! The deprecated TaskOutput tool is removed; Claude reads a background task's output file with Read instead, and the taskOutputMaxChars setting and TASK_MAX_OUTPUT_LENGTH no longer have any effect
Adds syncClaudeAiSkills/plugins config, --forward-subagent-text flag, /plugin install marketplace, and VSCode accept/reject diff buttons
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.275 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.275
Adds syncClaudeAiSkills: false and syncClaudeAiPlugins: false config keys to disable syncing of claude.ai account skills and plugins to terminal sessions Not checked yet Adds /plugin install <plugin> --marketplace <source> command to install plugins directly from a named marketplace source Not checked yet Adds claudeCode.scrollToBottomOnSend setting in VS Code to disable automatic scroll-to-bottom after sending a message Not checked yet Adds accept and reject buttons in the VS Code proposed-change diff tab for reviewing edits change-by-change Not checked yet
4 details in Everything
New env var CLAUDE_CODE_MCP_STARTUP_WAIT_MS, store.connect_timeout_seconds config, and claude_code.managed_settings_resolved OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. event in v2.1.274
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.274 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.274
Adds CLAUDE_CODE_MCP_STARTUP_WAIT_MS environment variable to control how long the first non-interactive turn waits for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server connections. Not checked yet Adds store.connect_timeout_seconds setting in the Claude apps gateway config to adjust the Postgres connection timeout. Not checked yet Adds claude_code.managed_settings_resolved OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. event exposing managed-settings sources and policy helper state. Not checked yet
3 details in Everything
└──▷ BREAKING ON UPGRADE
! Changes /code-review to use leaner inline review prompts instead of spawning many review subagents, altering the output format and execution path.
Claude Code v2.1.273 adds LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway hint headers, session forking via remote control, and several improved MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. /AWS integration capabilities.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.273 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.273
Adds x-claude-code-request-class, x-claude-code-agent-type, x-claude-code-prev-tool-durations, x-claude-code-compaction and x-claude-code-context-compacted request headers for LLM gateways; opt in with CLAUDE_CODE_GATEWAY_HINT_HEADERS=1 Not checked yet Adds forking a session started with claude --remote-control or /remote-control from the Claude app, running it as a background session on your computer Not checked yet Changes auto mode on Bedrock, Vertex and Foundry to use the local classifier by default; set CLAUDE_CODE_AUTO_MODE_SERVER=1 to use the platform's server-side classifier Not checked yet Improves OAuth client-credentials and JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. -bearer connections with providers that return a lowercase token type: requests now send the standard Bearer scheme Not checked yet
4 details in Everything
Claude Code v2.1.271 adds --drain-marker-file, per-command allowed_domains, --accept-command for plugins, and modelPricing multiplier.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.271 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.271
└──▷ TRY IT
Configure a self-hosted runner to gracefully drain and report its exit via a marker file when receiving SIGTERM.
copy
$ claude self-hosted-runner --drain-marker-file /tmp/drain.marker
Install a plugin by securely accepting only the specific command hash verified in a previous JSON run.
copy
$ claude plugin install --accept-command <sha256>
Set up agent subagents to bypass user, project, and local CLAUDE.md files using the new omitClaudeMd flag in JSON input.
copy
$ claude --agents '{"omitClaudeMd": true}' "Run analysis"
Adds claude self-hosted-runner --drain-marker-file <path> to signal host drain on SIGTERM Not checked yet Adds per-command allowed_domains configuration for Bash, PowerShell and Monitor in auto mode with sandboxing sandboxing Running code inside a restricted environment that limits what it can access or change. The isolation reduces the impact of mistakes or untrusted code, depending on the sandbox's controls. Not checked yet Adds omitClaudeMd field to agent frontmatter and --agents JSON for subagent runs without standard CLAUDE.md files Not checked yet Adds --accept-command <sha256> flag to claude plugin install and claude plugin update for safe plugin installation from JSON output Not checked yet Adds support for a multiplier above 1, up to 10, in the modelPricing managed setting and gateway pricing block for chargeback rates Not checked yet
5 details in Everything
Adds claude plugin eval subcommand, /output-style slash command, new env vars for telemetry and concurrency, and VSCode permission rules dialog.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.269 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.269
└──▷ USE IT
Evaluate a plugin's performance against Claude Code using its built-in suite.
shell
copy
claude plugin eval --help
Extend the LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateway model discovery timeout to 10 seconds.
shell
copy
export CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS=10000
Set the maximum concurrent agents for a workflow run to 64.
shell
copy
export CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS=64
Adds the claude plugin eval subcommand to run a plugin's eval suite with JSON + HTML reports Not checked yet Adds the /output-style [name] slash command to list and switch output styles in headless sessions Not checked yet Adds the CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS environment variable to configure the LLM gateway discovery timeout (default 3s) Not checked yet Adds the OTEL_METRICS_INCLUDE_REPOSITORY environment variable to tag OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. metrics with vcs.* repository attributes Not checked yet Adds the CLAUDE_CODE_WORKFLOW_MAX_CONCURRENT_AGENTS environment variable (1–256) to raise the Workflow tool's per-run concurrent agent limit Not checked yet
+5 more
show less
Adds a diff of files changed by Bash commands to the Bash tool result when bashEditDiffEnabled is set Not checked yet Adds an agent map in VSCode that opens from an N agents footer pill to show sub-agents with Stop and transcript controls Not checked yet Adds a Permission rules dialog in VSCode for managing permission rules in user, project, and local settings files Not checked yet Adds a Hooks dialog in VSCode for viewing and editing hooks in user, project, and local settings files Not checked yet Adds the ability to take back a queued message in a cloud session via Esc o before Claude reads it Not checked yet
10 details in Everything
v2.1.268 adds gateway network allowlisting, session state cleanup CLI, JSON plugin commands, and configurable WebFetch timeout
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.268 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.268
└──▷ TRY IT
Run the self-hosted runner with automatic session state cleanup enabled.
copy
$ claude self-hosted-runner --remove-session-state
Set a custom 60-second timeout for WebFetch requests via environment variable.
copy
$ export CLAUDE_CODE_WEBFETCH_DEADLINE_MS=60000 && claude 'fetch https://example.com'
Adds gatewayInternalNetworks managed setting to allow /login from a specific public IPv4 block on a Claude apps gateway Not checked yet Adds claude self-hosted-runner --remove-session-state subcommand to delete per-session directories under <base-dir>/_sessions/ when the session ends Not checked yet Adds CLAUDE_CODE_WEBFETCH_DEADLINE_MS environment variable to configure the WebFetch timeout (default 300 seconds) Not checked yet Adds --json output to claude plugin install, uninstall, update, enable, and disable commands Not checked yet Adds errorDetails and noteDetails fields to each row when running claude plugin list --json Not checked yet
5 details in Everything
Claude Code v2.1.267 adds maxEffortLevel config and --system-prompt-snapshot CLI flag for prompt iteration.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.267 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.267
└──▷ USE IT
Iterate on prompt text without the model caching the initial system prompt.
shell
copy
claude --system-prompt-snapshot off
Adds maxEffortLevel setting (top-level or per model under modelSettings) to cap the effort level on every provider, including Bedrock, Vertex and Foundry Not checked yet Adds --system-prompt-snapshot off CLI argument to render the system prompt fresh on every request instead of reusing the conversation's recorded prompt Not checked yet
2 details in Everything
v2.1.265 adds dynamic plugin-dir scanning, OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. telemetry export, and VSCode session archiving
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.265 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.265
--plugin-dir now loads a folder of plugins (each child folder with a manifest) and hot-adds/hot-removes them while running Not checked yet OTEL_EXPORTER_OTLP_ENDPOINT is used by Claude apps gateway sessions to export OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. directly to a collector, bypassing the relay Not checked yet [VSCode] New Archive inactive sessions setting (default 14 days) adds automatic session archiving Not checked yet
3 details in Everything
Claude Code v2.1.261 adds --append-subagent-system-prompt-file, new /skill-doctor command, and output size limits.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.261 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.261
Adds bashOutputMaxChars and taskOutputMaxChars config keys to control inline output limits up to 128K characters Not checked yet Adds --append-subagent-system-prompt-file CLI flag to read subagent system prompts from a file instead of the command line Not checked yet Adds /skill-doctor slash command to identify unused loaded skills and their context cost for pruning Not checked yet Adds VS Code walkthrough to build custom output styles and an Add/Remove form for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers in the IDE Not checked yet
4 details in Everything
Claude Code v2.1.260 adds /diff panel, /reload-plugins for headless, OIDC OIDC OpenID Connect, a sign-in protocol built on OAuth 2.0. An application uses identity information from a trusted provider instead of maintaining a separate password for each user. scope_on_refresh, and agent team fixes.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.260 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.260
└──▷ TRY IT
Monitor uncommitted code changes in real-time during an agent session by toggling the new diff view.
Adds a /diff slash command to toggle a fullscreen diff panel showing uncommitted changes as Claude edits files Not checked yet Adds /reload-plugins subcommand to headless sessions (SDK and Remote Control), appearing in standard command lists Not checked yet Adds a text form of the /advisor command for desktop, remote control, and -p agent SDK sessions (/advisor, /advisor <model>, /advisor off) Not checked yet Adds oidc.scope_on_refresh support in the Claude apps gateway for IdPs requiring openid scope on refresh to return an id_token Not checked yet Adds support for newer Claude Desktop policy fields userPluginMarketplacesEnabled and userPluginUploadsEnabled in desktop policy blocks via the Claude apps gateway Not checked yet
5 details in Everything
Adds managedMcpServers org setting, --permission-prompts none, and --json output to claude plugin validate
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.259 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.259
└──▷ USE IT
Run Claude Code in headless mode where any permission prompt is automatically denied.
shell
copy
claude --permission-prompts none 'Summarize this file'
Get a JSON validation report from the plugin system for CI integration.
shell
copy
claude plugin validate --json
Adds managedMcpServers managed setting allowing organizations to provide HTTP/SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers to every user. Not checked yet Adds --permission-prompts none flag for unattended headless hosts to automatically deny prompts. Not checked yet Adds --json output format to claude plugin validate for machine-readable validation reports. Not checked yet
3 details in Everything
Adds Claude Fable 5.1 as default, CLAUDE_CODE_SUBAGENT_MODEL_FORCE, time settings, auto-mode containment rules, and /effort session scope.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.257 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.257
claude-fable-5-1 is now the default Fable model with 1M context and new pricing tiers ($10/$50 per Mtok, $0.25/Mtok cache reads). Not checked yet Added timeFormat and timeZone settings to control the turn-end clock and transcript-view timestamps. Not checked yet Added a Containment Escape rule in auto mode that requires explicit approval for cloud metadata-credential fetches, egress evasion, and cross-tenant reach. Not checked yet CLAUDE_CODE_SUBAGENT_MODEL_FORCE environment variable now applies the subagent model to every subagent, ignoring per-spawn and agent-definition overrides. Not checked yet Added s modifier to /effort command to change effort for the current session only. Not checked yet
+3 more
show less
Added /doctor warning for stale sandbox mask files left by killed sessions. Not checked yet Added a one-time prompt in auto mode before the first file read outside working directories, with permissions.blockReadsOutsideWorkingDirectories config key to block such reads. Not checked yet Support for gateway-supplied description on discovered /model picker entries via CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY. Not checked yet
8 details in Everything
Claude Code v2.1.251 adds model switch hooks, subagent streaming, and session context to status lines.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.251 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.251
└──▷ USE IT
Attach to a specific background session ID to view its output or interact with it
shell
copy
claude attach <id>
Adds PreModelSwitch and PostModelSwitch hook events for blocking, confirming, or annotating model changes Not checked yet Enables live streaming of foreground subagent tool calls and results to Remote Control clients via new event hooks Not checked yet Adds rate_limits.spend_limit status line field for tracking spend caps behind Claude apps gateways Not checked yet Adds prompt_cache object to status line scripts with hit ratio, misses, re-cache count, and warm/cold metrics Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! CLAUDE_CODE_SUBAGENT_MODEL no longer overrides all models; it now sets the default for unconfigured spawns, yielding to agent definition or per-spawn model settings
Claude Code v2.1.248 adds --restricted mode, agent frontmatter cache TTL TTL Time to live, a limit on how long data remains valid or how far a packet can travel. Caches use a time limit; IP packets use a hop limit. , cross-session messaging, and self-hosted-runner client labeling.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.248 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.248
└──▷ TRY IT
Run Claude Code in a locked-down environment where code execution and external API calls are forbidden.
copy
$ claude --restricted
Configure a specific agent to cache prompts for 1 hour instead of the default duration.
text
copy
---
name: my-agent
model: sonnet
experimental:
cacheTtl: "1h"
---
Identify a specific self-hosted runner with a custom label for routing or logging purposes.
copy
$ claude self-hosted-runner --client-label prod-worker-01
Adds --restricted flag (or CLAUDE_CODE_RESTRICTED=1 env var) to disable command/code execution tools, limit file access to the working directory, refuse bypassPermissions, and ignore user/project/local settings files Not checked yet Adds experimental.cacheTtl key to agent frontmatter (accepting values like "5m" or "1h") to control per-agent prompt cache TTL when no subagent setting is configured Not checked yet Adds claude self-hosted-runner --client-label <label> argument (or SELF_HOSTED_RUNNER_CLIENT_LABEL env var) to override the label the runner registers with (default: hostname) Not checked yet Adds /doctor and /status slash commands in server-managed settings diagnostics to explain load failures for Bedrock/Vertex/third-party providers or custom ANTHROPIC_BASE_URL Not checked yet Adds /usage-credits slash command for Enterprise organizations billed through AWS Marketplace, self-serve Enterprise, and Enterprise trials to request higher usage limits from admin Not checked yet
+1 more
show less
Adds cross-session messaging capabilities via SendMessage and ListAgents between sessions on the same machine on Bedrock, Vertex, Foundry, and when telemetry is disabled Not checked yet
6 details in Everything
New /claude-api cost-optimize subcommand, SendFeedback tool with feedbackDrafts config, and spinnerTipsOverride structure expansion
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.247 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.247
└──▷ TRY IT
Profile an existing project's Claude API spend to identify cost optimization levers like caching and token hygiene.
copy
$ claude /claude-api cost-optimize
Added /claude-api cost-optimize to profile an existing project's Claude API spend and work through cost levers (caching, token hygiene, batch, effort, model choice) one measured change at a time Not checked yet Added the SendFeedback tool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from /feedback (turn off with the feedbackDrafts setting) Not checked yet Added {id, text, cooldownSessions, priority} entries, tipsFile, and label to spinnerTipsOverride, so organizations can rotate their own tips alongside the built-in ones Not checked yet Updated the /claude-api skill with Admin API Admin API A dedicated HTTP interface that exposes management and configuration operations separately from the data plane, letting cyber tools automate provisioning, policy changes, or monitoring without touching the main user-facing service. coverage (organization members, invites, workspaces, API keys, rate limit reports, workload identity federation workload identity federation A mechanism that lets a workload running in one cloud or platform prove its identity to another service using a trusted token exchange, eliminating the need to store long-lived credentials or secrets. , CMEK) Not checked yet
4 details in Everything
Claude Code v2.1.246 adds Auto mode permissions tab, subagent output tracking, and improved latency.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.246 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.246
Adds /permissions auto mode tab for viewing and editing classifier rules Not checked yet Returns partial output marker from subagents that hit maxTurns limit Not checked yet Improves Bash tool latency by replaying snapshot functions instead of base64 subshells Not checked yet Automatically continues non-interactive responses cut off mid-stream Not checked yet Enables /code-review on Bedrock, Vertex AI, Foundry via Claude apps gateway Not checked yet
5 details in Everything
New /claude-api upgrade command for Anthropic SDK migration, synced cloud plugins, and new CLAUDE_CODE_RETRY_WATCHDOG behavior
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.239 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.239
└──▷ TRY IT
Migrate an existing Python project to use the new Anthropic SDK 1.x API structure.
copy
$ /claude-api upgrade
Configure persistent retry behavior that fails fast on budget limits rather than waiting indefinitely.
copy
$ export CLAUDE_CODE_RETRY_WATCHDOG=1
Enable a plugin synced from the cloud in your local session using the synced naming convention.
copy
$ claude plugin enable my-synced-plugin@synced
Adds the /claude-api upgrade subcommand to migrate Python projects from anthropic 0.x to 1.x. Not checked yet New cloud session plugins sync from claude.ai as name@synced, supporting claude plugin enable/disable <name>@synced. Not checked yet New persistent retry mode via CLAUDE_CODE_RETRY_WATCHDOG environment variable for immediate failure on organization spend-limit errors. Not checked yet Added /cost, status line, and --max-budget-usd support for the 1.1× US-only-inference premium in data-residency workspaces. Not checked yet
4 details in Everything
Claude Code v2.1.238 adds readline keybinding flavor, self-hosted runner shutdown delays, proxy auth commands, and plugin headersHelper
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.238 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.238
└──▷ TRY IT
Keep the runner running for 5 minutes after SIGTERM to finish active sessions before shutting down
copy
$ claude self-hosted-runner --defer-shutdown-max-min 5
Pass a script that outputs a fresh Proxy-Authorization header on every connection via the runner's CLI flag
copy
$ claude self-hosted-runner --proxy-authorization-command "./fetch-proxy-token.sh"
Adds keybindingFlavor setting to .claude/config.yaml to select readline style editing Not checked yet Adds --defer-shutdown-max-min <minutes> flag to claude self-hosted-runner for controlled session teardown Not checked yet Adds --proxy-authorization-command and --proxy-authorization-file flags to claude self-hosted-runner for dynamic proxy auth Not checked yet Introduces headersHelper capability in plugin marketplaces and catalog entries for minting HTTP headers during installation/update Not checked yet Enables crossSessionInbound: "refuse" setting to explicitly reject inbound cross-session messages with a status report Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! Removed the double-press /clear shortcut; Ctrl+L and Cmd+K in fullscreen now only repaint without clearing history! MCP headersHelper from project .mcp.json, plugin, or agent file no longer inherits credential environment variables
Adds a Concise output style to /config that suppresses preamble and narration
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.237 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.237
└──▷ HOW TO FIND IT
Reduce output noise when using Claude Code in a terminal or CI pipeline where only the final result matters.
📍 /config › Output style › Concise
Adds ANTHROPIC_DEFAULT_MODEL env var, cross-session notify_when_idle, and macOS wildcard sandbox rules
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.236 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.236
Added ANTHROPIC_DEFAULT_MODEL environment variable: sets the model new sessions start on, while a /model pick still overrides it and persists across restarts (unlike ANTHROPIC_MODEL) Not checked yet Added notify_when_idle to cross-session SendMessage: ask another Claude Code session on this machine to send one notice when it next goes idle — opt-in, one-shot, no polling (macOS and Linux) Not checked yet Sandbox: on macOS, wildcard read-deny rules (e.g. **/.env) now take precedence inside allowed read regions, cover matched directories' contents, and can't be bypassed by renaming the denied file Not checked yet [VSCode] Added screen reader support for the transcript: live announcements for replies, permission requests, errors, and status changes, plus per-turn heading navigation Not checked yet
4 details in Everything
Claude Code v2.1.235 adds optional spellcheck setting with aspell/hunspell/ispell support and hardens SendMessage size limits.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.235 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.235
└──▷ USE IT
Enable live spellchecking in the prompt input so typos are underlined as you type — requires aspell, hunspell, or ispell to be installed.
yaml
copy
spellcheck: true
Adds optional spellcheck setting that underlines misspelled words in the prompt input as you type, using your installed aspell, hunspell, or ispell. Not checked yet SendMessage now rejects messages too large for cross-session delivery up front instead of silently dropping them. Not checked yet Remote Control: claude rc now applies the same enterprise-gateway availability check as interactive startup. Not checked yet Improved memory and CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. usage while cloud sessions such as /ultrareview or /autofix-pr run in the background — their event streams are no longer re-scanned and re-rendered on every update. Not checked yet Context-limit error now indicates when auto-compact is off and points to /config to re-enable it. Not checked yet
+1 more
show less
Vim mode now preserves NORMAL mode and cursor position when toggling the detailed transcript (ctrl+o) or closing a panel. Not checked yet
6 details in Everything
Claude Code v2.1.234 adds CLAUDE_CODE_PROJECT_DIR_NAME, selection:clear keybinding, GitLab MR badges, auto-resume at usage limits, and mid-turn /permissions edits.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.234 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.234
└──▷ TRY IT
Give each CI job its own short transcript directory name instead of a long auto-generated one.
copy
$ export CLAUDE_CODE_PROJECT_DIR_NAME=my-feature-branch
claude
Opt out of the 30-minute background-task check-in so /goal never interrupts long-running agents.
copy
$ export CLAUDE_CODE_GOAL_CHECKIN_MINUTES=0
claude
Adds optional CLAUDE_CODE_PROJECT_DIR_NAME environment variable so hosts that give each session its own config directory can choose a short name for the per-project transcript directory. Not checked yet Adds CLAUDE_CODE_GOAL_CHECKIN_MINUTES environment variable (set to 0 to opt out) to control how long /goal waits before checking in on background tasks that have been running 30+ minutes. Not checked yet Adds selection:clear keybinding action, bindable to any key, that clears an in-app text selection in both the main view and the agents view. Not checked yet Adds a GitLab merge request badge to the footer and statusline: repos with a GitLab remote and an authenticated glab CLI show MR !N with draft/pending/green states. Not checked yet Adds automatic session continuation when a claude.ai usage limit resets; toggle off via /config (Continue automatically at usage limit ). Not checked yet
+10 more
show less
/permissions can now be opened while Claude is actively working, and rule changes apply immediately to the rest of the current turn. Not checked yet /add-dir <path> can now be invoked while Claude is working; /add-dir, /autocompact, /theme, /help, /config, and /advisor dialogs all open mid-turn in the fullscreen TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. . Not checked yet /goal now clears itself with a notice when a turn ends on an unrecoverable error (revoked auth, exhausted credit balance, or context overflow) instead of staying armed. Not checked yet claude setup-token now rejects unexpected extra arguments instead of silently ignoring them. Not checked yet Reduces context cost of loading the built-in claude-api skill from ~200k+ tokens to ~25k by loading reference docs on demand. Not checked yet Remote Control: effort picks made on a phone or on claude.ai/code now apply to terminal- and Desktop/VS Code-hosted sessions, and the session publishes its effort level to connected clients. Not checked yet Remote Control sessions from Claude Code Desktop or VS Code now keep phones and claude.ai/code updated on the session's permission mode and model as they change. Not checked yet SendMessage and ListAgents now report when your account's session list was too long to check completely, instead of treating unseen sessions as absent. Not checked yet Improves auto-generated session titles to read as short, specific names (e.g. Login button bug ) rather than sentences restating the request. Not checked yet Removes the Default teammate model setting from /config; agent-team teammates now use the leader's model unless the spawn command names one. Not checked yet
15 details in Everything
└──▷ BREAKING ON UPGRADE
! The Default teammate model setting is removed from /config; agent-team teammates now inherit the leader's model unless the spawn command explicitly names one.
Claude Code v2.1.233 adds GitLab MR support, per-user identity forwarding, Linux memory limits for Bash tools, and a WebFetch cache TTL TTL Time to live, a limit on how long data remains valid or how far a packet can travel. Caches use a time limit; IP packets use a hop limit. knob.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.233 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.233
└──▷ TRY IT
Cap memory for Bash tool commands on Linux to prevent a runaway build from consuming all RAM RAM Working memory that holds programs and data while a computer is running. Its contents usually disappear when power is removed. and stalling the session.
copy
$ CLAUDE_CODE_TOOL_MEMORY_LIMIT=2G claude
Shorten the WebFetch URL cache lifetime so repeatedly-fetched pages stay fresh during a long session.
copy
$ CLAUDE_CODE_WEBFETCH_CACHE_TTL_MS=300000 claude
Re-enable todo/task-tracking tools on newer models that disable them by default.
copy
$ CLAUDE_CODE_ENABLE_TODO_TOOLS=1 claude
Adds CLAUDE_CODE_TOOL_MEMORY_LIMIT environment variable (Linux) to cap memory for Bash tool commands via cgroup support, preventing runaway builds from stalling a session. Not checked yet Adds CLAUDE_CODE_WEBFETCH_CACHE_TTL_MS environment variable to control the WebFetch session URL cache TTL (default: 15 minutes). Not checked yet Adds opt-in forward_user_identity apps gateway setting on Anthropic upstreams, forwarding the signed-in user's identity as headers so a proxy can attribute spend per user. Not checked yet Extends the --worktree flag and the claude agents view to accept GitLab merge request URLs, displaying MRs as !N. Not checked yet Improves claude plugin validate to inspect a bare .claude/skills directory and report SKILL.md files with unparseable frontmatter. Not checked yet
+5 more
show less
Adds [claude-code:unrecognized_model] diagnostic line to stderr in print mode when a request is sent for an unrecognized model ID; suppress with modelOverrides. Not checked yet Improves claude self-hosted-runner session start time by creating the session branch without rewriting the working tree and eliminating two blocking server round trips. Not checked yet Improves apps gateway error forwarding: 400/413 responses from Vertex, Foundry, and Claude Platform on AWS upstreams now surface the upstream's own error message. Not checked yet Improves screen reader mode: the /effort selector renders as a numbered list with a typed-number prompt, and hint and dialog text is no longer clipped. Not checked yet Suppresses the GitHub app setup tip in repositories whose origin remote is on gitlab.com or bitbucket.org; the enterprise marketplace tip now covers non-GitHub internal git hosts. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! Todo/task-tracking tools (TaskCreate, TaskGet, TaskUpdate, TaskList, TodoWrite) are no longer available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and newer models; set CLAUDE_CODE_ENABLE_TODO_TOOLS=1 to restore them.
Claude Code v2.1.232 adds cross-session @-mentions, subagent forking by default, GitLab secret redaction, and GitLab plugin marketplace support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.232 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.232
└──▷ HOW TO FIND IT
Configure cross-session messaging policy so inbound messages from your other sessions are held for review rather than accepted automatically.
📍 /config
Block a private GitLab plugin marketplace from being used, even when the CLI identifies the URL as a git clone.
json
copy
{
"blockedMarketplaces": [
{ "type": "url", "value": "gitlab.com/my-org/internal-plugins" }
]
}
Use the friendlier allowedMarketplaces alias in settings instead of the legacy strictKnownMarketplaces key to restrict which marketplaces Claude Code may use.
json
copy
{
"allowedMarketplaces": [
"gitlab.com/my-org/approved-plugins"
]
}
Subagent forking is now on by default: a subagent_type: "fork" subagent inherits the full conversation and prompt cache, and non-teammate agent spawns in interactive sessions now run in the background by default. Not checked yet Type @ in the prompt to mention another Claude session by name; Claude uses SendMessage to reach that session directly — and SendMessage now delivers to a bare name that exactly matches one live session without a confirmation step. Not checked yet Adds /config rows for Dialog expiry and Messages from your other sessions , enabling per-session control over cross-session inbound messaging (accept/hold/refuse). Not checked yet Adds secret redaction for GitLab token families glrt-, gloas-, glptt-, glagent-, glimt-, glsoat-, glcbt-, glft-, and glffct-; fully redacts routable glpat- and gldt- tokens; extends the same sandbox and credential-path protection to the glab CLI config store. Not checked yet Adds GitLab support to plugin marketplaces: bare gitlab.com repo URLs (including nested subgroups) now clone like github.com URLs. Not checked yet
+13 more
show less
Settings now accept additionalMarketplaces and allowedMarketplaces as friendlier aliases for extraKnownMarketplaces and strictKnownMarketplaces. Not checked yet Enterprise policy: a url-typed blockedMarketplaces entry for a bare repo URL continues blocking that URL even when the CLI classifies it as a git clone. Not checked yet Gateway: the desktop: overlay now accepts every released Desktop setting (previously limited to 11 hand-listed keys), validated at boot against Desktop's own schema; unknown or invalid keys now fail boot. Not checked yet Gateway: empty managed.policies[].match.groups / admin.admin_groups entries and malformed email_domain values (empty, or containing @, whitespace, or commas) now fail at boot instead of silently matching no one or granting admin access. Not checked yet Fable 5 is offered as an advisor in /advisor again for organizations with Fable access, with usage-credits consent set up through /model fable. Not checked yet Interactive sessions on one machine now keep unique names: renaming a session to a name already in use generates a name-word-word variant and notifies the user. Not checked yet Bash input redirections (< file) are now permission-checked like their argument spellings on all platforms. Not checked yet Sandbox: sandbox.ripgrep is now honored only from user, managed, and --settings settings; project settings can no longer override the sandbox's ripgrep binary. Not checked yet /feedback and /bug now open immediately when invoked while Claude is responding, instead of waiting for the turn to finish. Not checked yet /plugin install plugin@marketplace now refreshes the marketplace first, so newly published plugins install without a manual marketplace update. Not checked yet /code-review at high, xhigh, and max effort now runs in a background agent, consistent with other effort levels. Not checked yet Remote Control now reconnects for approximately 30 minutes after a network blip and no longer drops after a few blips spread across an hour. Not checked yet Managed settings approval dialog now shows endpoint URLs, uses clearer wording for telemetry-only changes, skips routine OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. options, and requires explicit approval for server-managed sandbox binary overrides (sandbox.bwrapPath, sandbox.socatPath, sandbox.ripgrep). Not checked yet
18 details in Everything
└──▷ BREAKING ON UPGRADE
! sandbox.ripgrep set in project settings is no longer honored; it must now be placed in user, managed, or --settings settings.! Gateway: unknown or invalid keys under the desktop: overlay now fail boot (previously accepted silently).! Gateway: empty managed.policies[].match.groups / admin.admin_groups entries and malformed email_domain values now fail at boot instead of silently matching no one or granting admin access.
Claude Code v2.1.229 adds plugin command sources, Remote Control session status, SSE SSE Server-Sent Events, a browser API and HTTP-based protocol where a server pushes a stream of text events to a client over a single long-lived connection, giving tools a lightweight alternative to WebSockets for one-way real-time updates. keepalives, and VSCode session groups.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.229 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.229
└──▷ TRY IT
Resume the most recent Remote Control session without looking up its session ID — useful when reconnecting after a network drop.
copy
$ claude remote-control --continue
Disable workflow fan-out staggering in a latency-sensitive pipeline where you do not want agents to wait before starting.
copy
$ CLAUDE_CODE_WORKFLOW_PREFIX_STAGGER_MS=0 claude
Documents claude remote-control --continue to resume the most recent Remote Control session without specifying a session ID. Not checked yet Adds plugin marketplace command sources: a local command (e.g. an IDE) prints the plugin directory, re-resolved each session without a restart; mode: "link" uses it in place. Not checked yet Sets CLAUDE_CODE_WORKFLOW_PREFIX_STAGGER_MS=0 to disable the new workflow fan-out staggering that lets same-prefix sibling agents share a cached prompt prefix. Not checked yet ListAgents now marks disconnected Remote Control sessions as offline and labels cloud sessions as cloud, giving clearer session inventory. Not checked yet Adds SSE keepalive pings to gateway streaming responses during long thinking pauses, preventing idle-timeout disconnects on Vertex and Bedrock upstreams. Not checked yet
+5 more
show less
Adds server-supplied Claude Code hook support for self-hosted runner sessions, matching managed-environment behavior. Not checked yet Self-hosted runner Windows startup now requires an explicit --base-dir; there is no default checkout directory on Windows. Not checked yet Removes auto-approval of git/gh commands with dangerous flags (--force, --amend, --no-verify, etc.) in /commit-push-pr. Not checked yet [VSCode] Adds session groups in the sidebar — right-click to create, rename, or delete; Cmd/Ctrl- or Shift-click to move multiple sessions at once. Not checked yet [VSCode] Makes the /btw side-question panel resizable by dragging its boundary, in both side-docked and stacked layouts. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! Self-hosted runner Windows startup now requires an explicit --base-dir; launches that previously relied on a default checkout directory will fail without it.! /commit-push-pr no longer auto-approves git/gh commands that include dangerous flags (--force, --amend, --no-verify, etc.); workflows depending on silent approval of these flags will now prompt for confirmation.
Claude Code v2.1.228 hardens synced skills, improves cross-session messaging display, and lets newer models overwrite unread files.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.228 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.228
Hardens skills synced from claude.ai: they no longer shadow local commands or MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. prompts, descriptions are sanitized and labeled, and skill bodies cannot run ! commands or expand @ files on your machine. Not checked yet Changes the Write tool so newer models can overwrite an existing file they have not read in the current session, matching the Edit tool's rules; older models still require a prior read. Not checked yet Improves cross-session messages: sender and body now display inline instead of as a collapsed line, and messages to Remote Control sessions on other machines show your Remote Control session name as the sender. Not checked yet Improves Vertex AI credential handling: expired or missing Google Cloud credentials now fail within seconds instead of retrying for minutes. Not checked yet Improves compaction progress: the retry countdown and stall hint now appear during compaction alongside the progress bar. Not checked yet
5 details in Everything
v2.1.225 adds gateway spend-limit warnings, workspace trust in claude agents, and SendMessage can now initiate Remote Control sessions by name.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.225 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.225
Adds gateway spend-limit support to Claude Code's usage warning — the limit-reached message now names the cap, its reset time, and the operator's message (requires gateway on 2.1.225). Not checked yet Adds a workspace trust prompt to claude agents for untrusted directories, matching the existing behavior of claude. Not checked yet SendMessage can now initiate a conversation with Remote Control sessions on other machines by name — ListAgents surfaces them as name [ref] — instead of only being able to reply after they message you first. Not checked yet SendMessage now locks in a Remote Control recipient you have already confirmed, preventing it from being silently swapped for a same-named session on the local machine when the remote list could not be checked. Not checked yet Remote Control: photos attached from the Claude app are now passed directly to Claude rather than being read from disk via a separate tool call. Not checked yet
5 details in Everything
Claude Code v2.1.224 adds self-hosted runners, cross-session messaging, archive plugin sources, and new sandbox credential-masking options.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.224 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.224
└──▷ TRY IT
Route Bedrock API calls through a specific cross-region inference profile instead of the one derived from AWS_REGION.
copy
$ export ANTHROPIC_BEDROCK_REGION_PREFIX=us-west-2
claude
Enable JWT JWT An open standard (RFC 7519) for encoding claims as a signed, optionally encrypted JSON object passed between parties. Cyber tools use it to verify identity and permissions without querying a central session store. -aware credential masking in the sandbox to redact specific claims from bearer tokens bearer tokens A credential that grants access to whoever presents it, without a separate proof of possession. Protecting the token matters because a stolen copy can be used by someone else. before they leave the environment.
yaml
copy
decode: "jwt"
maskClaims:
- sub
- email
- aud
New claude self-hosted-runner subcommand turns your own machines or containers into execution environments for Claude Code web, mobile, and desktop sessions (Team and Enterprise plans). Not checked yet New ANTHROPIC_BEDROCK_REGION_PREFIX environment variable lets Bedrock users prefer a specific cross-region inference profile over the AWS_REGION-derived default. Not checked yet New crossSessionInbound and dialogExpiry settings: cross-session messages sent to a bypassed-permission session are held for approval; messages to other sessions auto-deliver. Not checked yet New sandbox credential-masking options — extract and onExtractNoMatch for structured env values, decode: "jwt" with maskClaims for JWT-aware masking, and awsPairs/sigv4 for AWS SigV4 SigV4 AWS's request-signing protocol that authenticates HTTP calls by hashing the request body, headers, and credentials into a signature; cyber tools use it to talk to AWS APIs without embedding long-lived secrets. re-signing — honored only from user, managed, or --settings settings and require network.tlsTerminate. Not checked yet New archive plugin source: install plugins from a zip over HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. without git or npm, with optional SHA-256 SHA-256 A cryptographic hash function that turns data into a fixed 256-bit fingerprint. It is used to check integrity; hashing does not encrypt the original data. pinning. Not checked yet
+5 more
show less
New cross-session SendMessage API lets Claude Code sessions message each other across any of your machines; ListAgents discovers available sessions (macOS and Linux). Not checked yet Removes the 200-subagent-per-session spawn cap, allowing long-running sessions to continue spawning agents without hitting a hard limit (concurrency and depth limits still apply). Not checked yet Remote Control now shows a persistent failure indicator with details and a reconnect shortcut on connection failure, instead of only an 8-second toast. Not checked yet Remote Control improvements: attached web and mobile clients now see compaction progress and the post-compaction boundary; /clear resets propagate to attached clients. Not checked yet Fullscreen mode now keeps the full pre-compaction history in scrollback across repeated compactions instead of only the most recent interval. Not checked yet
10 details in Everything
Claude Code v2.1.223 adds owner wildcard marketplace controls, /teleport for cloud-to-local handoff, and upgraded /code-review with effort levels.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.223 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.223
└──▷ USE IT
Block all marketplace repos from a specific GitHub org in managed settings with a single wildcard entry instead of listing each repo.
json
copy
{
"blockedMarketplaces": ["acme-corp/*"]
}
Pick up a cloud session on your local machine when you need to switch environments mid-task.
copy
$ claude --teleport <session id>
Run a deep review of a pull request straight from the terminal using the new effort-level syntax.
copy
$ /code-review ultra 4321
Adds "owner/*" wildcard entries to strictKnownMarketplaces and blockedMarketplaces managed settings to allow or block all marketplace repos under a GitHub org in one entry. Not checked yet Adds claude --teleport <session id> flag and a /teleport hint in cloud sessions to continue a cloud session locally. Not checked yet Adds CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT=1 env var to opt out of the new behavior that keeps sessions on unrecognized model IDs within the assumed context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. . Not checked yet Expands CLAUDE_CODE_DISABLE_1M_CONTEXT to cap every Claude model with a native 1M context window to 200K via auto-compaction (not just a fixed model list); adds a startup warning when auto-compaction isn't holding the session to 200K. Not checked yet Makes /review an alias of /code-review; /code-review now accepts an effort level and PR number (/code-review <level> <pr#>), with /code-review ultra triggering a deep cloud review. Not checked yet
+2 more
show less
Makes /code-review remember the last effort level used when invoked without one, so repeat reviews don't require retyping the level. Not checked yet Adds a warning when a workflow agent, forked skill, slash command, or resumed background agent's requested subagent model is restricted and the parent model runs instead. Not checked yet
7 details in Everything
Claude Code v2.1.222 tightens multi-agent permission enforcement and improves Remote Control scoping
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.222 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.222
Remote Control auto-start can no longer be enabled via repo-local .claude/settings.json or .claude/settings.local.json; enable it at user scope via /config instead (repo-local settings can still turn it off) Not checked yet Improves auto mode safety: messages dispatched to other agent sessions via SendMessage are now evaluated by the permission classifier before delivery Not checked yet Improves disable-model-invocation refusal behavior: Claude now prompts the user to run the skill directly rather than attempting to replicate its workflow Not checked yet The /diff view, Remote Control workspace diff, and file-edit diffs in web sessions now use raw git blob content, ignoring workspace-configured diff drivers and textconv Not checked yet Removes the ultraplan feature Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! Remote Control auto-start can no longer be enabled from .claude/settings.json or .claude/settings.local.json; configurations relying on repo-local settings to turn it on will stop working — use /config at user scope instead.! The ultraplan feature has been removed; any configuration or workflows depending on it will break.
Claude Code v2.1.221 adds Focus view, sandbox credential masking, prompt-audit subcommand, and smarter plugin/session management.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.221 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.221
└──▷ TRY IT
Audit your prompts and tool descriptions for patterns written for older models before migrating to Claude 4.5-generation.
copy
$ claude-api prompt-audit
Validate a plugin and catch names that would be rejected by Claude Desktop's managed marketplace sync.
copy
$ claude plugin validate
Configure a sandbox credential file to use masking on Linux/WSL WSL Windows Subsystem for Linux, a Microsoft-built compatibility layer that lets a Linux environment run directly on Windows without a virtual machine, giving cyber tools access to Linux binaries, filesystems, and syscalls on a Windows host. so sandboxed commands see a sentinel value while the proxy substitutes the real credential on egress.
yaml
copy
mode: "mask"
extract: "(sk-[A-Za-z0-9]+)"
Adds mode: "mask" for sandbox credential files on Linux and WSL — sandboxed commands read a sentinel copy (whole file or spans captured by an extract regex) while the sandbox proxy substitutes the real value on egress; on macOS falls back to deny. Not checked yet Adds prompt-audit subcommand to the claude-api skill for auditing prompts and tool descriptions for patterns written for older models. Not checked yet Adds warnings to claude plugin validate when a marketplace or plugin name would be rejected by Claude Desktop's managed marketplace sync. Not checked yet [VSCode] Adds Focus view: a chat-menu toggle that hides tool activity behind an expandable per-turn summary with a live running-tool indicator, toggled with Ctrl+Alt+F or the Claude Code: Toggle Focus view command. Not checked yet Changes /status to show the session kind: interactive, or a background job that is attached or unattended. Not checked yet
+12 more
show less
Changes sessions forked with /fork to create a new worktree of their own instead of working in the original session's checkout. Not checked yet Changes plugins to accept "." as a skills path, with the root-level SKILL.md validation error now suggesting using the plugin root. Not checked yet Changes /plugin install to refresh a stale marketplace catalog and retry before reporting a plugin not found. Not checked yet Changes plugins installed from /plugin to activate immediately when safe, instead of always requiring /reload-plugins. Not checked yet Changes background sessions to commit and push to preserve work, open a draft PR only when the task calls for one, follow CLAUDE.md git instructions, and always report where the work lives. Not checked yet Improves Stats panel to count cache tokens in its token totals, with a breakdown by input, output, cache read, and cache write. Not checked yet Re-enables tool search on Google Vertex AI for Claude 4.5-generation and newer models. Not checked yet Improves Windows startup by reading process creation times via a native kernel32 call instead of spawning PowerShell, so endpoint security tools that gate powershell.exe no longer prompt. Not checked yet Changes emoji autocomplete to accept common alternate shortcodes like :thumbsup:, :thumbsdown:, and :love:. Not checked yet Changes fast mode to report on the stream when usage credits run out mid-session, instead of failing silently. Not checked yet Changes Monitor: a watch that exits without producing any output now says so instead of reporting stream ended . Not checked yet Changes Gateway model field validation to reject non-string values with a 400 instead of forwarding them. Not checked yet
17 details in Everything
Claude Opus 5 lands as the new default Opus model, with 1M context, strict sandbox networking, and depth-3 nested subagents.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.219 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.219
└──▷ USE IT
Lock sandbox network access to only approved hosts so any unexpected outbound call is silently denied without an interactive prompt.
json
copy
# In your Claude Code settings file (e.g. ~/.claude/settings.json)
{
"sandbox": {
"network": {
"strictAllowlist": true
}
}
}
Cap the depth of nested subagent spawning at 1 (flat) to reproduce pre-v2.1.219 behaviour in automation pipelines that shouldn't recurse.
copy
$ CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH=1 claude -p "refactor the auth module"
Pin the Dynamic workflow size guideline org-wide via settings so all users get it without having to touch /config.
json
copy
# In a shared settings file
{
"workflowSizeGuideline": "medium"
}
Adds Claude Opus 5 (claude-opus-5) as the default Opus model — 1M context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. , fast mode at $10/$50 per Mtok. Not checked yet Adds sandbox.network.strictAllowlist setting to silently deny any sandboxed-command network request to a non-allowlisted host (no prompt). Not checked yet Adds DirectoryAdded hook that fires whenever /add-dir or the SDK register_repo_root control request registers a new working directory mid-session. Not checked yet Adds mcp_server_errors field to the headless stream-json init event, listing --mcp-config entries skipped by config validation; terminal runs surface a startup warning. Not checked yet Adds workflowSizeGuideline settings key so the Dynamic workflow size advisory can be set from any settings file (hides the /config row while active). Not checked yet
+4 more
show less
Adds nested subagent forwarding in stream-json: depth-2+ subagents now appear in the stream when --forward-subagent-text is set, keyed by their spawning Agent tool_use id. Not checked yet Subagents can now spawn nested subagents up to depth 3 (was 1); set CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH=1 to revert to flat spawning. Not checked yet Adds current default workflow size to the running-workflow status line with a pointer to /config for changes. Not checked yet Removes Opus 4.7 from fast mode; /fast now applies to Opus 5 and Opus 4.8 only. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! Opus 4.7 is removed from fast mode; /fast now applies only to Opus 5 and Opus 4.8.! Dynamic workflows now default to a medium size guideline (fewer than 15 agents); workflows relying on the previous unrestricted default will be subject to this new cap unless overridden in /config.! Managed MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. allowlist/denylist ${VAR} entries now resolve from the startup environment and managed-settings env instead of the settings-file env, which may change which values are substituted.
Claude Code v2.1.218 runs /code-review as a background subagent, adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. error details, and expands auto-mode intelligence.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.218 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.218
└──▷ USE IT
Opt a forked skill back into foreground execution when it must block the conversation before continuing.
yaml
copy
# In your skill's frontmatter:
---
context: fork
background: false
---
Runs /code-review as a background subagent so review output no longer floods the conversation and stacked slash commands stay on target. Not checked yet Adds HTTP status codes and error text to claude mcp list and /mcp when a server fails to connect, plus a warning for MCP config values with hidden leading or trailing whitespace. Not checked yet Adds screen-reader announcements of deleted text for word and line deletions (Option+Delete , Ctrl+W , Cmd+Backspace , Ctrl+U , Ctrl+K ) in --ax-screen-reader mode. Not checked yet Announces fast-mode changes when switching models via /config model=<x> or Remote Control. Not checked yet Changes /deep-research to start only on explicit invocation — Claude no longer launches it autonomously. Not checked yet
+6 more
show less
Auto mode now routes dangerous-rm, background-&, and suspicious-Windows-path checks through the auto-mode classifier instead of opening permission dialogs. Not checked yet Plan mode with auto no longer prompts for Bash commands the static analyzer can't prove read-only; the auto-mode classifier judges them instead. Not checked yet Skills with context: fork now run in the background by default; individual skills can opt out with background: false in frontmatter. Not checked yet Expands accepted frontmatter boolean values for skills and plugins to include yes/no/on/off/1/0 (case-insensitive) alongside true/false. Not checked yet Agent markdown files now reject agent names containing :, reserving that character for plugin namespacing. Not checked yet Server-managed settings changes for benign feature and cost toggles no longer trigger the settings-approval prompt. Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! Agent markdown files with names containing : are now rejected; any agent whose name includes : must be renamed before it will load.! Skills with context: fork now run in the background by default; skills that must run in the foreground need background: false added to their frontmatter.
Claude Code v2.1.217 adds emoji autocomplete, subagent concurrency controls, and AWS gateway deployment assets.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.217 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.217
└──▷ TRY IT
Cap parallel subagents to a lower value in resource-constrained CI environments to prevent runaway agent fan-out.
copy
$ CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS=5 claude
Allow nested subagent spawning up to two levels deep for multi-stage agentic workflows that require it.
copy
$ CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH=2 claude
Adds emoji shortcode autocomplete in the prompt input (type :heart: to insert or :hea for suggestions); disable with the emojiCompletionEnabled setting. Not checked yet Adds visible warnings when transcript writes are failing (e.g. disk full) or when session saving is disabled via an inherited environment variable, preventing silent transcript loss. Not checked yet Adds a cap on concurrently-running subagents (default 20), overridable with CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS, preventing unbounded agent fan-out from a single message. Not checked yet Adds CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH to control nested subagent depth; nested spawning is now disabled by default. Not checked yet Makes footer PR badge links clickable hyperlinks in environments where terminal support can't be detected (e.g. over SSH/tmux); opt out with FORCE_HYPERLINK=0. Not checked yet
+1 more
show less
Adds AWS reference deployment assets for Claude apps gateway on Bedrock under examples/gateway/aws/, including setup.sh, a distroless Dockerfile , gateway.yaml.example (Bedrock/Okta template), and a Terraform module. Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! Subagents no longer spawn nested subagents by default; existing workflows that relied on nested subagent spawning will stop working unless CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH is set to permit deeper nesting.
Claude Code v2.1.216 adds sandbox filesystem-isolation bypass, smarter /context warnings, and improved /fork, /ultrareview, and /code-review ultra feedback.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.216 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.216
└──▷ USE IT
Allow a sandboxed session to read/write the filesystem freely while still blocking unexpected network egress — useful when your task requires broad file access but you still want outbound network control.
json
copy
# In your Claude Code settings (e.g. .claude/settings.json)
{
"sandbox": {
"filesystem": {
"disabled": true
}
}
}
Adds sandbox.filesystem.disabled setting to skip filesystem isolation while keeping network egress control active. Not checked yet Adds explicit context-window overflow warning to /context and surfaces failed /compact as a visible error. Not checked yet Improves /fork confirmation to include the new session name, claude attach id, and whether the copy shares the checkout. Not checked yet Improves /ultrareview diff-too-large error to display configured limits, measured diff size, and the largest contributing files. Not checked yet Improves /code-review ultra empty-diff message to name the exact base ref and suggest passing an explicit base. Not checked yet
+3 more
show less
Improves spend-limit rejection prompt to show the server's stated reason. Not checked yet Background sessions: /mcp and /install-github-app now park a needs input request in the agent view when no client is attached. Not checked yet Adds safety guardrail to /rewind: skips files reachable via symlinks or hard links and reports how many paths were skipped. Not checked yet
8 details in Everything
Claude Code v2.1.215 makes /verify and /code-review user-invoked only — no more automatic runs.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.215 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.215
└──▷ TRY IT
Manually trigger a code review after making changes, instead of waiting for Claude to decide to run it automatically.
Run verification on demand after a refactor to confirm correctness on your own schedule.
The /verify and /code-review slash commands now run only on explicit user invocation, giving practitioners full control over when those checks execute. Not checked yet
1 detail in Everything
└──▷ BREAKING ON UPGRADE
! Claude no longer automatically runs the /verify and /code-review skills; any workflow that relied on Claude triggering these autonomously must now invoke /verify or /code-review explicitly.
Claude Code now runs in the browser and mobile app with --cloud flag for remote, parallel, and local-setup-free tasks.
└──▷ TRY IT
Start a cloud-hosted Claude Code session to work on a remote repo or run a long task without local setup.
New --cloud flag runs Claude Code sessions remotely in the browser with no local setup required. Not checked yet Supports long-running async tasks — kick off work and check back when done. Not checked yet Enables working on repos not cloned locally via cloud-hosted sessions. Not checked yet Run multiple Claude Code tasks in parallel via the cloud mode. Not checked yet Available on desktop browsers and the Claude mobile app (iOS and Android). Not checked yet
5 details in Everything
Claude Code adds a cloud/browser mode for running long-running tasks without local setup, accessible on desktop and mobile.
└──▷ TRY IT
Start a cloud-based Claude Code session when you don't have a repo locally or want to hand off a long-running task and check back later.
New --cloud flag launches Claude Code in-browser with no local environment required, enabling long-running async tasks and parallel workstreams. Not checked yet Supports working on repos you don't have checked out locally via the cloud runtime. Not checked yet Cloud sessions are accessible from the Claude mobile app on iOS and Android, letting you kick off tasks on desktop and check back from mobile. Not checked yet
3 details in Everything
Claude Code v2.1.214 adds EndConversation tool, OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. message correlation attributes, docker daemon-redirect permission prompts, and more.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.214 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.214
└──▷ TRY IT
Cap OTel content attribute size below the default 60 KB to stay within your observability backend's event-size limits.
copy
$ CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTH=16384 claude
Adds the EndConversation tool so Claude can autonomously terminate sessions involving highly abusive users or jailbreak attempts. Not checked yet Adds a periodic progress heartbeat for long-running tool calls that previously went silent. Not checked yet Adds an ISO ISO A widely adopted international standards body that publishes technical specifications; cyber tools cite ISO standards to signal compliance with recognized benchmarks for quality, security, or interoperability. modified timestamp to memory file frontmatter. Not checked yet Adds message.uuid, client_request_id, and tool_source attributes to OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. log events for message-level correlation and tool provenance provenance Evidence recording where a software artifact came from and how it was built, including its source and build process. It helps a consumer check that the artifact matches a trusted build. . Not checked yet Adds CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTH environment variable to configure the 60 KB truncation limit on OpenTelemetry content attributes. Not checked yet
+2 more
show less
Adds reasoning effort to the subagentStatusLine payload so custom agent rows can render model and effort. Not checked yet Adds permission prompts for docker commands (including the Podman docker shim) carrying daemon-redirect flags (--url, --connection, --identity, and Podman's remote mode). Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! Single-segment dir/** hook if: conditions now match only <cwd>/dir; write **/dir/** to match at any depth.! file commands using -m/--magic-file or -f/--files-from now require permission instead of being auto-allowed as read-only.! SessionStart hooks now report source "fork" when a session begins as a fork instead of "resume".
Claude Code v2.1.212 adds background /fork, auto-mode reset, per-session WebSearch/subagent caps, and auto-backgrounding slow MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. calls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.212 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.212
└──▷ TRY IT
Reset auto-mode to its defaults non-interactively in a script or CI context.
copy
$ claude auto-mode reset --yes
Cap WebSearch calls and subagent spawns to tighter limits for a long-running autonomous session to prevent runaway loops.
copy
$ CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION=50 CLAUDE_CODE_MAX_SUBAGENTS_PER_SESSION=20 claude
Lower the MCP auto-background threshold to 30 seconds so slow MCP calls yield the session sooner.
copy
$ CLAUDE_CODE_MCP_AUTO_BACKGROUND_MS=30000 claude
Redesigns /fork to copy the current conversation into a new background session (visible in claude agents) rather than an in-session subagent; the old in-session subagent behavior is now /subtask. Not checked yet Adds claude auto-mode reset command to restore default auto-mode configuration, with an optional --yes flag to skip the confirmation prompt. Not checked yet Adds a per-session WebSearch call cap (default 200, tunable via CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION) to prevent runaway search loops. Not checked yet Adds a per-session subagent spawn cap (default 200, override via CLAUDE_CODE_MAX_SUBAGENTS_PER_SESSION); /clear resets the budget. Not checked yet MCP tool calls exceeding 2 minutes automatically move to the background to keep the session responsive; threshold is configurable or disableable via CLAUDE_CODE_MCP_AUTO_BACKGROUND_MS. Not checked yet
+8 more
show less
Typing /resume in the agent view now opens a session picker — including previously deleted sessions — and resumes the chosen session as a background session. Not checked yet Improves prompt caching: mid-conversation system block now works behind LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. gateways and custom base URLs (Bedrock, Vertex, 1P). Not checked yet Reduces token usage in inter-agent messaging by no longer duplicating SendMessage bodies into replayed history and tool results. Not checked yet Extends Enterprise forceLoginMethod enforcement to VS Code extension, SDK, setup-token, and install-github-app logins. Not checked yet Headless/SDK sessions now apply a set_model control request mid-turn so the next LLM round-trip uses the new model immediately. Not checked yet Agent view and claude agents --json now show sessions waiting on a sandbox, MCP-input, or managed-settings prompt as Needs input instead of Working . Not checked yet Session transcripts now record the reasoning effort level on each assistant message. Not checked yet Background agent cold-attach now instantly renders the formatted transcript while the session boots, eliminating the blank-wait screen. Not checked yet
13 details in Everything
└──▷ BREAKING ON UPGRADE
! The Task tool's mode parameter is now ignored; subagents inherit the parent session's permission mode by default.
Claude Code v2.1.211 adds subagent stream visibility, cross-worktree permission persistence, and scientific-notation env vars.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.211 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.211
└──▷ TRY IT
Capture subagent reasoning in a CI pipeline that parses stream-json to audit what sub-tasks were run.
copy
$ claude --output-format stream-json --forward-subagent-text -p 'Refactor the auth module and write tests' | tee agent-stream.ndjson
Override a token-budget environment variable using scientific notation — useful in shell configs where large numbers are error-prone.
copy
$ CLAUDE_CODE_MAX_OUTPUT_TOKENS=1e6 claude -p 'Summarize the entire repo'
Adds --forward-subagent-text flag and CLAUDE_CODE_FORWARD_SUBAGENT_TEXT env var to surface subagent text and thinking inside --output-format stream-json output. Not checked yet Changes always allow permission rules to save at the repository root, so approvals granted in one git worktree persist across all worktrees and sessions. Not checked yet Accepts scientific notation and digit-separator spellings (e.g. 1e6, 64_000) for integer environment variables such as timeouts, token budgets, and retry counts. Not checked yet Enables save_to_disk on Claude-in-Chrome screenshot actions to actually write the image to disk and return its path. Not checked yet Improves background agent result reporting so Claude waits for real completion and reports still-running agents instead of fabricating results. Not checked yet
+3 more
show less
Adds Vim NORMAL-mode support for s (substitute char) and S (substitute line) in the editor input. Not checked yet Improves the memory index over-limit warning to measure only loaded content, excluding frontmatter and HTML comments. Not checked yet Changes /usage-credits to require confirmation before sending a request to organization admins. Not checked yet
8 details in Everything
Claude Code v2.1.210 adds a live tool timer, memory overflow errors, screen-reader mode announcements, and agent input-waiting counts.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.210 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.210
Adds a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of appearing frozen. Not checked yet Adds a startup warning when permission rules use Write(path) , NotebookEdit(path) , or Glob(path) — directing users to Edit(path) or Read(path) instead. Not checked yet Memory writes that would push a MEMORY.md index over its read limit now surface an explicit error instead of silently truncating content. Not checked yet Screen reader mode now announces permission mode changes aloud when cycling through modes with Shift+Tab. Not checked yet The agents footer hint now displays how many background agents are waiting on user input, with brief color emphasis when the count changes. Not checked yet
+3 more
show less
Hardens the Agent tool against indirect prompt injection indirect prompt injection An attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. via content read by a subagent. Not checked yet Improves auto mode: the permission classifier now defaults to Sonnet 5 for external sessions, validated on the first request and pinned for the session. Not checked yet Improves Bash/PowerShell timeout messaging so the model can distinguish a hung command from an intentional background request. Not checked yet
8 details in Everything
Claude Code v2.1.208 adds screen reader mode, vim insert remaps, corporate process wrapper, and fullscreen mouse support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.208 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.208
└──▷ TRY IT
Enable screen reader-compatible plain-text output for assistive technology users in a one-off session.
copy
$ claude --ax-screen-reader
Persist screen reader mode across all sessions via settings instead of passing the flag every time.
json
copy
# In your Claude Code settings (JSON)
{ "axScreenReader": true }
Route all Claude Code subprocess spawns through a corporate launcher in a managed enterprise environment.
copy
$ export CLAUDE_CODE_PROCESS_WRAPPER=/usr/local/bin/corp-launcher
claude
Adds --ax-screen-reader flag (also CLAUDE_AX_SCREEN_READER=1 env var or "axScreenReader": true in settings) for opt-in plain-text rendering compatible with screen readers. Not checked yet Adds vimInsertModeRemaps setting to map two-key vim insert-mode sequences (e.g. jj → Escape) without leaving the editor. Not checked yet Adds CLAUDE_CODE_PROCESS_WRAPPER env var so every Claude Code self-spawn routes through a corporate launcher executable, enabling enterprise wrapper enforcement. Not checked yet Adds mouse-click support for multi-select menus and Other input rows in fullscreen mode. Not checked yet Up to 7x faster tool rounds in print/SDK sessions with many MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools via cached tool-pool assembly. Not checked yet
+3 more
show less
Completed background agents now remain listed in /tasks until cleanup instead of disappearing immediately upon finishing. Not checked yet Catastrophic removals (e.g. rm -rf ~) inside command substitutions ($(…), backticks, <(…)) now prompt for confirmation in --dangerously-skip-permissions and auto mode. Not checked yet /usage now displays last-known usage bars with an as of timestamp when the usage endpoint is rate-limited, instead of an error screen. Not checked yet
8 details in Everything
Auto mode goes GA on Bedrock/Vertex/Foundry, Opus 4.8 becomes the default, and plugin config scoping tightens.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.207 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.207
└──▷ USE IT
Opt out of auto mode on a Bedrock or Vertex deployment where you want to keep manual control over model selection.
json
copy
# In ~/.claude/settings.json
{
"disableAutoMode": true
}
Migrate a per-repo auto mode override to the correct user-level settings file so it is still respected after this release.
json
copy
# Move autoMode from .claude/settings.local.json to ~/.claude/settings.json
{
"autoMode": "auto"
}
Update a plugin hook that previously used shell-form ${user_config.*} to the new exec-form with $CLAUDE_PLUGIN_OPTION_<KEY> to avoid the shell-injection rejection.
json
copy
# Before (now rejected):
# command: "my-hook --token ${user_config.api_token}"
# After — exec form with env var:
{
"args": ["my-hook", "--token"],
"env": { "TOKEN": "$CLAUDE_PLUGIN_OPTION_API_TOKEN" }
}
Auto mode is now generally available on Bedrock, Vertex AI, and Foundry without the CLAUDE_CODE_ENABLE_AUTO_MODE opt-in flag; disable it via disableAutoMode in settings. Not checked yet Bedrock, Vertex, and Claude Platform on AWS now default to Claude Opus 4.8. Not checked yet Auto mode config is now read exclusively from ~/.claude/settings.json; the repo-resident .claude/settings.local.json autoMode key is no longer honored (breaking change for teams using per-repo overrides). Not checked yet Plugin option values (pluginConfigs) are no longer read from project-level .claude/settings.json; only user-level, --settings, and managed settings are honored (breaking change for project-scoped plugin configs). Not checked yet Plugin hooks/monitors/MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. headersHelper: ${user_config.*} interpolation in shell-form commands is now rejected; hooks must use exec form (args array) or $CLAUDE_PLUGIN_OPTION_<KEY> env vars instead (breaking change). Not checked yet
+2 more
show less
/doctor now reports when the launcher at ~/.local/bin/claude is externally managed (e.g. a custom script or symlink). Not checked yet Amounts over $1,000 in /usage-credits now require a typed confirmation, and malformed inputs are rejected with an error rather than silently stripped. Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! Auto mode no longer reads autoMode from .claude/settings.local.json (repo-resident); use ~/.claude/settings.json instead! ${user_config.*} in shell-form commands for plugin hooks/monitors/MCP headersHelper is now rejected; hooks must use exec form (args array) or $CLAUDE_PLUGIN_OPTION_<KEY>; monitors and headersHelper must read the value inside the script! Plugin option values (pluginConfigs) are no longer read from project-level .claude/settings.json; only user, --settings, and managed settings are honored
Claude Code v2.1.206 adds smarter /cd suggestions, /doctor CLAUDE.md trimming, broader push-remote support, and faster background agent upgrades.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.206 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.206
└──▷ TRY IT
Identify and trim bloated CLAUDE.md files before committing them — useful when onboarding a repo where the memory file has grown to repeat what the codebase already shows.
Push and open a PR from a repo whose push remote is set to something other than origin (e.g. a fork workflow with remote.pushDefault=upstream) without manually allowing the remote first.
Adds directory path tab-completion to /cd, matching the existing /add-dir behavior. Not checked yet New /doctor check analyzes checked-in CLAUDE.md files and proposes trimming content Claude can already derive from the codebase. Not checked yet Extends /commit-push-pr to auto-allow git push to the repo's configured remote.pushDefault (or the sole remote when only one exists), not just origin. Not checked yet Enables /login to authenticate against Anthropic-operated public gateway endpoints. Not checked yet EnterWorktree now prompts for confirmation before entering a git worktree that lives outside the project's .claude/worktrees/ directory. Not checked yet
+3 more
show less
Background agents now upgrade to the latest Claude Code version immediately after an update, eliminating slow upgrade delays when you attach to a stale session. Not checked yet Agents view status column now uses the full terminal width instead of truncating at 64 characters. Not checked yet Adds Ctrl+X in the agents view to permanently remove a completed session; deleted background jobs now stay deleted across renders. Not checked yet
8 details in Everything
Claude Code v2.1.205 upgrades /doctor into a full setup checkup, hardens auto mode safety rules, and improves the agents view.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.205 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.205
└──▷ TRY IT
Run a full environment health check and let Claude Code automatically fix any issues it finds.
Review the enriched agent list — with colored state labels, classifier headlines, and PR links — for all background sessions.
Adds auto mode rule that blocks tampering with session transcript files. Not checked yet Improves auto mode to prompt for confirmation before running rm -rf on an unresolvable variable, reducing accidental data loss. Not checked yet Upgrades /doctor into a full setup checkup that can both diagnose and fix issues; adds /checkup as an alias. Not checked yet Enhances claude agents view: PR-linked sessions (edit, merge, comment, push) now surface the PR link directly in the list. Not checked yet Enhances claude agents view: rows show a colored state word and classifier-written headline instead of raw tool call text; peek view shows full status and the exact ask for blocked sessions. Not checked yet
+3 more
show less
Background task notifications now explicitly state no human input has occurred, preventing fabricated in-transcript approvals from being acted on. Not checked yet Streams auto-update binary downloads to disk instead of buffering in memory, cutting peak updater memory usage by ~400 MB. Not checked yet Reserves the Claude Browser MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server name (alongside Claude Preview ); user-configured MCP servers can no longer register under either name. Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! User-configured MCP servers can no longer register under the names Claude Browser or Claude Preview
Claude Code v2.1.203 adds login-expiry warnings, manual-mode visibility, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. roots updates, and a VSCode remote-control toggle.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.203 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.203
Adds a pre-expiry warning when your login session is about to expire, letting you re-authenticate before background sessions are interrupted. Not checked yet Adds a grey ⏸ badge in the footer when manual permission mode is active, so the current permission mode is always visible. Not checked yet Exposes the session's additional working directories in MCP roots/list, and sends notifications/roots/list_changed whenever that set changes — enabling MCP servers to stay in sync with multi-root workspaces. Not checked yet Changes the Escape key (instead of left arrow) to close background tasks, diff, and workflow detail views — practitioners must update muscle memory. Not checked yet Changes the empty claude agents view to always display organized sections (Needs Input / Working / Completed) with descriptions, even when no agents are running. Not checked yet
+2 more
show less
Moves startup 'claude command missing or broken' warnings out of the startup flow into /doctor and /status only. Not checked yet [VSCode] Adds a Settings toggle for Enable Remote Control for all sessions . Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! The left arrow key no longer closes the background tasks, diff, and workflow detail views — press Esc instead
Claude Code v2.1.202 adds dynamic workflow sizing, OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. workflow attributes, and a new /code-review command for multi-agent PR review.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.202 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.202
└──▷ TRY IT
Run a thorough multi-agent review on a PR when you want deeper analysis than the default single-pass review.
copy
$ /code-review high 4821
Tune agent parallelism for a complex workflow without hitting a hard cap — useful before kicking off a large refactor.
📍 /config
Adds a Dynamic workflow size setting in /config to guide how many agents Claude spawns for dynamic workflows (small/medium/large) — advisory, not an enforced cap. Not checked yet Adds workflow.run_id and workflow.name OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. attributes to telemetry from workflow-spawned agents, enabling full reconstruction of a workflow run from OTel data. Not checked yet Introduces /code-review <level> <pr#> for multi-agent PR review at a chosen effort level; /review <pr> reverts to a fast single-pass review. Not checked yet Improves /workflows agent list layout with wider titles, a dedicated time column, and shorter model names. Not checked yet Improves MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. error messages to suggest "type": "http" when a server config has url but no type. Not checked yet
5 details in Everything
Claude Code v2.1.200 makes Manual the default permission mode and adds opt-in idle timeout for user-question dialogs.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.200 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.200
└──▷ TRY IT
Enforce Manual permission mode explicitly in automation or shared configs to match the new canonical name.
copy
$ claude --permission-mode manual
Changes AskUserQuestion dialogs to no longer auto-continue by default; opt into an idle timeout via /config. Not checked yet Renames the default permission mode to Manual across CLI, --help, VS Code, and JetBrains; accepts --permission-mode manual and "defaultMode": "manual" as canonical values. Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! The AskUserQuestion dialogs no longer auto-continue by default; auto-continue must be explicitly opted into via /config! The default permission mode is renamed from default to Manual across the CLI, --help, VS Code, and JetBrains (though --permission-mode default and "defaultMode": "default" remain accepted alongside manual)
Stacked slash-skills (up to 5), auto-retry on 429s, and a raised retry ceiling via CLAUDE_CODE_MAX_RETRIES
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.199 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.199
└──▷ TRY IT
Apply multiple skills together in one prompt to layer context (e.g. a security-review skill and a repo-conventions skill) before asking Claude to act.
copy
$ /skill-security-review /skill-repo-conventions find all places we call eval() and suggest safer alternatives
On long-running agentic jobs in flaky network environments, raise the retry ceiling so transient 429s don't abort the session.
copy
$ CLAUDE_CODE_MAX_RETRIES=200 claude 'run the full test suite and summarise failures'
Supports stacking up to 5 slash-skill invocations in a single prompt (e.g. /skill-a /skill-b /skill-c do XYZ), loading all leading skills instead of just the first. Not checked yet Auto-retries transient server rate-limit errors (HTTP 429s unrelated to usage limits) with backoff for subscribers, instead of failing the turn. Not checked yet New CLAUDE_CODE_RETRY_WATCHDOG behavior raises the default retry count for non-capacity transient errors to 300 and removes the previous hard cap of 15 on CLAUDE_CODE_MAX_RETRIES. Not checked yet Idle surplus subagents in the agent panel now collapse into an expandable summary row instead of vanishing. Not checked yet
4 details in Everything
Claude Code v2.1.198 adds Chrome GA, automated draft PRs from background agents, /dataviz skill, and AWS gateway support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.198 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.198
└──▷ TRY IT
Get notified in your hook handler when a background agent needs input or completes, so you can automate follow-up actions.
copy
$ # In your Notification hook handler, inspect the event type:
# agent_needs_input — agent is waiting for a response
# agent_completed — agent finished its work
claude agents
Use the new /dataviz skill inside a session to get chart design guidance and validate color palettes for dashboards.
Launches Claude in Chrome as generally available. Not checked yet Adds agent_needs_input and agent_completed Notification hook events in claude agents so background sessions fire alerts when they need input or finish. Not checked yet New /dataviz skill provides chart and dashboard design guidance with a runnable color-palette validator. Not checked yet Adds Claude Platform on AWS (anthropicAws) as a gateway upstream provider; model-not-found responses now advance the failover chain instead of failing hard. Not checked yet Background agents launched from claude agents now automatically commit, push, and open a draft PR when they finish code work in a worktree. Not checked yet
+4 more
show less
Built-in Explore agent now inherits the main session's model (capped at opus) instead of always running on haiku. Not checked yet Subagents and context compaction context compaction Condensing an AI conversation or working history to free space in the model's context window. A summary preserves useful information, but details can be lost. now inherit the session's extended thinking extended thinking Intermediate reasoning a model writes out before its final answer. Reasoning models generate it automatically and it is often billed as extra output tokens. configuration, improving output quality on delegated tasks. Not checked yet Removes the /agents wizard; subagents are now created by asking Claude directly or editing .claude/agents/. Not checked yet Subagents now treat messages from their launching agent as normal task direction (never as user approval), clarifying the trust model. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! The --bg flag combined with --print/-p is now rejected up front instead of silently creating an unattachable session.! The /agents wizard has been removed; subagents must now be created by asking Claude or by editing .claude/agents/ directly.
Claude Code now defaults to Claude Sonnet 5 with a native 1M-token context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. and promotional pricing through August 31.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.197 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.197
Switches default model to Claude Sonnet 5, featuring a native 1M-token context window for working across very large codebases in a single session. Not checked yet Introduces promotional pricing of $2/$10 per million input/output tokens for Claude Sonnet 5 through August 31. Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! Claude Sonnet 5 is now the default model in Claude Code, replacing the previously default model
Claude Code v2.1.196 adds org-default models, clickable file attachments, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. security hardening, and an always-on stream watchdog.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.196 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.196
└──▷ TRY IT
Inspect which MCP servers are approved before trusting a cloned repo — untrusted servers now show as pending instead of silently starting.
Adds organization default model support — admins configure it in the org console and users see Org default or Role default in /model when no personal selection is made. Not checked yet Adds readable auto-generated names for sessions at startup, making sessions easier to identify and reference. Not checked yet Adds clickable file attachments in chat — Cmd/Ctrl-click a file to reveal it in Finder/Explorer. Not checked yet Security hardening: claude mcp list/get no longer auto-spawn MCP servers that a repo self-approved via a committed .claude/settings.json; untrusted workspaces now show a ⏸ Pending approval indicator instead. Not checked yet Enables the streaming idle watchdog by default for all providers — aborts and retries any response stream that produces no events for 5 minutes; set CLAUDE_ENABLE_STREAM_WATCHDOG=0 to opt out. Not checked yet
+4 more
show less
Disables Remote Control when ANTHROPIC_BASE_URL points at a non-Anthropic host, consistent with existing Bedrock/Vertex/Foundry behavior. Not checked yet Simplifies agents view navigation from a foreground session — now requires a single ← press instead of two. Not checked yet Improves /code-review workflow by consolidating five cleanup finders into one, cutting token usage by ~25%. Not checked yet Improves background agent resilience — workers killed by a daemon restart auto-resume from their last state when the agents view next opens. Not checked yet
9 details in Everything
Adds CLAUDE_CODE_DISABLE_MOUSE_CLICKS env var and remote session provisioning checklist in v2.1.195
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.195 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.195
└──▷ TRY IT
Prevent Claude Code's fullscreen UI from intercepting mouse clicks in a tmux or remote terminal session while still allowing scroll.
copy
$ CLAUDE_CODE_DISABLE_MOUSE_CLICKS=1 claude
Adds CLAUDE_CODE_DISABLE_MOUSE_CLICKS environment variable to suppress mouse click, drag, and hover events in fullscreen mode while preserving wheel scroll — useful when running Claude Code inside terminal multiplexers or remote sessions where mouse events conflict with the host terminal. Not checked yet Adds a provisioning checklist during Remote session startup so practitioners can track container initialization progress in real time. Not checked yet Hook matchers now require exact matching for hyphenated identifiers (e.g. mcp__brave-search); use mcp__brave-search__.* glob syntax to match all tools from a hyphenated MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server — a breaking change for any hooks relying on previous substring behavior. Not checked yet Linux voice mode now distinguishes between no microphone detected and SoX not installed when SoX is present but no audio capture device exists, enabling clearer troubleshooting for automated or headless environments. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! Hook matchers now exact-match hyphenated identifiers (e.g. code-reviewer, mcp__brave-search) instead of substring-matching; existing configurations that relied on substring matching must be updated to use explicit wildcards (e.g. mcp__brave-search__.*) to match all tools from a hyphenated MCP server.
Claude Code v2.1.193 adds shell classifier controls, OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. response logging, live path autocomplete, and memory-pressure reaping.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.193 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.193
└──▷ TRY IT
Enforce auto-mode classification on every shell command — useful in CI/enterprise deployments where you want consistent policy enforcement regardless of command pattern.
copy
$ claude config set autoMode.classifyAllShell true
Capture full conversation transcripts (prompts + responses) in your OTel pipeline for audit or observability — opt in explicitly so response text isn't silently included on upgrade.
copy
$ OTEL_LOG_ASSISTANT_RESPONSES=1 claude
Run Claude Code in memory-constrained environments without the automatic background-shell reaper interfering with long-running idle shells you want to keep alive.
copy
$ CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP=1 claude
New autoMode.classifyAllShell setting routes all Bash/PowerShell commands through the auto-mode classifier, not just arbitrary-code-execution patterns. Not checked yet Surfaces auto-mode denial reasons in the transcript, denial toast, and /permissions recent-denials view. Not checked yet New claude_code.assistant_response OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. log event captures model response text (redacted by default; enable with OTEL_LOG_ASSISTANT_RESPONSES=1). Not checked yet Adds live file-path autocomplete when typing in bash mode (!). Not checked yet Startup notice now appears when MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers require authentication, directing users to /mcp. Not checked yet
+4 more
show less
Automatic memory-pressure reaping terminates idle background shell commands to reclaim resources (disable with CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP=1). Not checked yet Background agents now continue working on additional tasks after launching a sub-agent instead of being instructed to end their response. Not checked yet MCP headersHelper auth automatically re-runs and reconnects when a tool call returns a 401/403. Not checked yet Plugin auto-rename now follows marketplace renames maps, automatically updating settings to the new plugin name. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! Deployments that already log prompt content via OTEL_LOG_USER_PROMPTS will automatically start receiving assistant response content in claude_code.assistant_response OpenTelemetry log events on upgrade; set OTEL_LOG_ASSISTANT_RESPONSES=0 to keep prompts-only logging.
Claude Code v2.1.191 adds /rewind for post-clear conversation recovery and cuts streaming CPU CPU The main general-purpose processor in a computer. It runs application instructions and coordinates work with memory and other hardware. usage by ~37%.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.191 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.191
└──▷ TRY IT
Recover context after accidentally running /clear mid-session — rewind to the last pre-clear state and continue where you left off.
Adds /rewind command to resume a conversation from the state before /clear was last run, enabling recovery of cleared context. Not checked yet Sandbox network permission dialog now remembers hosts approved with Yes for the entire session, eliminating repeated prompts for the same host. Not checked yet MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. capability discovery (tools/list, prompts/list, resources/list) now retries on transient network errors with backoff, improving server reliability. Not checked yet MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. in headless environments skips the browser popup and goes directly to a paste-the-URL prompt. Not checked yet MCP HTTP 404 errors now surface the failing URL and link to the MCP config for faster troubleshooting. Not checked yet
+2 more
show less
Reduces streaming response CPU usage by ~37% via 100ms text-update coalescing, enabling longer uninterrupted agentic sessions. Not checked yet Reduces memory growth in long sessions by optimizing the terminal output cache. Not checked yet
7 details in Everything
Claude Code v2.1.187 adds credential sandboxing sandboxing Running code inside a restricted environment that limits what it can access or change. The isolation reduces the impact of mistakes or untrusted code, depending on the sandbox's controls. , org model restrictions, mouse support in fullscreen, and UX improvements to /btw, /plugin, and /install-github-app.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.187 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.187
└──▷ TRY IT
Prevent sandboxed subcommands from exfiltrating credentials or secret env vars — useful when running untrusted or AI-generated shell commands.
copy
$ claude config set sandbox.credentials false
Adds sandbox.credentials setting to block sandboxed commands from reading credential files and secret environment variables. Not checked yet Adds org-configured model restrictions enforced across the model picker, --model, /model, and ANTHROPIC_MODEL, with a clear 'restricted by your organization's settings' message. Not checked yet Adds mouse click support for selecting menus (permission prompts, /model, /config, etc.) in fullscreen mode. Not checked yet Improves /install-github-app so GitHub Actions GitHub Actions GitHub's built-in CI/CD system that runs automated workflows triggered by repository events, letting cyber tools automate testing, building, and releasing without managing separate pipeline infrastructure. workflow setup is now optional — install just the GitHub App without configuring the workflow or secrets. Not checked yet Improves /btw with ←/→ arrow navigation to step through earlier answers. Not checked yet
+1 more
show less
Improves /plugin to surface recently unused plugins so practitioners can clean them up. Not checked yet
6 details in Everything
Claude Code v2.1.186 adds CLI MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. auth commands, bash auto-response, AWS credential refresh, and subagent permission surfacing.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.186 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.186
└──▷ TRY IT
Authenticate an MCP server over an SSH session where a browser cannot open — complete the OAuth flow via stdin redirect instead.
copy
$ claude mcp login my-server --no-browser
Use CLAUDE_CODE_RETRY_WATCHDOG instead of CLAUDE_CODE_MAX_RETRIES for robust unattended CI/CD pipeline runs now that the latter is capped at 15.
copy
$ CLAUDE_CODE_RETRY_WATCHDOG=1 claude --print 'run the full test suite and fix any failures'
Adds claude mcp login <name> and claude mcp logout <name> commands to authenticate MCP servers directly from the CLI, with --no-browser stdin redirect for SSH sessions. Not checked yet Enables ! bash commands to automatically trigger Claude to respond to their output; disable with "respondToBashCommands": false in settings.json to restore context-only behavior. Not checked yet Adds status filtering (press f) to the /workflows agent detail view for narrowing displayed agents by state. Not checked yet Adds a Skills section to the /plugin Installed tab for visibility into installed skills. Not checked yet Adds teammateMode: "iterm2" setting for iTerm2 pane-based teammate integration, with a warning when the it2 CLI cannot be found. Not checked yet
+6 more
show less
Adds a 'Claude Platform on AWS - refresh credentials' option to /login when awsAuthRefresh is configured. Not checked yet Surfaces background subagent permission prompts in the main session instead of auto-denying them; the dialog identifies which agent is requesting, and Esc denies only that tool. Not checked yet Changes /review <pr> to use the same engine as /code-review medium for consistent PR review quality. Not checked yet Caps CLAUDE_CODE_MAX_RETRIES at 15; introduces CLAUDE_CODE_RETRY_WATCHDOG as the recommended alternative for unattended sessions. Not checked yet Supports kebab-case, snake_case, and camelCase for skill frontmatter keys (display-name, default-enabled, fallback, metadata.*). Not checked yet Loads malformed SKILL.md YAML frontmatter with empty metadata instead of silently failing, surfacing skills even when their headers are broken. Not checked yet
11 details in Everything
└──▷ BREAKING ON UPGRADE
! The ! bash commands now trigger Claude to respond to the output automatically by default; set "respondToBashCommands": false in settings.json to keep the previous context-only behavior! CLAUDE_CODE_MAX_RETRIES is now capped at 15; unattended sessions relying on higher values must switch to CLAUDE_CODE_RETRY_WATCHDOG instead
Claude Code v2.1.183 adds auto-mode guardrails against destructive commands, attribution controls, and improved /config UX.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.183 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.183
└──▷ TRY IT
Discover all shorthand config keys you can set inline without navigating the interactive menu.
Adds auto-mode safety guardrails that block destructive git commands (git reset --hard, git checkout -- ., git clean -fd, git stash drop) unless you explicitly asked to discard local work, blocks git commit --amend on commits not made by the agent this session, and blocks terraform destroy/pulumi destroy/cdk destroy unless a specific stack was requested. Not checked yet Adds deprecation warnings when a requested model is deprecated or auto-upgraded, surfaced on stderr in print mode (-p) and now also covering models set in agent frontmatter. Not checked yet New attribution.sessionUrl setting lets you omit the claude.ai session link from commits and PRs in web and Remote Control sessions. Not checked yet New /config --help subcommand lists all available shorthand keys for use with /config key=value. Not checked yet Updated /config toggle behavior: Enter and Space both toggle the selected setting; Esc now saves and closes (previously reverted changes). Not checked yet
+1 more
show less
Removes the startup setup issues line from under the logo — configuration issues are now surfaced on demand via /doctor or --debug. Not checked yet
6 details in Everything
Claude Code v2.1.181 adds inline /config setting, Apple Events sandbox opt-in, and presence-based push notification suppression.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.181 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.181
└──▷ TRY IT
Toggle extended thinking extended thinking Intermediate reasoning a model writes out before its final answer. Reasoning models generate it automatically and it is often billed as extra output tokens. off mid-session without leaving the prompt — useful when you want faster, cheaper responses for a straightforward task.
copy
$ /config thinking=false
Suppress mobile push notifications automatically while you're at your workstation by pointing Claude Code at a marker file your session manager creates on login.
copy
$ CLAUDE_CLIENT_PRESENCE_FILE=~/.at-desk claude
Adds /config key=value slash command to set any Claude Code setting mid-session from the prompt (e.g. /config thinking=false), usable in interactive mode, -p, and Remote Control. Not checked yet Adds sandbox.allowAppleEvents opt-in setting so sandboxed commands can send Apple Events on macOS — enables osascript and similar automation inside the sandbox. Not checked yet Adds CLAUDE_CLIENT_PRESENCE_FILE environment variable to suppress mobile push notifications when a specified marker file is present, signaling you're already at the machine. Not checked yet Upgrades bundled Bun runtime to 1.4. Not checked yet Enables auto-retry on API connection drops mid-thinking, eliminating manual intervention when the connection closes during extended reasoning. Not checked yet
+3 more
show less
Improves subagent panel UX: idle subagents auto-hide after 30 seconds, list caps at 5 rows with scroll hints, and keyboard hints appear in the footer. Not checked yet Changes fullscreen mode URL opening to require Cmd+click (macOS) / Ctrl+click, aligning with native terminal behavior. Not checked yet Improves long-paragraph streaming so text appears line-by-line rather than waiting for the first line break. Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! Fullscreen mode URL opening now requires Cmd+click (macOS) / Ctrl+click instead of a plain click, matching native terminal behavior
Claude Code v2.1.178 adds parameter-scoped permission rules, nested skills/config resolution, and streamlined agent teams.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.178 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.178
└──▷ TRY IT
Block subagents from spawning with a specific model (e.g. Opus) by adding a parameter-scoped deny rule to your permission config.
copy
$ claude --disallow-tool 'Agent(model:opus)' "Refactor the auth module"
Spawn a named teammate directly without a team-setup step when agent teams are enabled.
copy
$ CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 claude "Use the Agent tool with name:reviewer to audit my PR diff"
Adds Tool(param:value) syntax for permission rules to match a tool's input parameters with * wildcard support — e.g. Agent(model:opus) to block Opus subagents. Not checked yet Supports skills in nested .claude/skills directories, loading them automatically when working in that subtree; name clashes surface as <dir>:<name> so both remain accessible. Not checked yet Nearest-wins resolution for nested .claude/ directories: the agent, workflow, and output-style closest to the working directory take precedence on name collisions; project-scope workflow saves target the closest existing .claude/workflows/. Not checked yet Strengthens auto mode by evaluating subagent spawns through the classifier before launch, closing a gap where a subagent could request a blocked action without review. Not checked yet Removes TeamCreate and TeamDelete tools for agent teams Experimental : with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1, every session now has one implicit team — spawn teammates directly via the Agent tool's name parameter. Not checked yet
+3 more
show less
Enhances /doctor with a consistent flat tree layout, clearer section status icons, and highlighted command names. Not checked yet Changes the workflow prompt keyword to use a purple shimmer highlight and trigger only on explicit phrases like run a workflow or "workflow:", not on any mention of the word. Not checked yet Improves Remote Control error messages: connection failures show a persistent red /rc failed footer indicator, and the not yet enabled error now explains whether the cause is a gate, check failure, stale entitlement, or org policy. Not checked yet
8 details in Everything
Claude Code v2.1.176 adds language-aware session titles, footer link badges, and smarter Bedrock credential caching.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.176 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.176
Session titles are now generated in the language of the conversation; pin a specific language with the language setting. Not checked yet New footerLinksRegexes setting lets you add regex-matched link badges to the footer row via user or managed settings. Not checked yet
2 details in Everything
Claude Code adds enforceAvailableModels managed setting to lock model selection within admin-defined allowlists.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.175 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.175
└──▷ USE IT
Lock an enterprise deployment so users can never select a model outside the admin-approved list, even via project or user settings.
json
copy
{
"enforceAvailableModels": true,
"availableModels": ["claude-3-5-sonnet-20241022", "claude-3-haiku-20240307"]
}
Adds enforceAvailableModels managed setting that forces the Default model to fall back to the first allowed model when it would otherwise resolve to a disallowed model, and prevents users or projects from widening a managed availableModels list. Not checked yet
1 detail in Everything
Claude Code v2.1.174 adds wheel-scroll acceleration control and detailed VS Code usage attribution breakdowns.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.174 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.174
└──▷ HOW TO FIND IT
Review where your token spend is going — broken down by subagents, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools, skills, and context size — without leaving VS Code.
📍 In VS Code, open the Claude Code panel, then run /usage to open the Account & usage dialog showing the last 24h or 7d breakdown.
Adds wheelScrollAccelerationEnabled setting to disable mouse-wheel scroll acceleration in fullscreen mode. Not checked yet Adds usage attribution panel in the VS Code Account & usage dialog (/usage) showing cache misses, long context, subagents, and per-skill/agent/plugin/MCP breakdowns over the last 24h or 7d. Not checked yet
2 details in Everything
Claude Code v2.1.172 adds recursive sub-agents (5 levels deep), Bedrock region auto-detection, plugin search, and a new OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. model attribute.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.172 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.172
└──▷ TRY IT
Inspect which AWS region Bedrock is using and where it came from, without needing to set AWS_REGION explicitly.
Filter a long marketplace plugin list without scrolling through every entry.
📍 /plugin
Enables sub-agents to spawn their own sub-agents, up to 5 levels of nesting. Not checked yet Amazon Bedrock now auto-detects AWS region from ~/.aws config files following AWS SDK precedence when AWS_REGION is unset; /status shows the region source. Not checked yet Adds a search bar inside the /plugin marketplace browser for filtering plugins. Not checked yet Adds a model attribute to the claude_code.lines_of_code.count OTEL metric, enabling per-model telemetry breakdowns. Not checked yet
4 details in Everything
Claude Code v2.1.170 adds access to Claude Fable 5, Anthropic's most capable generally available model.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.170 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.170
Claude Code v2.1.169 adds --safe-mode, /cd command, and disableBundledSkills for cleaner troubleshooting and session control.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.169 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.169
└──▷ TRY IT
Troubleshoot a misbehaving setup by launching Claude Code with all customizations stripped out — no CLAUDE.md, hooks, plugins, or MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers.
copy
$ claude --safe-mode
Switch your active session to a different project directory without losing prompt cache continuity.
copy
$ /cd ~/projects/other-repo
List all background agent sessions — including completed ones — with their IDs and states for scripting or monitoring pipelines.
copy
$ claude agents --json --all
Adds --safe-mode flag (and CLAUDE_CODE_SAFE_MODE env var) to launch with all customizations disabled — CLAUDE.md, plugins, skills, hooks, and MCP servers — for clean troubleshooting. Not checked yet Adds /cd command to change the working directory mid-session without breaking the prompt cache. Not checked yet Adds disableBundledSkills setting and CLAUDE_CODE_DISABLE_BUNDLED_SKILLS env var to hide bundled skills, workflows, and built-in slash commands from the model. Not checked yet Adds --all flag to claude agents --json to include completed sessions; also surfaces new id and state fields on each session entry. Not checked yet The claude agents --json command now correctly includes blocked and just-dispatched background sessions. Not checked yet
+5 more
show less
Background sessions now preserve --ide, --chrome, --bare, --remote-control, and other flags across retire→wake cycles. Not checked yet Remote-managed settings with an invalid entry now apply remaining valid policies and surface the validation error instead of silently dropping the whole payload. Not checked yet /workflows command now opens immediately even while a turn is in progress. Not checked yet The CLAUDE.md is too long warning threshold now scales with the model's context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. . Not checked yet Adds a tip suggesting claude agents when running multiple concurrent sessions. Not checked yet
10 details in Everything
Claude Code v2.1.166 adds fallback model chains, glob-based tool deny rules, and hardened cross-session security.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.166 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.166
└──▷ TRY IT
Run a model that thinks by default without extended thinking extended thinking Intermediate reasoning a model writes out before its final answer. Reasoning models generate it automatically and it is often billed as extra output tokens. to reduce latency and token cost.
copy
$ MAX_THINKING_TOKENS=0 claude -p "Analyze this code for vulnerabilities" < main.go
Adds fallbackModel setting to configure up to three fallback models tried in order when the primary model is overloaded or unavailable; --fallback-model now also applies to interactive sessions. Not checked yet Adds glob pattern support in deny rule tool-name position ("*" denies all tools); allow rules reject non-MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. globs, and unknown tool names in deny rules warn at startup. Not checked yet Hardens cross-session messaging: messages relayed via SendMessage from other Claude sessions no longer carry user authority — receivers refuse relayed permission requests, and auto mode blocks them. Not checked yet Enables disabling thinking on models that think by default via the Claude API using MAX_THINKING_TOKENS=0, --thinking disabled, or the per-model thinking toggle (3P providers unchanged). Not checked yet Retries a turn once on the fallback model when the API rejects an unexpected non-retryable error; auth, rate-limit, request-size, and transport errors still surface immediately. Not checked yet
+2 more
show less
claude update now announces the target version before downloading. Not checked yet In claude agents, typing a URL into the session list now filters to the session whose first prompt contained it. Not checked yet
7 details in Everything
Claude Code v2.1.163 adds version enforcement settings, /plugin list, hook feedback context, and stdio MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. session IDs.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.163 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.163
└──▷ USE IT
Enforce an approved version range across a managed fleet so users on out-of-range builds are blocked at startup.
json
copy
{
"requiredMinimumVersion": "2.1.163",
"requiredMaximumVersion": "2.1.999"
}
Audit which plugins are active in the current session — useful after an update or policy change.
copy
$ /plugin list --enabled
Surface stop-hook diagnostics back to Claude (e.g. a linter summary) so it can react without the run being marked as a hook error.
json
copy
{
"hookSpecificOutput": {
"additionalContext": "Linter found 3 warnings in src/main.ts — please review before finishing."
}
}
Adds requiredMinimumVersion and requiredMaximumVersion managed settings to enforce a permitted Claude Code version range, refusing startup if the installed version falls outside it. Not checked yet New /plugin list command lists installed plugins, with --enabled/--disabled filters to narrow results. Not checked yet Adds a c to copy shortcut in /btw that copies the raw markdown answer to the clipboard, preserving formatting on paste. Not checked yet Skills: new \$ escape syntax lets command bodies include a literal $ before a digit. Not checked yet stdio MCP servers now receive the same CLAUDE_CODE_SESSION_ID environment variable as hooks and Bash when using --resume. Not checked yet
+1 more
show less
Background agent sessions now update to a new Claude Code version silently in the background, eliminating cold-restart wait times when reopening a session after an update. Not checked yet
6 details in Everything
claude agents gets richer status info, --tools Grep/Glob now works on native builds, and /effort persists as default.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.162 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.162
└──▷ TRY IT
Poll agent session status in CI/automation to detect which sessions are blocked waiting for a permission prompt.
copy
$ claude agents --json | jq '.[] | select(.waitingFor != null) | {id, waitingFor}'
Restrict Claude Code to only built-in Grep and Glob search tools on a native build — previously listing these names was silently ignored.
copy
$ claude --tools Grep,Glob
Adds waitingFor field to claude agents --json output, showing what a waiting session is blocked on (e.g. a permission prompt). Not checked yet Explicitly listing Grep or Glob in --tools now activates the dedicated embedded search tools on native builds (previously silently ignored). Not checked yet The /effort command now confirms when the chosen level will persist as the default for new sessions. Not checked yet Clicking a slash command in the autocomplete menu fills it into the prompt instead of running it immediately — press Enter to run. Not checked yet Remote Control status is now shown as a persistent footer pill with a session link instead of a one-time startup message. Not checked yet
+2 more
show less
Launch-prompt warnings (deep link/pre-filled prompt) now stay pinned below the input until acted upon instead of scrolling away. Not checked yet Background service startup and claude update now wait for endpoint-security scanning of new binaries instead of timing out after 5 seconds. Not checked yet
7 details in Everything
Claude Code v2.1.161 adds OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. label slicing, smarter agents UI, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector collapsing, and independent parallel tool results.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.161 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.161
└──▷ TRY IT
Slice Claude Code usage metrics by team or repo in your OTEL backend without any code changes — just set resource attributes before launching.
copy
$ OTEL_RESOURCE_ATTRIBUTES="team=security,repo=infra-scanner" claude <prompt>
Adds OTEL_RESOURCE_ATTRIBUTES values as labels on metric datapoints, enabling usage metrics to be sliced by custom dimensions like team or repo. Not checked yet Shows done/total progress before detail text in claude agents rows when work is fanned out; peek view highlights the longest-running item. Not checked yet Collapses never-signed-in claude.ai connectors in /mcp behind a Show unused connectors row to reduce noise. Not checked yet Parallel tool calls now return independent results — a failed Bash command no longer cancels sibling calls in the same batch. Not checked yet
4 details in Everything
Claude Code v2.1.160 adds shell-startup write prompts, safer acceptEdits mode, and a grep-satisfies-read shortcut.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.160 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.160
Adds a confirmation prompt before writing to shell startup files (.zshenv, .zlogin, .bash_login) and ~/.config/git/ to prevent unintended command execution. Not checked yet In acceptEdits mode, prompts before writing build-tool config files that grant code execution (.npmrc, .yarnrc*, bunfig.toml, .bazelrc, .pre-commit-config.yaml, .devcontainer/, etc.). Not checked yet Single-file grep/egrep/fgrep commands now satisfy the read-before-edit check, eliminating the need for a separate Read step after grepping a file. Not checked yet Renames the dynamic-workflow trigger keyword from workflow to ultracode; the keyword is highlighted in violet in the prompt input. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! The CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE environment variable is removed and is now a no-op.! The dynamic-workflow trigger keyword is renamed from workflow to ultracode; the word workflow no longer triggers a dynamic workflow run.
Claude Code v2.1.157 adds auto-loaded plugins, plugin scaffolding, richer telemetry, and smarter agents dispatch.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.157 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.157
└──▷ TRY IT
Bootstrap a new plugin without touching any marketplace — scaffold it locally and it loads automatically on next launch.
copy
$ claude plugin init my-recon-tool
Capture detailed tool parameters (bash commands, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. /skill names) in OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. traces for audit or pipeline debugging.
copy
$ OTEL_LOG_TOOL_DETAILS=1 claude --print 'Run nmap on 10.0.0.0/24 and summarize open ports'
Adds automatic loading of plugins from .claude/skills directories — no marketplace required. Not checked yet New claude plugin init <name> command scaffolds a new plugin directly into .claude/skills. Not checked yet Adds autocomplete for /plugin arguments: subcommands, installed plugin names, and plugins from known marketplaces. Not checked yet Honors the agent field in settings.json for dispatched sessions, with --agent <name> to override per-run. Not checked yet EnterWorktree can now switch between Claude-managed worktrees mid-session. Not checked yet
+5 more
show less
tool_decision telemetry events now include tool_parameters (bash commands, MCP/skill names) when OTEL_LOG_TOOL_DETAILS=1 is set. Not checked yet Claude-managed worktrees are left unlocked after an agent finishes, enabling clean git worktree remove/prune workflows. Not checked yet Adds a Workflow keyword trigger setting in /config to prevent the word workflow in a prompt from triggering a dynamic workflow. Not checked yet Slash-command autocomplete in the claude agents dispatch input now matches substrings. Not checked yet Pressing backspace immediately after a workflow trigger keyword dismisses the workflow request instead of deleting a character. Not checked yet
10 details in Everything
Claude Code v2.1.154 adds Opus 4.8 with fast mode, dynamic multi-agent workflows, shell background sessions, and smarter plugin discovery.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.154 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.154
└──▷ TRY IT
Hand off a large, multi-step research or coding task to a fleet of background agents and check their progress.
copy
$ claude
# Inside the session:
> Create a workflow to audit every Go package in this repo for security issues
> /workflows
Run a long-lived shell process as a detachable background session inside the agents view.
copy
$ claude agents
# Inside agents view:
! npm run build:watch
Run a background shell command directly from the CLI without entering the interactive UI.
copy
$ claude --bg --exec 'pytest tests/ -x -q'
Adds Claude Opus 4.8 as the new default model with /effort xhigh for maximum effort on hard tasks. Not checked yet Introduces dynamic workflows: ask Claude to orchestrate work across tens to hundreds of background agents; view runs with /workflows. Not checked yet Fast mode on Opus 4.8 now available at 2× the standard rate for 2.5× the speed. Not checked yet The lean system prompt is now the default for all models except Haiku, Sonnet, and Opus 4.7 and earlier. Not checked yet Reduces unsolicited multiple-choice prompts: Claude now reserves them for decisions it genuinely cannot make itself. Not checked yet
+10 more
show less
claude agents: type ! <command> to run a shell command as a background session you can attach to and detach from; also available as claude --bg --exec '<command>'. Not checked yet claude agents: /logout now signs you out instead of routing to a background session. Not checked yet The ←← agents view shortcut now works on Bedrock, Vertex, Foundry, and with telemetry disabled. Not checked yet Claude in Chrome: choose which connected browser to use via /chrome → Select browser… or inline during a browser action with multiple browsers connected. Not checked yet Plugins can declare defaultEnabled: false in plugin.json or a marketplace entry; enable them with /plugin or claude plugin enable. Dependencies of enabled plugins are still auto-enabled. Not checked yet The /plugin Discover tab now pins contextually relevant plugins with a "suggested for this directory" annotation. Not checked yet Streaming tool execution is now always on, including when telemetry is disabled or on Bedrock/Vertex/Foundry (previously behind a feature flag). Not checked yet Stdio MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server subprocesses now receive CLAUDE_CODE_SESSION_ID and CLAUDECODE=1 environment variables. Not checked yet claude mcp list/get now show unapproved .mcp.json servers as ⏸ Pending approval when output is piped, instead of auto-approving and connecting. Not checked yet Improves auto-mode classifier detection of data exfiltration data exfiltration Moving data out of a system or organization without authorization. It can happen through network transfers, removable media or other channels. , particularly bulk transfers of repository contents. Not checked yet
15 details in Everything
└──▷ BREAKING ON UPGRADE
! CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE is deprecated and will be removed on 06/01; switch to /model claude-opus-4-6[1m] then /fast on to use fast mode on Opus 4.6.! The lean system prompt is now the default for all models except Haiku, Sonnet, and Opus 4.7 and earlier, which may change Claude's behavior on upgrade for affected model users.! /simplify no longer runs the full /code-review --fix bug-hunting review; it now performs a cleanup-only pass.
Claude Code v2.1.153 adds LFS-skip for marketplace sources, richer agent autocomplete, terminal-aware status scripts, and persistent macOS permissions.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.153 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.153
└──▷ USE IT
Skip downloading large LFS objects when adding a heavy model or dataset repo as a marketplace source.
yaml
copy
# In your Claude Code marketplace config:
github:
repo: owner/heavy-dataset-repo
skipLfs: true
Size a custom status-line script to the actual terminal width without hardcoding column counts.
copy
$ # status_line.sh — now receives COLUMNS and LINES automatically
printf '%*s' "$COLUMNS" '' | tr ' ' '-'
Adds skipLfs option to github/git plugin marketplace sources to skip Git LFS downloads during clone and update. Not checked yet Adds COLUMNS and LINES environment variables to status line commands so scripts can size output to the terminal width. Not checked yet Expands claude agents dispatch autocomplete to suggest native slash commands and bundled skills, not just project skills. Not checked yet Updates claude agents PR column to display PR #N for a single PR or N PRs for multiple. Not checked yet Merges separate needs authentication startup notices for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers and connectors into a single message. Not checked yet
+3 more
show less
macOS background agents now appear as Claude Code in Privacy & Security and retain permission grants across upgrades. Not checked yet New /model picker saves your model selection as the default for new sessions; press s to switch for the current session only. Not checked yet Moving /bg while Claude is responding now continues the response in the background session instead of dropping it. Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! The modelPicker:setAsDefault keybinding is renamed to modelPicker:thisSessionOnly in keybindings.json; the previous d action is replaced by s.
Claude Code v2.1.152 adds auto-fix code review, hook-driven skill reloading, a MessageDisplay hook, and live thinking indicators.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.152 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.152
└──▷ TRY IT
Run a code review and immediately apply all suggestions to your working tree in one step.
copy
$ claude /code-review --fix
Restrict which tools are available when a skill is active — useful for locked-down review or planning skills.
yaml
copy
# In a skill's frontmatter (e.g., .claude/skills/review.md)
---
disallowed-tools:
- Bash
- Edit
---
Reload skills installed by a SessionStart hook without restarting the session.
copy
$ claude /reload-skills
Adds --fix flag to /code-review: automatically applies review findings (reuse, simplification, efficiency suggestions) to the working tree after review; /simplify now invokes /code-review --fix. Not checked yet Skills and slash commands can now set disallowed-tools in frontmatter to restrict which tools the model can use while that skill is active. Not checked yet Adds /reload-skills command to re-scan skill directories mid-session without restarting. Not checked yet SessionStart hooks can now return reloadSkills: true to make newly installed skills available in the same session. Not checked yet SessionStart hooks can now set the session title via hookSpecificOutput.sessionTitle on startup and resume. Not checked yet
+11 more
show less
Adds MessageDisplay hook event, enabling hooks to transform or hide assistant message text as it is rendered. Not checked yet Adds pluginSuggestionMarketplaces managed setting, allowing admins to allowlist org marketplaces whose plugins may be suggested via context-aware tips. Not checked yet claude plugin marketplace remove now accepts --scope user|project|local for symmetry with marketplace add, install, and uninstall. Not checked yet Automatically switches to the configured --fallback-model for the rest of the session when the primary model is not found, instead of failing every request. Not checked yet Auto mode no longer requires opt-in consent. Not checked yet Vim mode: / in NORMAL mode now opens reverse history search (like Ctrl+R), matching bash/zsh vi-mode behavior. Not checked yet The /usage breakdown now includes large session files, scanned with a streaming read to keep memory usage flat. Not checked yet Thinking summaries in collapsed groups now render as markdown, stay readable for at least 3 seconds, and cap at 10 lines; Ctrl+O shows the full thinking. Not checked yet In fullscreen mode, the Thinking for Ns indicator now counts up live while the model thinks and retains its value if interrupted mid-thought. Not checked yet Post-response timer now shows 'Waiting for N background agents/workflows to finish' and reports cumulative time once results are processed. Not checked yet Adds session entrypoint as an OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. metric attribute (app.entrypoint), opt-in via OTEL_METRICS_INCLUDE_ENTRYPOINT=true. Not checked yet
16 details in Everything
Claude Code v2.1.149 adds per-category usage breakdowns, keyboard-scrollable diffs, GFM task list rendering, and enterprise MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connector controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.149 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.149
└──▷ TRY IT
Check which categories (skills, subagents, plugins, MCP servers) are eating into your usage limits before hitting a cap.
Allow all claude.ai cloud MCP connectors in an enterprise managed deployment, alongside your existing managed-mcp.json config.
json
copy
{ "allowAllClaudeAiMcps": true }
Adds per-category breakdown in /usage showing what's consuming your limits — skills, subagents, plugins, and per-MCP-server MCP-server A process that exposes tools, resources, and prompts over Anthropic's Model Context Protocol, letting an AI agent call external APIs or local services through a standardised interface. cost. Not checked yet Enables keyboard scrolling in /diff detail view via arrows, j/k, PgUp/PgDn, Space , and Home /End . Not checked yet Renders GFM task list checkboxes (- [ ] todo / - [x] done) in Markdown output instead of plain bullets. Not checked yet New enterprise managed setting allowAllClaudeAiMcps loads claude.ai cloud MCP connectors alongside managed-mcp.json. Not checked yet Improves /feedback reports to include conversation context from before compaction, aiding triage of issues in long sessions. Not checked yet
5 details in Everything
Claude Code v2.1.147 adds a new /code-review command with inline GitHub PR comments and pinned background session persistence.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.147 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.147
└──▷ TRY IT
Run a high-effort correctness review on your current code and post findings as inline comments on an open GitHub PR.
copy
$ /code-review high --comment
New /code-review command (replaces /simplify) reports correctness bugs at a chosen effort level and can post findings as inline GitHub PR comments via --comment. Not checked yet Pinned background sessions (Ctrl+T in claude agents) now stay alive when idle, restart in place to apply updates, and are only shed under memory pressure after non-pinned sessions. Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! The /simplify command is renamed to /code-review and its cleanup-and-fix behavior has been removed; scripts or workflows invoking /simplify will no longer work.
Claude Code v2.1.146 renames /simplify to /code-review with optional effort levels.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.146 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.146
└──▷ TRY IT
Run a high-effort code review on your current working changes to catch deeper issues before merging.
New /code-review command (replaces /simplify) with an optional effort level parameter (e.g. /code-review high). Not checked yet Auto mode now respects AskUserQuestion when the user or a skill explicitly relies on it, enabling interactive flows in automated contexts. Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! The /simplify command has been renamed to /code-review; any scripts, docs, or habits referencing /simplify will need to be updated.
Claude Code v2.1.145 adds JSON agent listing, richer OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. spans, plugin previews, and mouse support in fullscreen.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.145 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.145
└──▷ TRY IT
Pipe live agent session data into a status bar or session picker script.
copy
$ claude agents --json | jq '.[] | select(.status == "awaiting_input") | .agent_id'
New claude agents --json command lists live Claude sessions as JSON for scripting (tmux-resurrect, status bars, session pickers). Not checked yet Adds agent_id and parent_agent_id attributes to claude_code.tool OTEL spans, with corrected trace parenting so subagent spans nest under their dispatching Agent tool span. Not checked yet Status line JSON input now includes GitHub repo and PR information when detected. Not checked yet /plugin Discover and Browse screens now preview a plugin's commands, agents, skills, hooks, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. /LSP LSP Language Server Protocol, the standard way editors get code intelligence such as completions, go-to-definition and errors from a separate per-language server. Coding agents use it to understand code. servers before installation. Not checked yet claude agents terminal tab title now shows the awaiting-input count so an alt-tabbed window indicates when an agent needs attention. Not checked yet
+2 more
show less
Slash command and @-mention suggestion list now supports mouse hover and click in fullscreen mode. Not checked yet Read tool now returns a truncated first page with a PARTIAL view notice instead of a hard error when a whole-file read exceeds the token limit. Not checked yet
7 details in Everything
Claude Code v2.1.144 adds /resume for background sessions, elapsed-time notifications, plugin last-updated stamps, and per-session model switching.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.144 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.144
└──▷ TRY IT
Switch to a different model mid-session without changing your default, so tomorrow's new sessions still open with your preferred model.
copy
$ /model # then select the desired model; press 'd' to set a new default for future sessions only if wanted
Adds /resume support for background sessions — sessions started via claude --bg or agent view now appear alongside interactive ones, marked with bg. Not checked yet Adds elapsed duration to background subagent completion notifications (e.g. Agent completed · 3h 2m 5s ). Not checked yet Plugin browse and discover panes now display when each plugin was last updated. Not checked yet /model now changes the model for the current session only; press d in the model picker to set a default for all new sessions. Not checked yet Adds claude --bg --name <label> echoing the session name in the post-spawn confirmation message. Not checked yet
+8 more
show less
Adds claude agents Ctrl+R session rename that immediately updates the attached session's banner. Not checked yet /doctor now shows an exec-form example when a command hook is missing the command field. Not checked yet Skill-listing truncation moved out of startup notifications — full breakdown now available via /doctor. Not checked yet Improved SDK/headless MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. startup: pre-wait now overlaps with startup instead of blocking before the first turn (up to 2 s faster with slow MCP servers). Not checked yet Improved recovery from rare pre-response stream stalls — now retries streaming once instead of falling back to a slower non-streaming request. Not checked yet claude agents / --bg rejection messages now name the specific gate (non-TTY, env var, or setting) instead of a generic message. Not checked yet Plugin marketplace add/update now respects the CLAUDE_CODE_PLUGIN_PREFER_HTTPS environment variable. Not checked yet /plugin now returns to the Installed list after enabling, disabling, or uninstalling a plugin. Not checked yet
13 details in Everything
Claude Code v2.1.143 adds plugin dependency enforcement, projected context costs, and richer claude agents session control.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.143 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.143
└──▷ TRY IT
Launch the agents dashboard scoped to a specific model, effort level, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. config so every dispatched session inherits those defaults.
copy
$ claude agents --model claude-opus-4-5 --effort high --mcp-config ./mcp.json
Allow background sessions to edit the working copy directly when git worktrees are impractical in your repo.
json
copy
# In settings.json
{ "worktree": { "bgIsolation": "none" } }
Adds plugin dependency enforcement: claude plugin disable refuses when another enabled plugin depends on the target and shows a copy-pasteable disable-chain hint; claude plugin enable force-enables transitive dependencies. Not checked yet Adds projected context cost (per-turn and per-invocation token estimates) to the /plugin marketplace browse pane. Not checked yet New worktree.bgIsolation: "none" setting lets background sessions edit the working copy directly without EnterWorktree, for repos where worktrees are impractical. Not checked yet PowerShell tool now passes -ExecutionPolicy Bypass by default; opt out with CLAUDE_CODE_POWERSHELL_RESPECT_EXECUTION_POLICY=1. Not checked yet PowerShell tool is now enabled by default on Windows for Bedrock, Vertex, and Foundry users; opt out with CLAUDE_CODE_USE_POWERSHELL_TOOL=0. Not checked yet
+8 more
show less
claude agents now accepts --add-dir, --settings, --mcp-config, --plugin-dir, --permission-mode, --model, --effort, and --dangerously-skip-permissions to configure the dashboard and sessions dispatched from it. Not checked yet claude --bg --dangerously-skip-permissions now persists across retire→wake cycles. Not checked yet /bg now preserves --mcp-config, --settings, --add-dir, --plugin-dir, and --strict-mcp-config, keeping MCP servers and settings across respawn. Not checked yet /bg and ←-detach now preserve --fallback-model, so backgrounded workers degrade gracefully on overload. Not checked yet /bg and ←-detach now preserve --allow-dangerously-skip-permissions, keeping bypass-permissions available in the Shift+Tab cycle. Not checked yet Background sessions now preserve the model and effort level set after waking from idle. Not checked yet Shift+Tab in attached agent sessions now includes auto mode in the permission cycle. Not checked yet Background sessions launched from claude agents now honor permissions.defaultMode from settings.json. Not checked yet
13 details in Everything
└──▷ BREAKING ON UPGRADE
! Worktree cleanup no longer falls back to rm -rf when git worktree remove fails, preventing accidental deletion of gitignored or in-progress files — workflows that relied on that fallback cleanup behavior will need an alternative removal step.
Claude Code v2.1.142 expands claude agents configuration flags and upgrades Fast mode to Opus 4.7 by default.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.142 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.142
└──▷ TRY IT
Pin fast mode to Opus 4.6 to keep consistent behavior across a team before adopting the new default.
copy
$ CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1 claude --fast
Adds --add-dir, --settings, --mcp-config, --plugin-dir, --permission-mode, --model, --effort, and --dangerously-skip-permissions flags to claude agents for fine-grained control over dispatched background sessions. Not checked yet Fast mode now defaults to Opus 4.7 (up from 4.6); set CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1 to pin back to 4.6. Not checked yet Plugins with a root-level SKILL.md and no skills/ subdirectory are now automatically surfaced as a skill. Not checked yet The /plugin details pane and claude plugin details command now display LSP LSP Language Server Protocol, the standard way editors get code intelligence such as completions, go-to-definition and errors from a separate per-language server. Coding agents use it to understand code. servers provided by a plugin. Not checked yet /web-setup now warns before overwriting an existing GitHub App connection. Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! Fast mode now uses Opus 4.7 by default instead of Opus 4.6; workloads sensitive to model changes must set CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1 to preserve previous behavior.
Claude Code v2.1.141 adds terminalSequence hooks, HTTPS HTTPS HTTP carried over an encrypted TLS connection. It protects traffic in transit and lets a browser verify the server's certificate. plugin cloning, workspace identity scoping, and richer agent/rewind controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.141 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.141
└──▷ TRY IT
Trigger a desktop notification from a hook after a long-running task completes, without needing a controlling terminal.
copy
$ # In your hook script, emit a bell via terminalSequence:
echo '{"terminalSequence": "\a"}'
Install a Claude Code plugin in a CI/CD environment that lacks a GitHub SSH key.
copy
$ CLAUDE_CODE_PLUGIN_PREFER_HTTPS=1 claude plugin install <plugin-name>
List only agents scoped to the current project directory, filtering out unrelated sessions.
copy
$ claude agents --cwd /path/to/project
Adds terminalSequence field to hook JSON output, enabling hooks to emit desktop notifications, window titles, and bells without a controlling terminal. Not checked yet Adds CLAUDE_CODE_PLUGIN_PREFER_HTTPS env var to clone GitHub plugin sources over HTTPS instead of SSH, for environments without a GitHub SSH key. Not checked yet Adds ANTHROPIC_WORKSPACE_ID env var for workload identity federation workload identity federation A mechanism that lets a workload running in one cloud or platform prove its identity to another service using a trusted token exchange, eliminating the need to store long-lived credentials or secrets. , scoping minted tokens to a specific workspace when a federation rule covers more than one. Not checked yet Adds claude agents --cwd <path> to scope the session list to a specific directory. Not checked yet Extends /feedback to optionally include sessions from the last 24 hours or 7 days, covering issues that span multiple sessions. Not checked yet
+5 more
show less
Adds Summarize up to here option in the Rewind menu to compress earlier context while keeping recent turns intact. Not checked yet Background agents launched via /bg or ←← now preserve the current permission mode instead of reverting to default. Not checked yet Auto mode permission dialog now explains when a permissions.ask rule triggered the prompt. Not checked yet Spinner now warms to amber after 10 seconds of thinking to signal Claude is still working. Not checked yet Improves plugin menu navigation: →/Tab switch tabs, ↑ moves to the tab strip, and tab headers and search box are clickable in fullscreen mode. Not checked yet
10 details in Everything
Claude Code v2.1.139 adds agent view, /goal command, hook exec form, and subagent OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. tracing.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.139 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.139
└──▷ TRY IT
Review all active and completed Claude Code sessions across projects from a single pane.
Let Claude autonomously iterate on a task until a specific condition is met, tracking progress live.
copy
$ /goal All unit tests pass and coverage is above 80%
Adds claude agents command Research preview : a unified list of all Claude Code sessions — running, blocked, or complete. Not checked yet Adds /goal command: set a completion condition and Claude works autonomously across turns until it's met, with a live elapsed/turns/tokens overlay panel. Not checked yet Adds /scroll-speed command to tune mouse wheel scroll speed with a live preview. Not checked yet Adds claude plugin details <name> to inspect a plugin's component inventory and projected per-session token cost. Not checked yet Adds transcript view navigation shortcuts: ? for keyboard shortcuts, {/} to jump between user prompts, v to toggle the shortcut panel. Not checked yet
+12 more
show less
Adds args: string[] field (exec form) to hooks, spawning the command directly without a shell so path placeholders never need quoting. Not checked yet Adds continueOnBlock config option for PostToolUse hooks — when true, feeds the hook's rejection reason back to Claude and continues the turn instead of blocking. Not checked yet MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. stdio servers now receive CLAUDE_PROJECT_DIR in their environment; plugin configs can reference ${CLAUDE_PROJECT_DIR} in commands. Not checked yet Compaction prompt now instructs the model to preserve sensitive user instructions across compaction. Not checked yet /mcp Reconnect now picks up .mcp.json edits without a full restart and surfaces the HTTP status and URL on reconnect failure. Not checked yet API requests from subagents now carry x-claude-code-agent-id and x-claude-code-parent-agent-id headers; claude_code.llm_request OTEL spans include agent_id and parent_agent_id attributes. Not checked yet Remote MCP server reconnect retry on transient failures is now enabled for all users. Not checked yet /context all per-skill token estimates now account for the model's tokenizer and display rounded values. Not checked yet claude plugin install <name>@<marketplace> now auto-refreshes the marketplace and retries before reporting a plugin as not found. Not checked yet /context now shows the providing plugin's name for plugin-sourced skills. Not checked yet Remote Control, /schedule, claude.ai MCP connectors, and notification preferences are now disabled when ANTHROPIC_API_KEY / apiKeyHelper / ANTHROPIC_AUTH_TOKEN is set, even if a Claude.ai login also exists. Not checked yet [VSCode] Press Cmd/Ctrl+Shift+T to reopen the most recently closed session tab, configurable via claudeCode.enableReopenClosedSessionShortcut. Not checked yet
17 details in Everything
└──▷ BREAKING ON UPGRADE
! Remote Control, /schedule, claude.ai MCP connectors, and notification preferences are disabled when ANTHROPIC_API_KEY, apiKeyHelper, or ANTHROPIC_AUTH_TOKEN is set — even if a Claude.ai login also exists. Unset the API key to re-enable these features.
Claude Code v2.1.136 adds hard-deny auto mode classifier rules and an OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. survey toggle for enterprises.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.136 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.136
└──▷ USE IT
Enforce a hard block on a category of auto mode actions that no allow rule or user intent can override.
json
copy
{
"autoMode": {
"hard_deny": ["delete_files", "network_requests"]
}
}
Re-enable the session quality survey when your enterprise pipelines session telemetry through OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. .
copy
$ CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL=1 claude
Adds CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL env var to re-enable the session quality survey for enterprises capturing responses via OpenTelemetry. Not checked yet Adds settings.autoMode.hard_deny for auto mode classifier rules that block requests unconditionally, regardless of user intent or allow exceptions. Not checked yet WSL2 WSL2 A Microsoft-maintained compatibility layer in Windows 10/11 that runs a real Linux kernel inside a lightweight VM, letting cyber tools built for Linux execute natively on Windows without dual-booting or a full VM. : image paste from Windows clipboard now works via a PowerShell fallback when xclip/wl-paste cannot read image data. Not checked yet
3 details in Everything
Claude Code v2.1.133 adds worktree base-ref control, custom sandbox binary paths, admin policy merge, and effort-level hook inputs.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.133 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.133
└──▷ TRY IT
Read the active effort level inside a hook script to adjust external tooling (e.g. skip heavy analysis on low-effort runs).
copy
$ #!/bin/bash
# In a Claude hook script
echo "Current effort: $CLAUDE_EFFORT"
if [ "$CLAUDE_EFFORT" = "low" ]; then
exit 0 # skip expensive checks
fi
Adds worktree.baseRef setting (fresh | head) to control whether new worktrees branch from origin/<default> or local HEAD. Not checked yet Adds sandbox.bwrapPath and sandbox.socatPath managed settings (Linux/WSL WSL Windows Subsystem for Linux, a Microsoft-built compatibility layer that lets a Linux environment run directly on Windows without a virtual machine, giving cyber tools access to Linux binaries, filesystems, and syscalls on a Windows host. ) to specify custom bubblewrap and socat binary locations. Not checked yet Adds parentSettingsBehavior admin-tier key ('first-wins' | 'merge') to opt SDK managedSettings into the policy merge chain. Not checked yet Hooks now receive the active effort level via the effort.level JSON input field and the $CLAUDE_EFFORT environment variable, readable by Bash tool commands. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! The default worktree.baseRef is fresh, which changes EnterWorktree's base back to origin/<default>; since v2.1.128 it has been local HEAD. Set worktree.baseRef: "head" to preserve unpushed commits in new worktrees.
Claude Code v2.1.132 adds session ID env var in subprocesses and an opt-out for the fullscreen alternate-screen renderer.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.132 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.132
└──▷ TRY IT
Keep Claude Code output in your terminal's native scrollback instead of the fullscreen renderer — useful in tmux, screen, or any workflow where you rely on scroll history.
copy
$ CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1 claude
Reference the session ID inside a Bash tool script to tag logs or correlate subprocess events back to the originating Claude Code session.
copy
$ echo "Running inside Claude Code session: $CLAUDE_CODE_SESSION_ID" >> /tmp/session-audit.log
Adds CLAUDE_CODE_SESSION_ID environment variable to Bash tool subprocess environments, matching the session_id passed to hooks — enabling scripts and hooks to correlate subprocess activity back to the parent session. Not checked yet Adds CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1 env var to opt out of the fullscreen alternate-screen renderer, keeping conversation output in the terminal's native scrollback. Not checked yet Adds a Pasting… footer hint while a Ctrl+V image paste is being read from the clipboard. Not checked yet
3 details in Everything
Claude Code v2.1.129 adds URL-based plugin loading, auto-update on Homebrew/WinGet, and cross-project history search by default.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.129 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.129
└──▷ TRY IT
Load a community or internal plugin directly from a URL without installing it permanently.
copy
$ claude --plugin-url https://example.com/my-plugin.zip
Enable background auto-updates on a Homebrew install so Claude Code silently upgrades and prompts to restart.
copy
$ export CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE=1
claude
Force synchronized output when running Claude Code inside Emacs eat or another terminal where auto-detection fails.
copy
$ CLAUDE_CODE_FORCE_SYNC_OUTPUT=1 claude
Adds --plugin-url <url> flag to fetch and load a plugin .zip archive from a URL for the current session. Not checked yet Adds CLAUDE_CODE_FORCE_SYNC_OUTPUT=1 env var to force synchronized output on terminals where auto-detection fails (e.g. Emacs eat). Not checked yet Adds CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE env var: when set on Homebrew or WinGet installs, Claude Code upgrades itself in the background and prompts to restart. Not checked yet Adds CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1 env var to opt in to Gateway /v1/models discovery for the /model picker (now opt-in instead of automatic). Not checked yet Ctrl+R history picker now searches all prompts across all projects by default; press Ctrl+S to narrow to the current project or session. Not checked yet
+4 more
show less
skillOverrides setting is now functional: off hides a skill from the model and /, user-invocable-only hides from the model only, name-only collapses the description. Not checked yet The claude_code.pull_request.count OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. metric now counts PRs/MRs created via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools in addition to shell commands. Not checked yet Policy refusal error messages now include the API Request ID to aid support debugging. Not checked yet Plugin manifests: themes and monitors should now be declared under "experimental": { ... }; claude plugin validate warns on top-level declarations. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! Gateway /v1/models model discovery (automatic in v2.1.126–2.1.128) is now opt-in via CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1; setups relying on automatic gateway model discovery will no longer see those models without setting this variable.
Claude Code v2.1.128 adds ZIP plugin support, channels auth expansion, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server diagnostics, and smarter /mcp and /color UX.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.128 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.128
└──▷ TRY IT
Install a plugin distributed as a ZIP archive without unpacking it first.
copy
$ claude --plugin-dir ./my-plugin.zip
Audit connected MCP servers to spot any that registered zero tools (possible misconfiguration).
Bare /color with no arguments now picks a random session color. Not checked yet Adds tool-count display to /mcp output; servers that connect with zero tools are flagged. Not checked yet --plugin-dir now accepts .zip plugin archives in addition to directories. Not checked yet --channels now works with console (API key) authentication; console orgs with managed settings must set channelsEnabled: true to enable. Not checked yet Updated /model picker collapses duplicate Opus 4.7 entries and labels the current Opus model simply as Opus . Not checked yet
+5 more
show less
Subprocesses (Bash, hooks, MCP, LSP LSP Language Server Protocol, the standard way editors get code intelligence such as completions, go-to-definition and errors from a separate per-language server. Coding agents use it to understand code. ) no longer inherit OTEL_* environment variables, isolating OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. -instrumented apps from the CLI's own OTLP OTLP OpenTelemetry Protocol, a standard way to send traces, metrics and logs between applications, collectors and monitoring systems. It lets telemetry move across compatible tools. endpoint. Not checked yet Reconnecting MCP servers now summarize re-announced tools by server prefix instead of flooding the conversation with full tool-name lists. Not checked yet SDK hosts now receive a persistent localSettings suggestion for Bash permission prompts, so Always allow writes to .claude/settings.local.json. Not checked yet Auto mode classifier errors now include a hint (retry, /compact, or run with --debug) when an action cannot be evaluated. Not checked yet Headless --output-format stream-json: init.plugin_errors now includes --plugin-dir load failures in addition to dependency demotions. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! workspace is now a reserved MCP server name — existing servers configured with that name will be skipped with a warning.! Subprocesses (Bash, hooks, MCP, LSP) no longer inherit OTEL_* environment variables; any setup relying on subprocess inheritance of the CLI's OTEL config will stop working.! EnterWorktree now creates the new branch from local HEAD instead of origin/<default-branch>; workflows that depended on the previous behavior of branching from the remote default may behave differently.
Claude Code v2.1.126 adds project purge, gateway model picker, headless OAuth, and richer OTel OTel An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. events.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.126 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.126
└──▷ TRY IT
Clean up all Claude Code state for a stale or sensitive project before archiving or handing off a repo — preview what will be deleted first.
copy
$ claude project purge /path/to/project --dry-run
Non-interactively purge all project state (transcripts, tasks, file history, config entry) in a CI or scripted cleanup flow.
copy
$ claude project purge /path/to/project -y
Adds claude project purge [path] command to delete all Claude Code state for a project (transcripts, tasks, file history, config entry) with --dry-run, -y/--yes, -i/--interactive, and --all flags. Not checked yet The /model picker now lists models from a gateway's /v1/models endpoint when ANTHROPIC_BASE_URL points at an Anthropic-compatible gateway. Not checked yet --dangerously-skip-permissions now bypasses write prompts for .claude/, .git/, .vscode/, shell config files, and other previously-protected paths (catastrophic removal commands still prompt). Not checked yet claude auth login now accepts an OAuth code pasted directly into the terminal when the browser callback can't reach localhost (WSL2 WSL2 A Microsoft-maintained compatibility layer in Windows 10/11 that runs a real Linux kernel inside a lightweight VM, letting cyber tools built for Linux execute natively on Windows without dual-booting or a full VM. , SSH, containers). Not checked yet The claude_code.skill_activated OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. event now fires for user-typed slash commands and carries a new invocation_trigger attribute ("user-slash", "claude-proactive", or "nested-skill"). Not checked yet
+2 more
show less
Windows: Claude now treats PowerShell as the primary shell (instead of Bash) when the PowerShell tool is enabled. Not checked yet Windows: PowerShell 7 installed via the Microsoft Store, MSI without PATH, or .NET global tool is now detected automatically. Not checked yet
7 details in Everything
Claude Code v2.1.122 adds Bedrock service tier selection, PR-URL session lookup, and new OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. events.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.122 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.122
└──▷ TRY IT
Route Bedrock API calls to a specific service tier (e.g., priority) for latency-sensitive workloads.
copy
$ ANTHROPIC_BEDROCK_SERVICE_TIER=priority claude --model anthropic.claude-opus-4-5
Adds ANTHROPIC_BEDROCK_SERVICE_TIER env var to select a Bedrock service tier (default, flex, or priority), sent as the X-Amzn-Bedrock-Service-Tier header. Not checked yet Pasting a GitHub, GitHub Enterprise, GitLab, or Bitbucket PR URL into the /resume search box now finds the session that created that PR. Not checked yet Adds claude_code.at_mention OpenTelemetry log event for @-mention resolution. Not checked yet OpenTelemetry numeric attributes on api_request/api_error log events are now emitted as numbers instead of strings. Not checked yet The /mcp view now surfaces claude.ai connectors hidden by a manually-added server with the same URL, with a hint to remove the duplicate. Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! OpenTelemetry consumers parsing numeric attributes on api_request/api_error log events as strings will receive numbers instead — pipelines that treat those fields as strings may need to be updated.
Claude Code v2.1.121 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. alwaysLoad, plugin pruning, PostToolUse output replacement, mTLS mTLS Mutual TLS, an encrypted connection where both client and server present certificates to prove their identity. It helps services verify who they are communicating with. Workload Identity, and expanded OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. spans.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.121 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.121
└──▷ USE IT
Pin a high-priority MCP server's tools so they are always available without waiting for tool-search deferral — useful for servers you rely on in every session.
json
copy
# In your MCP server config (e.g. .claude/mcp_settings.json)
{
"mcpServers": {
"my-server": {
"command": "my-mcp-server",
"alwaysLoad": true
}
}
}
Clean up orphaned plugin dependencies after removing plugins, or cascade-remove a plugin and all its unique dependencies in one step.
copy
$ # Prune all orphaned dependencies
claude plugin prune
# Or remove a plugin and cascade its dependencies
claude plugin uninstall my-plugin --prune
Adds alwaysLoad option to MCP server config — when true, all tools from that server bypass tool-search deferral and are always available. Not checked yet Adds claude plugin prune command to remove orphaned auto-installed plugin dependencies; plugin uninstall --prune cascades removals. Not checked yet PostToolUse hooks can now replace tool output for ALL tools via hookSpecificOutput.updatedToolOutput, not just MCP tools. Not checked yet Adds type-to-filter search box to /skills for quickly finding skills in long lists. Not checked yet Vertex AI: supports X.509 X.509 A standard defining the format of public-key certificates, maintained by the ITU-T, used by cyber tools to authenticate identities and establish encrypted connections over TLS and similar protocols. certificate-based Workload Identity Federation (mTLS ADC). Not checked yet
+11 more
show less
OpenTelemetry spans now include stop_reason, gen_ai.response.finish_reasons, and user_system_prompt (gated behind OTEL_LOG_USER_PROMPTS) on LLM LLM A large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. request spans. Not checked yet SDK: mcp_authenticate now supports redirectUri for custom scheme completion and claude.ai connectors. Not checked yet Enables CLAUDE_CODE_FORK_SUBAGENT=1 in non-interactive sessions for SDK and claude -p. Not checked yet --dangerously-skip-permissions no longer prompts for writes to .claude/skills/, .claude/agents/, and .claude/commands/. Not checked yet MCP servers that hit a transient error at startup now auto-retry up to 3 times instead of staying disconnected. Not checked yet Terminal tab session title is now generated in the configured language setting. Not checked yet LSP LSP Language Server Protocol, the standard way editors get code intelligence such as completions, go-to-definition and errors from a separate per-language server. Coding agents use it to understand code. diagnostic summaries now expand on click or Ctrl+O and show an expand hint. Not checked yet Scrollable overflow dialogs: terminal dialogs that exceed terminal height are now navigable with arrow keys, PgUp/PgDn, Home/End, and mouse wheel in both fullscreen and non-fullscreen modes. Not checked yet Clicking any line of a long URL wrapped across rows in fullscreen mode now opens the full URL. Not checked yet [VSCode] Voice dictation now respects the accessibility.voice.speechLanguage setting when no Claude Code language is configured. Not checked yet [VSCode] /context now opens a native token usage dialog. Not checked yet
16 details in Everything
Claude Code v2.1.119 adds GitLab/Bitbucket PR support, persistent config, richer hooks, and OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. improvements.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.119 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.119
└──▷ TRY IT
Load a GitLab MR or Bitbucket PR directly into a Claude Code session for review or agentic work, without converting the URL to GitHub format.
copy
$ claude --from-pr https://gitlab.com/myorg/myrepo/-/merge_requests/42
Hide the working directory from the startup logo when running Claude Code in shared or recorded terminal sessions.
copy
$ CLAUDE_CODE_HIDE_CWD=1 claude
Adds prUrlTemplate setting to point the footer PR badge at a custom code-review URL instead of github.com. Not checked yet Adds CLAUDE_CODE_HIDE_CWD environment variable to hide the working directory in the startup logo. Not checked yet --from-pr now accepts GitLab merge-request, Bitbucket pull-request, and GitHub Enterprise PR URLs in addition to github.com. Not checked yet /config settings (theme, editor mode, verbose, etc.) now persist to ~/.claude/settings.json and participate in project/local/policy override precedence. Not checked yet --print mode now honors the agent's tools: and disallowedTools: frontmatter, matching interactive-mode behavior. Not checked yet
+11 more
show less
--agent <name> now honors the agent definition's permissionMode for built-in agents. Not checked yet PowerShell tool commands can now be auto-approved in permission mode, matching Bash behavior. Not checked yet PostToolUse and PostToolUseFailure hook inputs now include duration_ms (tool execution time, excluding permission prompts and PreToolUse hooks). Not checked yet Subagent and SDK MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server reconfiguration now connects servers in parallel instead of serially, reducing startup latency. Not checked yet Plugins pinned by another plugin's version constraint now auto-update to the highest satisfying git tag. Not checked yet OpenTelemetry tool_result and tool_decision events now include tool_use_id; tool_result also includes tool_input_size_bytes. Not checked yet Status line stdin JSON now includes effort.level and thinking.enabled fields. Not checked yet Tool search on Vertex AI is now opt-in via ENABLE_TOOL_SEARCH environment variable. Not checked yet Slash command suggestions now highlight the characters that matched your query. Not checked yet Slash command picker now wraps long descriptions onto a second line instead of truncating. Not checked yet owner/repo#N shorthand links in output now use your git remote's host instead of always pointing at github.com. Not checked yet
16 details in Everything
└──▷ BREAKING ON UPGRADE
! Tool search is now disabled by default on Vertex AI; opt in by setting ENABLE_TOOL_SEARCH to restore the previous behavior.
Claude Code v2.1.118 adds vim visual mode, custom themes, MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool hooks, and a new /usage command.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.118 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.118
└──▷ TRY IT
Block all updates in a locked-down enterprise environment where even manual claude update must be prohibited.
copy
$ DISABLE_UPDATES=1 claude
Allow a hook to call an MCP tool directly — e.g., log an event to a custom MCP server after every agent stop.
json
copy
{
"type": "mcp_tool",
"server": "my-mcp-server",
"tool": "log_event",
"params": { "event": "agent_stop" }
}
Tag a plugin release with version validation before publishing.
copy
$ claude plugin tag v1.2.0
Adds vim visual mode (v) and visual-line mode (V) with selection, operators, and visual feedback in the editor. Not checked yet Merges /cost and /stats into a unified /usage command with tabs; old names remain as shortcuts. Not checked yet Introduces custom named themes: create/switch via /theme or hand-edit JSON in ~/.claude/themes/; plugins can ship themes via a themes/ directory. Not checked yet Hooks can now invoke MCP tools directly using type: "mcp_tool". Not checked yet New DISABLE_UPDATES env var completely blocks all update paths including manual claude update, stricter than DISABLE_AUTOUPDATER. Not checked yet
+8 more
show less
WSL WSL Windows Subsystem for Linux, a Microsoft-built compatibility layer that lets a Linux environment run directly on Windows without a virtual machine, giving cyber tools access to Linux binaries, filesystems, and syscalls on a Windows host. on Windows can now inherit Windows-side managed settings via the wslInheritsWindowsSettings policy key. Not checked yet Auto mode: include "$defaults" in autoMode.allow, autoMode.soft_deny, or autoMode.environment to extend the built-in rule list instead of replacing it. Not checked yet Adds a Don't ask again option to the auto mode opt-in prompt. Not checked yet New claude plugin tag subcommand creates release git tags for plugins with version validation. Not checked yet --continue/--resume now find sessions that added the current directory via /add-dir. Not checked yet /color now syncs the session accent color to claude.ai/code when Remote Control is connected. Not checked yet The /model picker honors ANTHROPIC_DEFAULT_*_MODEL_NAME/_DESCRIPTION overrides when using a custom ANTHROPIC_BASE_URL gateway. Not checked yet Plugin version-constraint skips during auto-update are now surfaced in /doctor and the /plugin Errors tab. Not checked yet
13 details in Everything
Claude Code v2.1.117 adds fork-subagent support, richer OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. attributes, and faster native search via embedded bfs/ugrep.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.117 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.117
└──▷ TRY IT
Surface custom/MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. slash-command names in OpenTelemetry traces for full audit visibility (they are redacted by default).
copy
$ OTEL_LOG_TOOL_DETAILS=1 claude
Enables forked subagents on external builds via CLAUDE_CODE_FORK_SUBAGENT=1. Not checked yet Loads agent frontmatter mcpServers for main-thread agent sessions launched with --agent. Not checked yet Persists /model selections across restarts even when a project pins a different model; startup header now indicates when the active model is from a project or managed-settings pin. Not checked yet Adds summarization offer in /resume for stale, large sessions before re-reading them. Not checked yet Concurrent MCP server connections now default when both local and claude.ai servers are configured, reducing startup time. Not checked yet
+9 more
show less
plugin install on an already-installed plugin now installs any missing dependencies instead of stopping. Not checked yet Adds claude plugin marketplace add auto-resolution of missing dependencies from configured marketplaces; dependency errors now include an install hint. Not checked yet Enforces managed-settings blockedMarketplaces and strictKnownMarketplaces on plugin install, update, refresh, and autoupdate. Not checked yet Advisor Tool Experimental dialog now carries an experimental label, a learn-more link, and a startup notification when enabled. Not checked yet Extends cleanupPeriodDays retention sweep to cover ~/.claude/tasks/, ~/.claude/shell-snapshots/, and ~/.claude/backups/. Not checked yet OpenTelemetry user_prompt events now include command_name and command_source for slash commands; cost.usage, token.usage, api_request, and api_error now include an effort attribute for models that support effort levels; custom/MCP command names are redacted unless OTEL_LOG_TOOL_DETAILS=1 is set. Not checked yet On native macOS and Linux builds, Glob and Grep tools are replaced by embedded bfs and ugrep available through the Bash tool, enabling faster searches without a separate tool round-trip. Not checked yet Windows builds now cache where.exe executable lookups per process for faster subprocess launches. Not checked yet Default effort for Pro/Max subscribers on Opus 4.6 and Sonnet 4.6 is now high (previously medium). Not checked yet
14 details in Everything
Claude Code v2.1.116 adds faster session resumption, deferred MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. startup, inline thinking progress, and smarter plugin dependency auto-install.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.116 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.116
└──▷ TRY IT
After adding a new plugin source, force-reload plugins so missing dependencies are pulled in automatically without manual marketplace steps.
Configure scroll sensitivity for VS Code, Cursor, or Windsurf so fullscreen sessions scroll smoothly without manual editor tweaks.
Run a main-thread agent that fires its frontmatter hooks as part of the agent lifecycle.
copy
$ claude --agent <path/to/agent.md>
Speeds up /resume on large sessions by up to 67% on sessions 40 MB and larger, with more efficient handling of dead-fork entries. Not checked yet Defers resources/templates/list to first @-mention, reducing MCP startup time when multiple stdio servers are configured. Not checked yet Improves fullscreen scrolling in VS Code, Cursor, and Windsurf terminals — /terminal-setup now configures scroll sensitivity for those editors. Not checked yet Replaces the separate thinking-hint row with an inline progress indicator (still thinking , thinking more , almost done thinking ) in the spinner. Not checked yet Extends /config search to match option values (e.g. searching vim surfaces the Editor mode setting). Not checked yet
+7 more
show less
Allows /doctor to be opened while Claude is actively responding, without waiting for the current turn to finish. Not checked yet Enables /reload-plugins and background plugin auto-update to auto-install missing plugin dependencies from already-added marketplaces. Not checked yet Surfaces a rate-limit hint in the Bash tool when gh commands hit GitHub's API rate limit, letting agents back off instead of retrying. Not checked yet Shows 5-hour and weekly usage immediately in the Settings Usage tab, with graceful handling when the usage endpoint is rate-limited. Not checked yet Fires agent frontmatter hooks: when the agent is run as a main-thread agent via --agent. Not checked yet Displays No commands match in the slash command menu when a filter has zero results instead of hiding the menu entirely. Not checked yet Security: sandbox auto-allow no longer bypasses the dangerous-path safety check for rm/rmdir targeting /, $HOME, or other critical system directories. Not checked yet
12 details in Everything
Claude Code v2.1.113 adds domain blocklisting, exec-wrapper deny rules, and expanded Remote Control capabilities.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.113 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.113
└──▷ USE IT
Block a specific domain (e.g., an exfiltration endpoint) even when a wildcard allowedDomains rule would normally permit it.
json
copy
# In your Claude Code settings (e.g., .claude/settings.json)
{
"sandbox": {
"network": {
"allowedDomains": ["*.example.com"],
"deniedDomains": ["malicious.example.com"]
}
}
}
New sandbox.network.deniedDomains setting blocks specific domains even when a broader allowedDomains wildcard would otherwise permit them. Not checked yet Security: Bash deny rules now match commands wrapped in env/sudo/watch/ionice/setsid and similar exec wrappers, closing bypass paths. Not checked yet Security: Bash(find:*) allow rules no longer auto-approve find -exec/-delete, preventing unintended file operations. Not checked yet Security: on macOS, /private/{etc,var,tmp,home} paths are treated as dangerous removal targets under Bash(rm:*) allow rules. Not checked yet Bash tool now shows the full command in the transcript for multi-line commands whose first line is a comment, closing a UI-spoofing vector. Not checked yet
+7 more
show less
Remote Control (mobile/web) clients can now use /extra-usage and query @-file autocomplete suggestions. Not checked yet CLI now spawns a native Claude Code binary via a per-platform optional dependency instead of bundled JavaScript. Not checked yet Ctrl+A and Ctrl+E move to the start/end of the current logical line in multiline input, matching readline behavior. Not checked yet Windows: Ctrl+Backspace now deletes the previous word. Not checked yet Long URLs in responses and bash output stay clickable when they wrap across lines in terminals with OSC 8 hyperlinks. Not checked yet Improved /ultrareview: faster launch with parallelized checks, diffstat in the launch dialog, and animated launching state. Not checked yet Improved /loop: pressing Esc cancels pending wakeups; wakeups display as Claude resuming /loop wakeup for clarity. Not checked yet
12 details in Everything
Claude Code v2.1.111 adds /ultrareview for cloud-based PR analysis, xhigh effort tier, PowerShell support, and a permission-prompt reducer.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.111 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.111
└──▷ TRY IT
Review a specific GitHub PR with multi-agent cloud analysis to get comprehensive feedback before merging.
Reduce permission prompts in a project by auto-generating an allowlist from your session history.
copy
$ /less-permission-prompts
Emit full API request and response bodies as OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. log events to trace model calls during debugging.
copy
$ OTEL_LOG_RAW_API_BODIES=1 claude --output-format stream-json '<prompt>'
Adds xhigh effort level for Opus 4.7, sitting between high and max; selectable via /effort, --effort, or the model picker. Not checked yet New /ultrareview command runs comprehensive code review in the cloud using parallel multi-agent analysis — no arguments reviews the current branch; /ultrareview <PR#> fetches and reviews a specific GitHub PR. Not checked yet New /less-permission-prompts skill scans transcripts for common read-only Bash and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool calls and proposes a prioritized allowlist for .claude/settings.json. Not checked yet Auto mode is now available for Max subscribers using Opus 4.7, and no longer requires the --enable-auto-mode flag. Not checked yet Adds PowerShell tool support on Windows (progressive rollout); opt in/out with CLAUDE_CODE_USE_POWERSHELL_TOOL; enable on Linux/macOS with CLAUDE_CODE_USE_POWERSHELL_TOOL=1 (requires pwsh on PATH). Not checked yet
+9 more
show less
Adds OTEL_LOG_RAW_API_BODIES environment variable to emit full API request and response bodies as OpenTelemetry log events for debugging. Not checked yet New Auto (match terminal) theme option automatically matches the terminal's dark/light mode; selectable via /theme. Not checked yet /effort now opens an interactive slider with arrow-key navigation and Enter to confirm when called without arguments. Not checked yet Read-only bash commands with glob patterns (e.g. ls *.ts) and commands beginning with cd <project-dir> && no longer trigger a permission prompt. Not checked yet /skills menu now supports sorting by estimated token count — press t to toggle. Not checked yet Ctrl+L now forces a full screen redraw in addition to clearing the prompt input. Not checked yet Transcript view footer now shows [ (dump to scrollback) and v (open in editor) shortcuts. Not checked yet Headless --output-format stream-json now includes plugin_errors on the init event when plugins are demoted for unsatisfied dependencies. Not checked yet Improved /setup-vertex and /setup-bedrock to show the actual settings.json path when CLAUDE_CONFIG_DIR is set, seed model candidates from existing pins on re-run, and offer a 1M context option for supported models. Not checked yet
14 details in Everything
└──▷ BREAKING ON UPGRADE
! Ctrl+U behavior changed: it now clears the entire input buffer instead of deleting only to the start of the line (press Ctrl+Y to restore).
Claude Code v2.1.110 adds flicker-free TUI TUI A text-based user interface that runs inside a terminal, using characters and ANSI escape codes to render menus, panes, and widgets without a graphical desktop, letting cyber tools ship rich interactivity with no GUI dependency. fullscreen, mobile push notifications, and distributed trace linking for SDK sessions.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.110 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.110
└──▷ TRY IT
Switch to flicker-free fullscreen rendering mid-conversation without starting a new session.
Link a headless Claude Code SDK run into your existing distributed trace for end-to-end observability.
copy
$ TRACEPARENT=00-4bf92f3577b34da6a3ce929d0e0e4736-00f067aa0ba902b7-01 TRACESTATE=vendor=value claude --headless --print "summarise logs"
Adds /tui command and tui setting — run /tui fullscreen to switch to flicker-free rendering within the same conversation. Not checked yet Adds /focus command to toggle focus view independently from verbose transcript (previously both were on Ctrl+O ). Not checked yet Adds push notification tool so Claude can send mobile push notifications when Remote Control and Push when Claude decides config are enabled. Not checked yet Adds autoScrollEnabled config to disable conversation auto-scroll in fullscreen mode. Not checked yet Adds option to show Claude's last response as commented context in the Ctrl+G external editor, enabled via /config. Not checked yet
+7 more
show less
Improves /plugin Installed tab: items needing attention and favorites float to the top, disabled items collapse behind a fold, and f favorites the selected item. Not checked yet Improves /doctor to warn when an MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server is defined in multiple config scopes with different endpoints. Not checked yet --resume/--continue now resurrects unexpired scheduled tasks. Not checked yet Enables /autocompact, /context, /exit, and /reload-plugins commands from Remote Control (mobile/web) clients. Not checked yet Write tool now informs the model when you edit proposed content in the IDE diff before accepting. Not checked yet SDK/headless sessions now read TRACEPARENTTRACEPARENT An HTTP header defined by the W3C Trace Context standard that carries a trace ID and span ID across service boundaries, letting distributed tracing systems stitch together request flows across multiple services. /TRACESTATE from the environment for distributed trace linking. Not checked yet Session recap is now enabled for users with telemetry disabled (Bedrock, Vertex, Foundry, DISABLE_TELEMETRY); opt out via /config or CLAUDE_CODE_ENABLE_AWAY_SUMMARY=0. Not checked yet
12 details in Everything
└──▷ BREAKING ON UPGRADE
! Ctrl+O no longer toggles focus view — it now toggles between normal and verbose transcript only; focus view must be toggled with the new /focus command.
Claude Code v2.1.108 adds 1-hour prompt cache TTL TTL Time to live, a limit on how long data remains valid or how far a packet can travel. Caches use a time limit; IP packets use a hop limit. opt-in, session recap, and slash-command discovery via Skill tool.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.108 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.108
└──▷ TRY IT
Opt into the 1-hour prompt cache TTL on Bedrock to cut repeated-context costs across long sessions.
copy
$ ENABLE_PROMPT_CACHING_1H=1 claude
Re-orient yourself after stepping away from a long session without scrolling through the full transcript.
Resume work in the current repo — the picker now defaults to sessions from this directory; switch to all projects if needed.
copy
$ /resume # Ctrl+A to expand to all projects
Adds ENABLE_PROMPT_CACHING_1H env var to opt into 1-hour prompt cache TTL across API key, Bedrock, Vertex, and Foundry backends; FORCE_PROMPT_CACHING_5M forces the 5-minute TTL. Not checked yet Adds /recap command (and CLAUDE_CODE_ENABLE_AWAY_SUMMARY env var) to generate a context summary when returning to a session; also configurable via /config. Not checked yet Enables the model to discover and invoke built-in slash commands (/init, /review, /security-review) via the Skill tool. Not checked yet Adds /undo as an alias for /rewind. Not checked yet Adds a warning at startup when prompt caching is disabled via DISABLE_PROMPT_CACHING* environment variables. Not checked yet
+5 more
show less
Adds a verbose indicator when viewing the detailed transcript via Ctrl+O . Not checked yet Improves /resume picker to default to sessions from the current directory; Ctrl+A reveals all projects. Not checked yet Improves /model to warn before switching models mid-conversation to flag the uncached full-history re-read cost. Not checked yet Improves error messages: rate limits distinguished from plan usage limits; 5xx/529 errors link to status.claude.com; unknown slash commands suggest the closest match. Not checked yet Reduces memory footprint for file reads, edits, and syntax highlighting by loading language grammars on demand. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! ENABLE_PROMPT_CACHING_1H_BEDROCK is deprecated (still honored) in favor of the unified ENABLE_PROMPT_CACHING_1H env var.
Claude Code v2.1.105 adds PreCompact hooks, plugin background monitors, worktree path switching, and a smarter /doctor with auto-fix.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.105 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.105
└──▷ TRY IT
Block compaction at a critical point in a long session by returning a structured decision from a PreCompact hook.
copy
$ #!/usr/bin/env sh
# .claude/hooks/pre-compact.sh
# Exit code 2 tells Claude Code to block compaction
exit 2
Adds path parameter to the EnterWorktree tool to switch into an existing worktree of the current repository. Not checked yet Adds PreCompact hook support: hooks can block compaction by exiting with code 2 or returning {"decision":"block"}. Not checked yet Adds background monitor support for plugins via a top-level monitors manifest key that auto-arms at session start or on skill invoke. Not checked yet Adds /proactive as an alias for /loop. Not checked yet Improves /doctor layout with status icons and adds f keypress to have Claude automatically fix reported issues. Not checked yet
+3 more
show less
Raises plugin skill description listing cap from 250 to 1,536 characters, with a startup warning when descriptions are truncated. Not checked yet Improves WebFetch to strip <style> and <script> contents from fetched pages, preventing CSS-heavy pages from exhausting the content budget. Not checked yet Improves MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. large-output truncation prompt with format-specific recipes (e.g. jq for JSON, computed Read chunk sizes for text). Not checked yet
8 details in Everything
Claude Code v2.1.101 adds /team-onboarding, OS CA store trust by default, and auto-create cloud environments for /ultraplan.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.101 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.101
└──▷ TRY IT
Generate a ramp-up guide for a new teammate joining your project, based on your existing Claude Code usage patterns.
Resume a named session by its human-readable title (set via /rename) rather than an opaque session ID.
copy
$ claude -p --resume my-project-audit
Restrict TLS trust to bundled CAs only, opting out of the new OS CA store default (e.g., in locked-down environments where OS trust anchors should not be used).
copy
$ CLAUDE_CODE_CERT_STORE=bundled claude
Adds /team-onboarding command to generate a teammate ramp-up guide from your local Claude Code usage. Not checked yet Trusts OS CA certificate store by default, enabling enterprise TLS proxies without extra configuration (set CLAUDE_CODE_CERT_STORE=bundled to restrict to bundled CAs only). Not checked yet Enables /ultraplan and other remote-session features to auto-create a default cloud environment, removing the requirement to complete web setup first. Not checked yet Beta tracing now honors OTEL_LOG_USER_PROMPTS, OTEL_LOG_TOOL_DETAILS, and OTEL_LOG_TOOL_CONTENT; sensitive span attributes are opt-in only. Not checked yet claude -p --resume <name> now accepts session titles set via /rename or --name. Not checked yet
+5 more
show less
Rate-limit retry messages now show which limit was hit and when it resets. Not checked yet Refusal error messages now include the API-provided explanation when available. Not checked yet Tool-not-available errors now explain why the tool is unavailable and how to proceed. Not checked yet /plugin and claude plugin update now warn when the marketplace could not be refreshed instead of silently showing stale versions. Not checked yet SDK query() now cleans up subprocesses and temp files when consumers break from for await or use await using. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! OS CA certificate store is now trusted by default; set CLAUDE_CODE_CERT_STORE=bundled to revert to bundled CAs only.
Claude Code v2.1.98 adds Vertex AI setup wizard, Perforce mode, subprocess sandboxing sandboxing Running code inside a restricted environment that limits what it can access or change. The isolation reduces the impact of mistakes or untrusted code, depending on the sandbox's controls. , and a new Monitor tool for background scripts.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.98 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.98
└──▷ TRY IT
Protect read-only Perforce-managed files so writes fail loudly with a p4 edit hint instead of silently overwriting them.
copy
$ CLAUDE_CODE_PERFORCE_MODE=1 claude
Sandbox background script subprocesses with PID namespace isolation and cap the number of script invocations per session.
copy
$ CLAUDE_CODE_SUBPROCESS_ENV_SCRUB=1 CLAUDE_CODE_SCRIPT_CAPS=10 claude
Print the current prompt in a cache-friendly form that strips dynamic sections, useful for sharing stable prompt hashes across users in CI.
copy
$ claude --print --exclude-dynamic-system-prompt-sections
Adds interactive Google Vertex AI setup wizard from the login screen under 3rd-party platform , guiding through GCP auth, project/region config, credential verification, and model pinning. Not checked yet New CLAUDE_CODE_PERFORCE_MODE env var: Edit/Write/NotebookEdit fail on read-only files with a p4 edit hint instead of silently overwriting them. Not checked yet New Monitor tool for streaming events from background scripts. Not checked yet Adds subprocess sandboxing with PID namespace isolation on Linux when CLAUDE_CODE_SUBPROCESS_ENV_SCRUB is set; new CLAUDE_CODE_SCRIPT_CAPS env var limits per-session script invocations. Not checked yet New --exclude-dynamic-system-prompt-sections flag for print mode to improve cross-user prompt caching. Not checked yet
+8 more
show less
Adds workspace.git_worktree to status line JSON input, set when the current directory is inside a linked git worktree. Not checked yet Propagates W3C TRACEPARENTTRACEPARENT An HTTP header defined by the W3C Trace Context standard that carries a trace ID and span ID across service boundaries, letting distributed tracing systems stitch together request flows across multiple services. env var to Bash tool subprocesses when OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. tracing is enabled, correctly parenting child-process spans in the trace tree. Not checked yet LSP LSP Language Server Protocol, the standard way editors get code intelligence such as completions, go-to-definition and errors from a separate per-language server. Coding agents use it to understand code. : Claude Code now identifies itself to language servers via clientInfo in the initialize request. Not checked yet Improved /agents with a tabbed layout: Running tab shows live subagents; Library tab adds Run agent and View running instance actions. Not checked yet Improved /reload-plugins to pick up plugin-provided skills without requiring a restart. Not checked yet Improved Vim mode: j/k in NORMAL mode now navigate history and select the footer pill at the input boundary. Not checked yet Improved OTEL tracing: interaction spans now correctly wrap full turns under concurrent SDK calls, and headless turns end spans per-turn. Not checked yet Updated /claude-api skill to cover Managed Agents alongside Claude API. Not checked yet
13 details in Everything
Claude Code v2.1.97 adds focus view toggle, refreshable status lines, git worktree context, live subagent indicators, and Cedar policy syntax highlighting.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.97 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.97
└──▷ USE IT
Keep a live clock or custom metric in the status line without restarting — useful for monitoring session-level stats in long-running agentic runs.
json
copy
# In settings.json
{
"statusLine": {
"command": "date '+%H:%M:%S'",
"refreshInterval": 5
}
}
Distinguish which git worktree a subagent is operating in from a shared status-line script — lets you label the session card with the worktree path.
python
copy
# Example status-line script that reads workspace.git_worktree from stdin
import sys, json
data = json.load(sys.stdin)
worktree = data.get("workspace", {}).get("git_worktree", "")
print(f"worktree: {worktree}" if worktree else "main worktree")
Toggle focus view during a long tool-heavy session to see just the prompt, a compact tool summary, and the final response without visual noise.
copy
$ # While Claude Code is running in NO_FLICKER mode, press:
Ctrl+O
Adds focus view toggle (Ctrl+O ) in NO_FLICKER mode showing prompt, one-line tool summary with edit diffstats, and final response Not checked yet Adds refreshInterval status line setting to re-run the status line command every N seconds Not checked yet Adds workspace.git_worktree field to status line JSON input, populated when inside a linked git worktree Not checked yet Adds ● N running indicator in /agents next to agent types with live subagent instances Not checked yet Adds syntax highlighting for Cedar policy files (.cedar, .cedarpolicy) Not checked yet
+8 more
show less
Accept Edits mode now auto-approves filesystem commands prefixed with safe env vars or process wrappers (e.g. LANG=C rm foo, timeout 5 mkdir out) Not checked yet Auto mode and bypass-permissions mode now auto-approve sandbox network access prompts Not checked yet sandbox.network.allowMachLookup now takes effect on macOS Not checked yet Pasted and attached images are now compressed to the same token budget as images read via the Read tool Not checked yet Slash command and @-mention completion now triggers after CJK sentence punctuation, enabling Japanese/Chinese input without a leading space Not checked yet Bridge sessions now display the local git repo, branch, and working directory on the claude.ai session card Not checked yet Bash tool OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. tracing now injects a W3C TRACEPARENTTRACEPARENT An HTTP header defined by the W3C Trace Context standard that carries a trace ID and span ID across service boundaries, letting distributed tracing systems stitch together request flows across multiple services. env var into subprocesses when tracing is enabled Not checked yet Updated /claude-api skill to cover Managed Agents alongside the Claude API Not checked yet
13 details in Everything
Claude Code v2.1.94 adds Mantle-powered Bedrock support, raises default effort to high, and expands hook/plugin capabilities.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.94 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.94
└──▷ TRY IT
Route Claude Code through Amazon Bedrock powered by Mantle instead of the default endpoint.
copy
$ CLAUDE_CODE_USE_MANTLE=1 claude
Set a custom session title from a UserPromptSubmit hook by returning hookSpecificOutput.sessionTitle.
json
copy
{
"hookSpecificOutput": {
"sessionTitle": "Incident triage — 2025-07-01"
}
}
Adds Amazon Bedrock powered by Mantle support via CLAUDE_CODE_USE_MANTLE=1. Not checked yet Raises default effort level from medium to high for API-key, Bedrock/Vertex/Foundry, Team, and Enterprise users (adjustable with /effort). Not checked yet Adds compact Slacked #channel header with a clickable channel link for Slack MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. send-message tool calls. Not checked yet Adds keep-coding-instructions frontmatter field support for plugin output styles. Not checked yet Adds hookSpecificOutput.sessionTitle to UserPromptSubmit hooks for setting the session title programmatically. Not checked yet
+3 more
show less
Plugin skills declared via "skills": ["./"] now use the skill frontmatter name as the invocation name instead of the directory basename, providing a stable name across install methods. Not checked yet Improves --resume to resume sessions from other worktrees of the same repo directly instead of printing a cd command. Not checked yet [VSCode] Adds a warning banner when settings.json files fail to parse so users know their permission rules are not being applied. Not checked yet
8 details in Everything
Claude Code v2.1.92 adds fail-closed remote policy enforcement, an interactive Bedrock setup wizard, and richer cost breakdowns.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.92 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.92
└──▷ TRY IT
Name a Remote Control session with your own prefix so it's identifiable across machines in a shared team environment.
copy
$ claude --remote-control-session-name-prefix my-team
Adds forceRemoteSettingsRefresh policy setting that blocks CLI startup until remote managed settings are freshly fetched and exits on fetch failure (fail-closed). Not checked yet Adds an interactive Bedrock setup wizard from the login screen (3rd-party platform ) guiding AWS auth, region config, credential verification, and model pinning. Not checked yet Adds per-model and cache-hit cost breakdown to the /cost command for subscription users. Not checked yet Upgrades /release-notes to an interactive version picker. Not checked yet Remote Control session names now default to your hostname as prefix (e.g. myhost-graceful-unicorn), overridable with --remote-control-session-name-prefix. Not checked yet
+2 more
show less
Pro users see a footer hint when returning to a session after prompt cache expiry, showing estimated uncached tokens for the next turn. Not checked yet Write tool diff computation is 60% faster on large files containing tabs, &, or $. Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! The /tag command has been removed.! The /vim command has been removed; vim mode must now be toggled via /config → Editor mode.
Claude Code v2.1.91 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. large-result passthrough, plugin executables, and multi-line deep link support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.91 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.91
└──▷ USE IT
Pass a large DB schema or other oversized MCP tool result through without truncation by annotating the result metadata.
json
copy
{ "_meta": { "anthropic/maxResultSizeChars": 500000 }, "content": "<full schema here>" }
Open Claude Code from a browser or launcher with a multi-line prompt pre-filled — useful for scripted handoffs or automation.
copy
$ open 'claude-cli://open?q=Summarize%20this%20file%0AHere%20is%20the%20context'
Lock down a shared or CI environment so plugin and slash commands cannot execute inline shell code.
json
copy
# In your Claude Code settings.json
{ "disableSkillShellExecution": true }
Adds MCP tool result persistence override via _meta["anthropic/maxResultSizeChars"] annotation (up to 500K), allowing large results like DB schemas to pass through without truncation. Not checked yet New disableSkillShellExecution setting to disable inline shell execution in skills, custom slash commands, and plugin commands. Not checked yet Supports multi-line prompts in claude-cli://open?q= deep links — encoded newlines (%0A) are no longer rejected. Not checked yet Plugins can now ship executables under bin/ and invoke them as bare commands from the Bash tool. Not checked yet
4 details in Everything
Claude Code v2.1.90 adds /powerup interactive lessons, offline plugin cache control, and faster /resume loading.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.90 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.90
└──▷ TRY IT
Launch interactive feature lessons to onboard yourself or a teammate to Claude Code capabilities.
Keep plugin marketplace working in an offline or network-restricted environment where git pull fails.
copy
$ CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 claude
Adds /powerup command: interactive lessons teaching Claude Code features with animated demos. Not checked yet Adds CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE env var to preserve the existing marketplace cache when git pull fails, enabling plugin use in offline or air-gapped environments. Not checked yet Adds .husky to the list of protected directories in acceptEdits mode. Not checked yet Improves /resume all-projects view to load project sessions in parallel, reducing wait times for users with many projects. Not checked yet Changes --resume picker to hide sessions created by claude -p or SDK invocations, keeping the list focused on interactive sessions. Not checked yet
+1 more
show less
Removes Get-DnsClientCache and ipconfig /displaydns from the auto-allow list to protect DNS cache privacy. Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! Get-DnsClientCache and ipconfig /displaydns are no longer auto-allowed; setups or scripts that relied on these commands running without a permission prompt will now require explicit approval.
Claude Code v2.1.89 adds deferred-permission hooks, flicker-free rendering, PermissionDenied hook, and faster MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connections in headless mode.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.89 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.89
└──▷ TRY IT
Pause a headless session at a sensitive tool call and let a hook re-evaluate before proceeding — useful for human-in-the-loop human-in-the-loop Human in the loop, involving a person in an otherwise automated workflow. The person can review, approve, correct or supply information before work continues. approval pipelines.
copy
$ claude -p --resume <session-id>
Speed up CI/automation runs by skipping MCP server wait entirely and capping individual server connect time at 5 s.
copy
$ MCP_CONNECTION_NONBLOCKING=true claude -p --mcp-config mcp.json '<prompt>'
Eliminate terminal flicker in long streaming sessions or when running inside a multiplexer like tmux.
copy
$ CLAUDE_CODE_NO_FLICKER=1 claude
Adds "defer" permission decision to PreToolUse hooks, letting headless sessions pause at a tool call and resume via -p --resume for hook re-evaluation. Not checked yet Adds CLAUDE_CODE_NO_FLICKER=1 environment variable to enable flicker-free alt-screen rendering with virtualized scrollback. Not checked yet Adds PermissionDenied hook that fires after auto-mode classifier denials — return {retry: true} to signal the model it can retry the tool call. Not checked yet Adds named subagents to @ mention typeahead suggestions. Not checked yet Adds MCP_CONNECTION_NONBLOCKING=true for -p mode to skip the MCP connection wait entirely; bounds --mcp-config server connections at 5 s instead of blocking on the slowest server. Not checked yet
+5 more
show less
Auto mode: denied commands now surface a notification and appear in /permissions → Recent tab where you can retry with r. Not checked yet Enables Edit to work on files viewed via Bash with sed -n or cat, without requiring a separate Read call first. Not checked yet Hook output exceeding 50 K characters is now saved to disk with a file path and preview instead of being injected directly into context. Not checked yet /env now applies to PowerShell tool commands (previously only affected Bash). Not checked yet Pasting !command into an empty prompt now enters bash mode, matching typed ! behavior. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! cleanupPeriodDays: 0 in settings.json is now rejected with a validation error (it previously silently disabled transcript persistence).! Thinking summaries are no longer generated by default in interactive sessions — existing workflows that relied on them must set showThinkingSummaries: true in settings.json.
Claude Code v2.1.86 adds session-ID headers for proxy aggregation and expands VCS VCS Version control system: software that tracks changes to files over time, letting teams collaborate and roll back mistakes. Cyber tools use it to manage source code, configs, and signatures. exclusions to Jujutsu and Sapling.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.86 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.86
└──▷ TRY IT
Filter and group Claude Code traffic in a reverse proxy or SIEM SIEM Security information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. by session without decoding request bodies.
copy
$ # In your proxy or log pipeline, match on the new header:
X-Claude-Code-Session-Id: <session-id>
Adds X-Claude-Code-Session-Id header to all API requests so proxies can correlate and aggregate a session's requests without body inspection. Not checked yet Adds .jj and .sl to VCS directory exclusion lists, preventing Grep and file autocomplete from descending into Jujutsu or Sapling metadata directories. Not checked yet Read tool now uses a compact line-number format and deduplicates unchanged re-reads, reducing token usage in file-heavy workflows. Not checked yet Memory filenames in the Saved N memories notice now highlight on hover and are clickable to open the file directly. Not checked yet Skill descriptions in the /skills listing are capped at 250 characters to reduce context consumption. Not checked yet
+5 more
show less
/skills menu now sorts alphabetically for easier scanning. Not checked yet Auto mode now displays 'unavailable for your plan' when restricted by plan limits instead of the misleading temporarily unavailable . Not checked yet Improves prompt cache hit rate for Bedrock, Vertex, and Foundry users by removing dynamic content from tool descriptions. Not checked yet Reduces startup event-loop stalls when many claude.ai MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. connectors are configured by extending the macOS keychain cache from 5 s to 30 s. Not checked yet Reduces token overhead when mentioning files with @ by no longer JSON-escaping raw string content. Not checked yet
10 details in Everything
Claude Code v2.1.85 adds conditional hook filtering, richer PreToolUse headless flows, and expanded deep-link query support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.85 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.85
└──▷ USE IT
Run a git-related hook only when Bash commands match git *, avoiding overhead for every other tool call.
json
copy
# In your hooks config (e.g., .claude/settings.json)
{
"hooks": {
"PreToolUse": [
{
"if": "Bash(git *)",
"command": "./scripts/audit-git-command.sh"
}
]
}
}
Allow a headless CI integration to answer tool-permission questions programmatically without interactive prompts.
json
copy
# PreToolUse hook returns both a permission decision and updated input
# so AskUserQuestion is satisfied without user interaction
{
"permissionDecision": "allow",
"updatedInput": { "answer": "yes" }
}
Enable full tool-parameter logging in OTEL OTEL An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. tool_result events for detailed pipeline observability.
copy
$ OTEL_LOG_TOOL_DETAILS=1 claude --mcp-config mcp.json 'audit my repo'
Adds CLAUDE_CODE_MCP_SERVER_NAME and CLAUDE_CODE_MCP_SERVER_URL environment variables to MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. headersHelper scripts, enabling a single helper script to serve multiple MCP servers. Not checked yet Adds conditional if field to hooks using permission rule syntax (e.g., Bash(git *) ) so hooks only fire for matching tool calls, reducing unnecessary process spawning. Not checked yet Adds timestamp markers in transcripts when scheduled tasks (/loop, CronCreate) fire, making it easier to audit timing of automated runs. Not checked yet Expands deep link query support (claude-cli://open?q=…) to 5,000 characters, with a scroll to review warning for long pre-filled prompts. Not checked yet MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. now follows RFC 9728 Protected Resource Metadata discovery to locate the authorization server automatically. Not checked yet
+4 more
show less
Organization-policy-blocked plugins (managed-settings.json) are now hidden from marketplace views and cannot be installed or enabled. Not checked yet PreToolUse hooks can now satisfy AskUserQuestion by returning updatedInput alongside permissionDecision: "allow", enabling headless integrations to supply answers programmatically. Not checked yet Gates tool_parameters in OpenTelemetry OpenTelemetry An open standard and set of tools for collecting traces, metrics and logs from applications. It lets services export observability data without tying instrumentation to one monitoring vendor. tool_result events behind the OTEL_LOG_TOOL_DETAILS=1 environment variable to reduce log verbosity by default. Not checked yet Improves PowerShell dangerous command detection coverage. Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! tool_parameters in OpenTelemetry tool_result events are no longer emitted by default; set OTEL_LOG_TOOL_DETAILS=1 to restore them.
Claude Code v2.1.84 adds PowerShell tool preview, new hooks, env-var overrides for 3p model capability detection, and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. deduplication.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.84 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.84
└──▷ TRY IT
Override capability detection when using a pinned Bedrock/Vertex/Foundry model that Claude Code doesn't recognize as supporting extended thinking extended thinking Intermediate reasoning a model writes out before its final answer. Reasoning models generate it automatically and it is often billed as extra output tokens. .
copy
$ ANTHROPIC_DEFAULT_OPUS_MODEL_SUPPORTS=thinking claude
Raise the streaming idle watchdog timeout to 3 minutes for slow-responding enterprise API gateways.
copy
$ CLAUDE_STREAM_IDLE_TIMEOUT_MS=180000 claude
Adds PowerShell tool for Windows as an opt-in preview, enabling native PowerShell execution alongside the existing bash tool. Not checked yet Adds ANTHROPIC_DEFAULT_{OPUS,SONNET,HAIKU}_MODEL_SUPPORTS env vars to override effort/thinking capability detection for pinned default models on Bedrock, Vertex, and Foundry; companion _MODEL_NAME/_DESCRIPTION vars customize the /model picker label. Not checked yet Adds CLAUDE_STREAM_IDLE_TIMEOUT_MS env var to configure the streaming idle watchdog threshold (default 90 s). Not checked yet Adds TaskCreated hook that fires when a task is created via TaskCreate. Not checked yet Adds type: "http" support for the WorktreeCreate hook — return the created worktree path via hookSpecificOutput.worktreePath in the response JSON. Not checked yet
+10 more
show less
Adds allowedChannelPlugins managed setting for team/enterprise admins to define a channel plugin allowlist. Not checked yet Adds x-client-request-id header to all API requests to aid timeout debugging. Not checked yet Adds idle-return prompt that nudges users back after 75+ minutes of inactivity to /clear, reducing unnecessary token re-caching on stale sessions. Not checked yet Deep links (claude-cli://) now open in the user's preferred terminal instead of the first terminal found in the detection list. Not checked yet Rules and skills paths: frontmatter now accepts a YAML list of globs, not just a single pattern. Not checked yet MCP servers configured both locally and via claude.ai connectors are now deduplicated — local config wins. Not checked yet Background bash tasks stuck on an interactive prompt now surface a notification after ~45 seconds. Not checked yet Global system-prompt caching now works when ToolSearch is enabled, including for users with MCP tools configured. Not checked yet [VSCode] Adds a rate-limit warning banner showing usage percentage and reset time. Not checked yet Stats screenshot (Ctrl+S in /stats) now works in all builds and renders 16× faster. Not checked yet
15 details in Everything
Claude Code v2.1.83 adds drop-in policy fragments, new hook events, credential scrubbing, transcript search, and agent initialPrompt support.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.83 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.83
└──▷ TRY IT
Strip cloud credentials from all subprocesses to prevent accidental credential leakage to spawned tools and MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers.
copy
$ CLAUDE_CODE_SUBPROCESS_ENV_SCRUB=1 claude
Prevent Claude Code from registering the claude-cli:// URL handler on a locked-down or shared workstation.
json
copy
# In managed-settings.json or a managed-settings.d/ fragment:
{ "disableDeepLinkRegistration": true }
Adds managed-settings.d/ drop-in directory so separate teams can deploy independent policy fragments that merge alphabetically alongside managed-settings.json. Not checked yet Adds CwdChanged and FileChanged hook events for reactive environment management (e.g., direnv integration). Not checked yet Adds sandbox.failIfUnavailable setting to exit with an error when sandbox is enabled but cannot start, instead of silently running unsandboxed. Not checked yet Adds disableDeepLinkRegistration setting to prevent claude-cli:// protocol handler registration. Not checked yet Adds CLAUDE_CODE_SUBPROCESS_ENV_SCRUB=1 environment variable to strip Anthropic and cloud provider credentials from subprocess environments (Bash tool, hooks, MCP stdio servers). Not checked yet
+10 more
show less
Adds transcript search — press / in transcript mode (Ctrl+O ) to search, then n/N to step through matches. Not checked yet Adds Ctrl+X Ctrl+E as a readline-native alias for opening the external editor (Ctrl+G still works). Not checked yet Pasted images now insert an [Image #N] chip at the cursor for positional referencing in prompts. Not checked yet Agents can now declare initialPrompt in frontmatter to auto-submit a first turn. Not checked yet chat:killAgents and chat:fastMode keybindings are now rebindable via ~/.claude/keybindings.json. Not checked yet /status now works while Claude is responding, instead of being queued until the turn finishes. Not checked yet Linux now respects XDG_DATA_HOME when registering the claude-cli:// protocol handler. Not checked yet WebFetch now identifies as Claude-User so site operators can recognize and allowlist Claude Code traffic via robots.txt. Not checked yet Increased non-streaming fallback token cap from 21k to 64k and timeout from 120s to 300s so fallback requests are less likely to be truncated. Not checked yet [VSCode] Spinner now turns red with Not responding when the backend hasn't responded for 60 seconds. Not checked yet
15 details in Everything
└──▷ BREAKING ON UPGRADE
! The 'stop all background agents' keybinding is changed from Ctrl+F to Ctrl+X Ctrl+K .! TaskOutput tool is deprecated in favor of using Read on the background task's output file path.
Claude Code v2.1.81 adds --bare flag for headless scripting and --channels permission relay to mobile devices.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.81 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.81
└──▷ TRY IT
Run a fully headless, hook-free scripted prompt in CI where only an API key is available — no OAuth, no plugin overhead.
copy
$ claude --bare -p "Summarize the security findings in findings.json" --settings ci-settings.json
Adds --bare flag for scripted -p calls — skips hooks, LSP LSP Language Server Protocol, the standard way editors get code intelligence such as completions, go-to-definition and errors from a separate per-language server. Coding agents use it to understand code. , plugin sync, and skill directory walks; requires ANTHROPIC_API_KEY or apiKeyHelper via --settings (OAuth/keychain and auto-memory disabled). Not checked yet Adds --channels permission relay so channel servers that declare the permission capability can forward tool-approval prompts to your phone. Not checked yet Updates MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. to support Client ID Metadata Document Client ID Metadata Document An OAuth 2.0 mechanism letting a client publish its own metadata (redirect URIs, grant types, contacts) at a well-known URL so authorization servers can fetch and verify it without manual registration. (CIMD CIMD A text-based Short Message Service protocol from Nokia for exchanging SMS messages between applications and SMS centers, used to build tools that send, receive, or test carrier messaging flows. / SEP-991) for servers without Dynamic Client Registration. Not checked yet Improves MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. read/search tool calls to collapse into a single Queried {server} line, expandable with Ctrl+O. Not checked yet Improves ! bash mode discoverability — Claude now suggests it when you need to run an interactive command. Not checked yet
+2 more
show less
Improves ref-tracked plugin freshness — plugins now re-clone on every load to pick up upstream changes. Not checked yet Resuming a session that was in a worktree now automatically switches back to that worktree. Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! Plan mode now hides the clear context option by default; restore it by setting "showClearContextOnPlanAccept": true in settings.! Line-by-line response streaming is disabled on Windows (including WSL WSL Windows Subsystem for Linux, a Microsoft-built compatibility layer that lets a Linux environment run directly on Windows without a virtual machine, giving cyber tools access to Linux binaries, filesystems, and syscalls on a Windows host. in Windows Terminal) due to rendering issues.
Claude Code v2.1.80 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. push channels, inline plugin settings, effort frontmatter, and rate-limit statusline fields.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.80 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.80
└──▷ TRY IT
Push messages into your session from an MCP server during a long-running workflow — currently in research preview.
Set a specific effort level for a skill or slash command so it always runs at the right cost/quality trade-off when invoked.
yaml
copy
# In your skill or slash-command frontmatter:
---
effort: low
---
Adds rate_limits field to statusline scripts exposing Claude.ai rate-limit usage across 5-hour and 7-day windows, including used_percentage and resets_at. Not checked yet Adds source: 'settings' plugin marketplace source so plugin entries can be declared inline in settings.json without a separate marketplace lookup. Not checked yet Adds CLI tool usage detection to plugin tips, supplementing existing file-pattern matching for smarter plugin suggestions. Not checked yet Adds effort frontmatter key for skills and slash commands to override the model effort level on a per-command basis. Not checked yet Adds --channels Research preview enabling MCP servers to push messages directly into a running session. Not checked yet
5 details in Everything
Claude Code v2.1.79 adds Console auth, turn-duration display, remote-control bridge, and multi-directory plugin seeds.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.79 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.79
└──▷ TRY IT
Authenticate with the Anthropic Console (API billing) instead of the default Claude.ai login flow.
copy
$ claude auth login --console
Load plugins from multiple seed directories at once — useful when team-wide and project-local plugins live in separate paths.
copy
$ CLAUDE_CODE_PLUGIN_SEED_DIR=/shared/plugins:/project/.claude/plugins claude
Bridge a running VSCode session to claude.ai/code so you can continue the conversation from a browser or phone.
Adds --console flag to claude auth login for Anthropic Console (API billing) authentication. Not checked yet Adds Show turn duration toggle to the /config menu to display how long each turn takes. Not checked yet Adds CLAUDE_CODE_PLUGIN_SEED_DIR support for multiple seed directories separated by the platform path delimiter (: on Unix, ; on Windows). Not checked yet [VSCode] Adds /remote-control command to bridge your session to claude.ai/code for continuation from a browser or phone. Not checked yet [VSCode] Session tabs now receive AI-generated titles based on your first message. Not checked yet
5 details in Everything
Claude Code v2.1.78 adds a StopFailure hook, plugin persistent state, and frontmatter-driven agent configuration.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.78 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.78
└──▷ USE IT
Trigger a Slack alert or pager when a session dies mid-run due to a rate limit or auth failure.
json
copy
# In your Claude Code hooks config, add a StopFailure handler:
{
"hooks": {
"StopFailure": "notify-on-error.sh"
}
}
Add a custom internal model (e.g. a fine-tune) to the /model picker so teammates can select it by name.
copy
$ export ANTHROPIC_CUSTOM_MODEL_OPTION=my-org/claude-fine-tune-v1
export ANTHROPIC_CUSTOM_MODEL_OPTION_NAME="FineTune v1"
export ANTHROPIC_CUSTOM_MODEL_OPTION_DESCRIPTION="Internal security-tuned variant"
claude
Store plugin state across updates so that user preferences or cached data persist after a /plugin upgrade.
copy
$ # Inside your plugin script, write persistent data to the provided path:
echo '{"last_scan": "2025-01-01"}' > "${CLAUDE_PLUGIN_DATA}/state.json"
New StopFailure hook event fires when a turn ends due to an API error (rate limit, auth failure, etc.), enabling automated error-handling workflows. Not checked yet New ${CLAUDE_PLUGIN_DATA} variable provides plugins a persistent state directory that survives plugin updates; /plugin uninstall now prompts before deleting it. Not checked yet Plugin-shipped agents can now declare effort, maxTurns, and disallowedTools in frontmatter for per-agent configuration. Not checked yet New ANTHROPIC_CUSTOM_MODEL_OPTION env var adds a custom entry to the /model picker, with optional _NAME and _DESCRIPTION suffix vars for display. Not checked yet Terminal notifications (iTerm2/Kitty/Ghostty popups, progress bar) now propagate to the outer terminal when Claude Code runs inside tmux with set -g allow-passthrough on. Not checked yet
+1 more
show less
Response text now streams line-by-line as it is generated. Not checked yet
6 details in Everything
Claude Code v2.1.77 raises output token limits to 128k, adds allowRead sandbox setting, and improves /copy, plugins, and agent resumption.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.77 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.77
└──▷ USE IT
Re-allow read access to a specific path inside a broader denyRead region for fine-grained sandbox control.
yaml
copy
# In your Claude Code sandbox config:
denyRead: ["/home/user"]
allowRead: ["/home/user/project"]
Retrieve a specific earlier assistant response — useful when you want to copy a response from several turns ago without scrolling.
Validate a plugin's frontmatter and hooks config before publishing to catch schema and YAML errors early.
copy
$ claude plugin validate ./my-plugin
Raises default max output tokens for Claude Opus 4.6 to 64k, and the upper bound for Opus 4.6 and Sonnet 4.6 models to 128k tokens. Not checked yet New allowRead sandbox filesystem setting lets you re-allow read access within denyRead regions for fine-grained filesystem control. Not checked yet /copy now accepts an optional index — /copy N copies the Nth-latest assistant response. Not checked yet Renames /fork to /branch (/fork remains as an alias). Not checked yet Background bash tasks are now killed if output exceeds 5 GB, preventing runaway processes from filling disk. Not checked yet
+8 more
show less
Sessions are now auto-named from plan content when you accept a plan. Not checked yet Improved claude plugin validate to check skill, agent, and command frontmatter plus hooks/hooks.json, catching YAML parse errors and schema violations. Not checked yet Headless mode plugin installation now composes correctly with CLAUDE_CODE_PLUGIN_SEED_DIR. Not checked yet Shows a notice when apiKeyHelper takes longer than 10s, preventing it from blocking the main loop. Not checked yet Faster startup on macOS (~60 ms) by reading keychain credentials in parallel with module loading. Not checked yet Faster --resume on fork-heavy and very large sessions — up to 45% faster loading and ~100–150 MB less peak memory. Not checked yet [VSCode] Plan preview tab titles now use the plan's heading instead of Claude's Plan . Not checked yet [VSCode] Footer now points to the macOptionClickForcesSelection setting when option+click doesn't trigger native selection on macOS. Not checked yet
13 details in Everything
└──▷ BREAKING ON UPGRADE
! The Agent tool no longer accepts a resume parameter — use SendMessage({to: agentId}) to continue a previously spawned agent.
Claude Code v2.1.76 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. elicitation, new hooks, sparse-checkout worktrees, /effort command, and session naming.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.76 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.76
└──▷ TRY IT
Name a session at startup so it's identifiable in Remote Control session lists and logs.
copy
$ claude -n "incident-2025-investigation" --worktree
Load plugins from two separate directories (e.g. company-wide and personal) using the updated --plugin-dir flag.
copy
$ claude --plugin-dir /opt/company-plugins --plugin-dir ~/.local/claude-plugins
Adds MCP elicitation support — MCP servers can now request structured input mid-task via an interactive dialog (form fields or browser URL). Not checked yet Adds Elicitation and ElicitationResult hooks to intercept and override MCP elicitation responses before they're sent back. Not checked yet Adds -n / --name <name> CLI flag to set a display name for a session at startup. Not checked yet Adds worktree.sparsePaths setting for claude --worktree to check out only specified directories via git sparse-checkout in large monorepos. Not checked yet Adds PostCompact hook that fires after conversation compaction completes. Not checked yet
+4 more
show less
Adds /effort slash command to set the model effort level interactively. Not checked yet Adds session quality survey with configurable sample rate via the feedbackSurveyRate setting for enterprise admins. Not checked yet Improves background agent behavior — killing a background agent now preserves its partial results in the conversation context. Not checked yet Updates --plugin-dir to support repeated use for multiple directories (one path per flag). Not checked yet
9 details in Everything
└──▷ BREAKING ON UPGRADE
! --plugin-dir now only accepts one path per flag; use repeated --plugin-dir flags to specify multiple plugin directories.
Claude Code v2.1.74 adds actionable /context optimization tips and a configurable auto-memory directory.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.74 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.74
└──▷ USE IT
Redirect auto-memory storage to a shared or project-specific path rather than the default location.
json
copy
# In your Claude Code settings (e.g., settings.json)
{
"autoMemoryDirectory": "/home/user/projects/myproject/.claude-memory"
}
Spot which tools or memories are eating your context budget and get specific tips to reclaim space before hitting limits.
Sideload a local plugin build that overrides a same-named marketplace plugin during development.
copy
$ claude --plugin-dir ./my-plugin-dev-copy
Adds actionable suggestions to the /context command — identifies context-heavy tools, memory bloat, and capacity warnings with specific optimization tips. Not checked yet Adds autoMemoryDirectory setting to configure a custom directory for auto-memory storage. Not checked yet Changes --plugin-dir so local dev copies now override installed marketplace plugins with the same name (unless force-enabled by managed settings). Not checked yet
3 details in Everything
Claude Code v2.1.73 adds modelOverrides for custom provider model IDs and actionable SSL SSL A cryptographic protocol for encrypting network connections, now deprecated in favor of TLS but whose name persists colloquially. Cyber tools reference it when handling HTTPS or other encrypted-channel inspection and termination. error guidance for corporate proxy users.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.73 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.73
└──▷ USE IT
Route model picker selections to a specific Bedrock inference profile ARN instead of the default model ID.
json
copy
# In your Claude Code settings (e.g. ~/.claude/settings.json)
{
"modelOverrides": {
"claude-opus-4-5": "arn:aws:bedrock:us-east-1::foundation-model/your-inference-profile-arn"
}
}
Adds modelOverrides setting to map model picker entries to custom provider model IDs (e.g., Bedrock inference profile ARNs). Not checked yet Adds actionable guidance when OAuth login or connectivity checks fail due to SSL certificate errors (corporate proxies, NODE_EXTRA_CA_CERTS). Not checked yet Updates default Opus model on Bedrock, Vertex, and Microsoft Foundry to Opus 4.6. Not checked yet Enables /effort command to work while Claude is responding, matching /model behavior. Not checked yet
4 details in Everything
└──▷ BREAKING ON UPGRADE
! The /output-style command is deprecated; output style is now fixed at session start for better prompt caching — use /config instead.
Claude Code v2.1.72 adds file-write in /copy, /plan descriptions, ExitWorktree tool, cron control, and a VS Code URI handler.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.72 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.72
└──▷ TRY IT
Write a focused selection to a file over SSH without relying on clipboard access.
copy
$ # In an active Claude Code session, open the copy picker with /copy, highlight the desired block, then press `w` to write it directly to a file.
Jump straight into plan mode with context so Claude starts immediately rather than waiting for a follow-up prompt.
copy
$ claude> /plan fix the auth bug
Stop all scheduled cron jobs mid-session without restarting Claude Code.
copy
$ CLAUDE_CODE_DISABLE_CRON=1 claude
Open a new Claude Code tab in VS Code programmatically with a pre-filled prompt from an external script or tool.
copy
$ open 'vscode://anthropic.claude-code/open?prompt=explain+this+file&session=abc123'
Adds w key in /copy to write the focused selection directly to a file, bypassing the clipboard — useful over SSH. Not checked yet Adds optional description argument to /plan (e.g., /plan fix the auth bug) to enter plan mode and immediately start working. Not checked yet Adds ExitWorktree tool to cleanly leave an EnterWorktree session. Not checked yet Adds CLAUDE_CODE_DISABLE_CRON environment variable to immediately stop scheduled cron jobs mid-session. Not checked yet Adds lsof, pgrep, tput, ss, fd, and fdfind to the bash auto-approval allowlist, reducing permission prompts for common read-only operations. Not checked yet
+9 more
show less
Adds support for marketplace git URLs without a .git suffix (Azure DevOps, AWS CodeCommit). Not checked yet Adds claude plugins as an alias for claude plugin. Not checked yet Simplifies effort levels to low/medium/high (removed max) with new symbols (○ ◐ ●); adds /effort auto to reset to default. Not checked yet Improves /config keyboard UX — Escape cancels changes, Enter saves and closes, Space toggles settings. Not checked yet Improves up-arrow history to show the current session's messages first when running multiple concurrent sessions. Not checked yet Improves voice input transcription accuracy for repo names and common dev terms (regex, OAuth, JSON). Not checked yet Hides CLAUDE.md HTML comments (<!-- ... -->) from Claude when auto-injected; comments remain visible when read with the Read tool. Not checked yet VSCode: Adds vscode://anthropic.claude-code/open URI handler to open a new Claude Code tab programmatically, with optional prompt and session query parameters. Not checked yet VSCode: Adds effort level indicator on the input border. Not checked yet
14 details in Everything
└──▷ BREAKING ON UPGRADE
! The CLAUDE_CODE_PROXY_SUPPORTS_TOOL_REFERENCE environment variable has been removed; the tool search proxy bypass is now controlled by a different environment variable.! Effort level max has been removed; valid levels are now low, medium, and high only.
Claude Code v2.1.71 adds /loop scheduling, rebindable push-to-talk voice, and expands bash auto-approval allowlist
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.71 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.71
└──▷ TRY IT
Continuously poll a deploy status every 5 minutes without manually re-running the prompt — useful for watching long-running CI/CD pipelines.
copy
$ /loop 5m check the deploy
Rebind push-to-talk to a modifier+letter combo that won't interfere with typing, then activate voice hands-free.
json
copy
// In keybindings.json
{ "voice:pushToTalk": "meta+k" }
New /loop command runs a prompt or slash command on a recurring interval (e.g. /loop 5m check the deploy) Not checked yet Adds cron scheduling tools for recurring prompts within a session Not checked yet New voice:pushToTalk keybinding makes the voice activation key rebindable in keybindings.json (default: space); supports modifier+letter combos like meta+k Not checked yet Expands bash auto-approval allowlist with fmt, comm, cmp, numfmt, expr, test, printf, getconf, seq, tsort, and pr Not checked yet Updates /debug to toggle debug logging on mid-session without requiring a restart Not checked yet
+2 more
show less
Improves /plugin uninstall to disable project-scoped plugins in .claude/settings.local.json instead of .claude/settings.json, keeping changes out of shared teammate config Not checked yet Plugin-provided MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers that duplicate a manually-configured server (same command/URL) are now automatically skipped, with suppressions shown in the /plugin menu Not checked yet
7 details in Everything
Claude Code v2.1.70 adds VS Code session browser, plan markdown view, and native MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. server management dialog.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.70 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.70
└──▷ TRY IT
Manage MCP servers (enable/disable, reconnect, OAuth) directly from the VS Code chat panel without switching to a terminal.
Adds a spark icon in the VS Code activity bar listing all Claude Code sessions, with sessions opening as full editors. Not checked yet Adds a full markdown document view for plans in VS Code, including support for inline comments to provide feedback. Not checked yet Adds a native MCP server management dialog via /mcp in the VS Code chat panel — enable/disable servers, reconnect, and manage OAuth authentication without leaving the editor. Not checked yet
3 details in Everything
Claude Code v2.1.69 adds Voice STT in 20 languages, new hook events, plugin hot-reload, and a suite of new settings and CLI options.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.69 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.69
└──▷ TRY IT
Strip Claude's default git commit/PR instructions from the system prompt when your team enforces its own commit conventions via a CLAUDE.md rule.
copy
$ CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS=1 claude
Hot-reload plugins mid-session after editing a SKILL.md or plugin manifest, without restarting Claude Code.
Adds /claude-api skill for building applications with the Claude API and Anthropic SDK Not checked yet Adds Ctrl+U on an empty bash prompt (!) to exit bash mode, matching Escape and Backspace Not checked yet Adds numeric keypad support for selecting options in Claude's interview questions Not checked yet Adds optional --name argument to /remote-control and claude remote-control to set a custom session title visible in claude.ai/code Not checked yet Expands Voice STT support to 20 total languages, adding Russian, Polish, Turkish, Dutch, Ukrainian, Greek, Czech, Danish, Swedish, and Norwegian Not checked yet
+16 more
show less
Adds effort level display (e.g., with low effort ) to the logo and spinner so the active effort setting is always visible Not checked yet Adds agent name display in the terminal title when using claude --agent Not checked yet Adds sandbox.enableWeakerNetworkIsolation setting (macOS only) to allow Go programs like gh, gcloud, and terraform to verify TLS certificates when using a custom MITM MITM A man-in-the-middle attack, where an adversary secretly intercepts and optionally alters traffic between two parties who believe they are communicating directly. Cyber tools use it to inspect or manipulate encrypted sessions. proxy with httpProxyPort Not checked yet Adds includeGitInstructions setting and CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS env var to remove built-in commit and PR workflow instructions from Claude's system prompt Not checked yet Adds /reload-plugins command to activate pending plugin changes without restarting Not checked yet Adds ${CLAUDE_SKILL_DIR} variable so skills can reference their own directory in SKILL.md content Not checked yet Adds InstructionsLoaded hook event that fires when CLAUDE.md or .claude/rules/*.md files are loaded into context Not checked yet Adds agent_id and agent_type fields to hook events for subagent and --agent sessions Not checked yet Adds worktree field to status line hook commands with name, path, branch, and original repo directory in --worktree sessions Not checked yet Adds pluginTrustMessage in managed settings to append organization-specific context to the plugin trust warning Not checked yet Adds pathPattern to strictKnownMarketplaces for regex-matching file/directory marketplace sources alongside hostPattern restrictions Not checked yet Adds plugin source type git-subdir to point to a subdirectory within a git repo Not checked yet Adds oauth.authServerMetadataUrl config option for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers to specify a custom OAuth metadata discovery URL when standard discovery fails Not checked yet Extends policy limit fetching (e.g., remote control restrictions) to Team plan OAuth users, not just Enterprise Not checked yet [VSCode] Adds compaction display as a collapsible Compacted chat card with the summary inside Not checked yet [VSCode] Permission mode picker now respects permissions.disableBypassPermissionsMode from effective Claude Code settings Not checked yet
21 details in Everything
Claude Code v2.1.68 adds ultrathink keyword for on-demand high-effort reasoning and defaults Opus 4.6 to medium effort.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.68 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.68
└──▷ TRY IT
Force maximum reasoning depth on a single turn when tackling a complex architectural or security analysis problem.
copy
$ ultrathink — type this keyword in your message to Claude Code to elevate the next turn to high effort
Re-introduces the ultrathink keyword to trigger high-effort reasoning mode for the next turn. Not checked yet Opus 4.6 now defaults to medium effort for Max and Team subscribers, balancing speed and thoroughness. Not checked yet
2 details in Everything
└──▷ BREAKING ON UPGRADE
! Opus 4 and Opus 4.1 are removed from Claude Code on the first-party API; users with either model pinned are automatically migrated to Opus 4.6.
Claude Code v2.1.63 adds HTTP hooks, /simplify & /batch slash commands, and cross-worktree config sharing.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.63 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.63
└──▷ TRY IT
Opt out of claude.ai MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers entirely for a session — useful in air-gapped or compliance-restricted environments.
copy
$ ENABLE_CLAUDEAI_MCP_SERVERS=false claude
Adds /simplify and /batch bundled slash commands. Not checked yet Adds HTTP hooks: POST JSON to a URL and receive JSON back, as an alternative to shell command hooks. Not checked yet Adds ENABLE_CLAUDEAI_MCP_SERVERS=false environment variable to opt out of claude.ai MCP servers. Not checked yet Improves /model command to display the currently active model in the slash command menu. Not checked yet Project configs and auto memory are now shared across git worktrees of the same repository. Not checked yet
+3 more
show less
Adds manual URL paste fallback during MCP OAuth MCP OAuth An authentication layer for the Model Context Protocol that lets MCP clients obtain delegated access tokens so cyber tools can call MCP servers on a user's behalf without handling raw credentials. authentication when the automatic localhost redirect fails. Not checked yet Adds Always copy full response option to the /copy picker, skipping the code block picker for future /copy calls. Not checked yet VSCode: Adds session rename and remove actions to the sessions list. Not checked yet
8 details in Everything
Claude Code v2.1.59 adds auto-memory saving, a /copy picker for code blocks, and smarter always-allow bash prefixes.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.59 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.59
└──▷ TRY IT
After a session, review and edit what Claude auto-saved to persistent memory so future sessions inherit the right context.
When a response contains multiple code blocks, pick exactly the one snippet you want on your clipboard instead of manually selecting text.
Adds auto-memory: Claude automatically saves useful context to persistent memory, manageable via the /memory command. Not checked yet New /copy command opens an interactive picker to select and copy individual code blocks or the full response. Not checked yet Smarter always allow prefix suggestions for compound bash commands — computes per-subcommand prefixes (e.g. each part of cd /tmp && git fetch && git push) instead of treating the whole command as one unit. Not checked yet Reduces memory usage in multi-agent sessions by releasing completed subagent task state. Not checked yet
4 details in Everything
Claude Code v2.1.51 adds remote-control subcommand, custom npm registry support for plugins, and new SDK account environment variables.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.51 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.51
└──▷ TRY IT
Serve your local Claude Code environment to an external build system using the new remote-control subcommand.
copy
$ claude remote-control
Extend the plugin git clone timeout when working behind a slow corporate proxy to avoid installation failures.
copy
$ CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS=300000 claude
Provide account metadata to Claude Code synchronously in SDK/CI contexts so telemetry events are correctly attributed from the very first event.
copy
$ CLAUDE_CODE_ACCOUNT_UUID=<uuid> CLAUDE_CODE_USER_EMAIL=user@example.com CLAUDE_CODE_ORGANIZATION_UUID=<org-uuid> claude --print "<prompt>"
Adds claude remote-control subcommand for external builds, enabling local environment serving for all users. Not checked yet Adds CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS environment variable to configure plugin marketplace git timeout (default raised from 30s to 120s). Not checked yet Supports custom npm registries and specific version pinning when installing plugins from npm sources. Not checked yet Reduces the tool-result disk-persistence threshold from 100K to 50K characters, lowering context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. consumption and extending conversation longevity. Not checked yet Adds CLAUDE_CODE_ACCOUNT_UUID, CLAUDE_CODE_USER_EMAIL, and CLAUDE_CODE_ORGANIZATION_UUID environment variables so SDK callers can supply account metadata synchronously, eliminating a race condition in early telemetry. Not checked yet
+2 more
show less
Routes HTTP hooks through the sandbox network proxy when sandboxing sandboxing Running code inside a restricted environment that limits what it can access or change. The isolation reduces the impact of mistakes or untrusted code, depending on the sandbox's controls. is enabled, enforcing the domain allowlist. Not checked yet The /model picker now shows human-readable labels (e.g., Sonnet 4.5 ) instead of raw model IDs for pinned versions, with an upgrade hint when a newer version is available. Not checked yet
7 details in Everything
└──▷ BREAKING ON UPGRADE
! BashTool now skips the login shell (-l flag) by default when a shell snapshot is available (previously required setting CLAUDE_BASH_NO_LOGIN=true to achieve this); environments that relied on login-shell initialization running unconditionally may behave differently.! HTTP hook header values no longer interpolate arbitrary environment variables — env var interpolation now requires an explicit allowedEnvVars list in the hook configuration, so existing hooks using env var interpolation in headers will stop expanding those variables.
Claude Code v2.1.50 adds worktree isolation for agents, new hook events, claude agents CLI command, and 1M context controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.50 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.50
└──▷ TRY IT
List all configured agents to audit what's available in your Claude Code setup.
Declare an agent that runs in its own isolated git worktree, keeping changes sandboxed from your main branch.
yaml
copy
isolation: worktree
Disable 1M context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. support to control token usage or costs in environments where smaller context is preferred.
copy
$ CLAUDE_CODE_DISABLE_1M_CONTEXT=1 claude -p "summarize this repo"
Adds WorktreeCreate and WorktreeRemove hook events for custom VCS VCS Version control system: software that tracks changes to files over time, letting teams collaborate and roll back mistakes. Cyber tools use it to manage source code, configs, and signatures. setup and teardown during agent worktree isolation. Not checked yet Supports isolation: worktree in agent definitions, letting agents declaratively run in isolated git worktrees. Not checked yet New claude agents CLI command lists all configured agents. Not checked yet Adds startupTimeout configuration option for LSP LSP Language Server Protocol, the standard way editors get code intelligence such as completions, go-to-definition and errors from a separate per-language server. Coding agents use it to understand code. servers. Not checked yet Adds CLAUDE_CODE_DISABLE_1M_CONTEXT environment variable to disable 1M context window support. Not checked yet
+5 more
show less
Opus 4.6 (fast mode) now includes the full 1M context window. Not checked yet CLAUDE_CODE_SIMPLE mode now also disables MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools, attachments, hooks, and CLAUDE.md file loading for a fully minimal experience. Not checked yet VSCode: Adds /extra-usage command support in VS Code sessions. Not checked yet Improves startup performance for headless mode (-p flag) by deferring Yoga WASM WASM A binary instruction format for a stack-based virtual machine, maintained by the W3C, that lets code compiled from any language run at near-native speed inside a sandboxed environment across browsers and servers. and UI component imports. Not checked yet Improves memory efficiency during long sessions by clearing internal caches after compaction and clearing large tool results after processing. Not checked yet
10 details in Everything
Claude Code v2.1.49 adds file editing in Simple mode, ConfigChange hooks for auditing, and richer SDK model capability discovery.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.49 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.49
└──▷ TRY IT
Use Simple mode for lightweight file-editing tasks without needing a full agent setup.
copy
$ CLAUDE_CODE_SIMPLE=1 claude
Simple mode (CLAUDE_CODE_SIMPLE) now includes the file edit tool alongside the Bash tool, enabling direct file editing without leaving simple mode. Not checked yet New ConfigChange hook event fires when configuration files change mid-session, enabling enterprise security auditing and optional blocking of settings changes. Not checked yet SDK model info now exposes supportsEffort, supportedEffortLevels, and supportsAdaptiveThinking fields so consumers can programmatically discover model capabilities. Not checked yet Permission suggestions are now populated when safety checks trigger an ask response, enabling SDK consumers to surface permission options to users. Not checked yet Pressing Ctrl+C or ESC twice within 3 seconds now kills all background agents when the main thread is idle. Not checked yet
+1 more
show less
Improved permission prompts for path safety and working directory blocks now display the reason for the restriction. Not checked yet
6 details in Everything
└──▷ BREAKING ON UPGRADE
! Sonnet 4.5 with 1M context is being removed from the Max plan in favor of Sonnet 4.6 (which now has 1M context); users must switch via /model.
Claude Code v2.1.47 adds new hook fields, keybindings, statusline data, and smarter background-agent lifecycle controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.47 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.47
└──▷ TRY IT
Kill all running background agents at once without interrupting the main thread.
copy
$ # While Claude Code is running, press ctrl+f to terminate all background agents instantly.
Adds last_assistant_message field to Stop and SubagentStop hook inputs, letting hooks read the final assistant response without parsing transcript files. Not checked yet Adds chat:newline keybinding action for configurable multi-line input. Not checked yet Adds added_dirs to the statusline JSON workspace section, exposing directories added via /add-dir to external scripts. Not checked yet New ctrl+f shortcut kills all background agents; pressing ESC now cancels only the main thread while background agents keep running, giving finer control over agent lifecycle. Not checked yet The /rename command now also updates the terminal tab title. Not checked yet
+3 more
show less
Increases initial session count in the /resume picker from 10 to 50 for faster session discovery. Not checked yet Config backup files are now stored in ~/.claude/backups/ instead of the home directory root. Not checked yet VS Code plan preview auto-updates as Claude iterates and keeps the preview open on rejection so Claude can revise. Not checked yet
8 details in Everything
Claude Code v2.1.45 adds Claude Sonnet 4.6 support, SDK rate-limit types, and richer plugin/spinner customization.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.45 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.45
└──▷ USE IT
Suppress all default spinner tips and show only your team's custom messages during long operations.
json
copy
In your Claude Code settings (e.g. .claude/settings.json), add:
{
"spinnerTipsOverride": {
"tips": ["Hang tight — running your scan…", "Almost there…"],
"excludeDefault": true
}
}
Load a shared plugin and marketplace config from a team-wide directory so all members get the same plugins without touching per-repo config.
copy
$ claude --add-dir /shared/team-claude-config
Supports Claude Sonnet 4.6 as a selectable model. Not checked yet Reads enabledPlugins and extraKnownMarketplaces from --add-dir directories, enabling plugin and marketplace configuration via added directories. Not checked yet New spinnerTipsOverride setting lets you supply custom spinner tip strings and optionally suppress built-in tips with excludeDefault: true. Not checked yet New SDKRateLimitInfo and SDKRateLimitEvent types expose rate-limit utilization, reset times, and overage data to SDK consumers. Not checked yet [VSCode] Permission destination choice (project/user/session) now persists across sessions. Not checked yet
5 details in Everything
Claude Code v2.1.41 adds auth subcommands, Windows ARM64 ARM64 A 64-bit CPU architecture from ARM Holdings, used in mobile chips, Apple Silicon, and cloud servers; cyber tools target it to run natively on those platforms instead of relying on emulation. support, and smarter /rename.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.41 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.41
└──▷ TRY IT
Check your current authentication state without opening a browser — useful in CI or remote SSH sessions.
copy
$ claude auth status
Log in to Claude Code from the CLI, e.g. when setting up a new machine or switching accounts.
Let Claude name the current session automatically based on what you've discussed, instead of typing a name manually.
Adds claude auth login, claude auth status, and claude auth logout CLI subcommands for managing authentication from the terminal. Not checked yet Adds native Windows ARM64 (win32-arm64) binary support. Not checked yet Improves /rename to auto-generate a session name from conversation context when called without arguments. Not checked yet
3 details in Everything
Claude Code v2.1.33 adds multi-agent hook events, sub-agent spawn restrictions, persistent agent memory, and VSCode remote sessions.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.33 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.33
└──▷ USE IT
Restrict an orchestrator agent so it can only spawn specific sub-agent types, reducing blast radius in automated pipelines.
yaml
copy
# In agent frontmatter (tools section):
---
tools:
- Task(researcher)
- Task(summarizer)
---
Give an agent persistent memory scoped to the current project so context survives across sessions.
yaml
copy
# In agent frontmatter:
---
memory: project
---
Adds TeammateIdle and TaskCompleted hook events for multi-agent workflows, enabling automation when agents become idle or complete tasks. Not checked yet Supports restricting which sub-agents can be spawned via Task(agent_type) syntax in agent tools frontmatter. Not checked yet Adds memory frontmatter field for agents with user, project, or local scope for persistent memory across sessions. Not checked yet Adds plugin name to skill descriptions and the /skills menu for improved discoverability. Not checked yet Improves API connection failure error messages to show specific causes (e.g., ECONNREFUSED, SSL SSL A cryptographic protocol for encrypting network connections, now deprecated in favor of TLS but whose name persists colloquially. Cyber tools reference it when handling HTTPS or other encrypted-channel inspection and termination. errors) instead of generic messages. Not checked yet
+3 more
show less
Surfaces errors from invalid managed settings. Not checked yet VSCode: Adds support for remote sessions, allowing OAuth users to browse and resume sessions from claude.ai. Not checked yet VSCode: Adds git branch and message count to the session picker with branch-name search support. Not checked yet
8 details in Everything
Claude Code v2.1.32 adds Opus 4.6, experimental multi-agent teams, automatic memory, and partial conversation summarization.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.32 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.32
└──▷ TRY IT
Spin up an experimental multi-agent team session to tackle complex, parallelizable tasks.
copy
$ CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 claude
Adds Claude Opus 4.6 model support. Not checked yet Introduces experimental multi-agent collaboration via agent teams (enable with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1). Not checked yet Claude now automatically records and recalls memories as it works across sessions. Not checked yet Adds Summarize from here option in the message selector for partial conversation summarization. Not checked yet Skills defined in .claude/skills/ inside --add-dir directories are now loaded automatically. Not checked yet
+2 more
show less
Skill character budget now scales with context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. size (2% of context), allowing more skill descriptions to appear untruncated for users with larger context windows context windows The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. . Not checked yet VSCode: Adds a spinner when loading the past conversations list. Not checked yet
7 details in Everything
Claude Code v2.1.31 adds session resume hints and Japanese IME support in checkbox selection.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.31 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.31
Adds a session resume hint on exit, showing the command to continue a conversation later. Not checked yet Supports full-width (zenkaku) space input from Japanese IME in checkbox selection. Not checked yet
2 details in Everything
Claude Code v2.1.30 adds PDF page-range reading, OAuth credentials for MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers, and a new /debug command
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.30 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.30
└──▷ TRY IT
Register a Slack MCP server that requires pre-configured OAuth credentials instead of Dynamic Client Registration.
copy
$ claude mcp add slack-mcp --client-id <your-client-id> --client-secret <your-client-secret>
Adds pages parameter to the Read tool for PDFs, enabling specific page ranges (e.g., pages: "1-5"); large PDFs (>10 pages) now return a lightweight reference when @-mentioned instead of being inlined into context Not checked yet Adds pre-configured OAuth client credentials for MCP servers that lack Dynamic Client Registration support (e.g., Slack) via new --client-id and --client-secret flags on claude mcp add Not checked yet Adds /debug command for Claude to help troubleshoot the current session Not checked yet Supports additional git log and git show flags in read-only mode, including --topo-order, --cherry-pick, --format, and --raw Not checked yet Adds token count, tool uses, and duration metrics to Task tool results Not checked yet
+4 more
show less
Adds reduced motion mode to the config Not checked yet Improves --resume memory usage by 68% for users with many sessions via lightweight stat-based loading and progressive enrichment Not checked yet Changes /model to execute immediately instead of being queued Not checked yet [VSCode] Adds multiline input support to the Other text input in question dialogs via Shift+Enter Not checked yet
9 details in Everything
Claude Code v2.1.27 adds --from-pr flag for PR-linked session resumption and automatic PR linking via gh pr create.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.27 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.27
└──▷ TRY IT
Pick up a Claude Code session exactly where you left off for a specific pull request, by PR number or full URL.
copy
$ claude --from-pr 42
Resume a session using a full PR URL instead of a number — useful when working across multiple repos.
copy
$ claude --from-pr https://github.com/myorg/myrepo/pull/42
New --from-pr flag lets you resume a session linked to a specific GitHub PR number or URL. Not checked yet Sessions created via gh pr create are now automatically linked to the corresponding PR. Not checked yet Tool call failures and denials are now recorded in debug logs for easier troubleshooting workflows. Not checked yet VSCode: Enables the Claude in Chrome integration. Not checked yet Permissions now respect content-level ask over tool-level allow, so granular deny patterns like ask: ["Bash(rm *)"] correctly override a broad allow: ["Bash"]. Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! Permission evaluation order has changed: a content-level ask rule now takes precedence over a tool-level allow. Configurations using allow: ["Bash"], ask: ["Bash(rm *)"] that previously permitted all Bash commands will now prompt for permission on rm commands.
Claude Code v2.1.23 adds customizable spinner verbs and shows PR merge status and timeout durations in the UI.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.23 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.23
Adds spinnerVerbs setting to customize the verbs displayed in the activity spinner. Not checked yet Shows timeout duration alongside elapsed time for Bash commands. Not checked yet Displays a purple status indicator in the prompt footer for merged pull requests. Not checked yet
3 details in Everything
Claude Code v2.1.21 adds Japanese IME input support and automatic Python venv activation in VS Code.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.21 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.21
└──▷ USE IT
Opt out of automatic Python venv activation in VS Code if you manage your interpreter another way.
json
copy
// In VS Code settings.json
{ "claudeCode.usePythonEnvironment": false }
Supports full-width (zenkaku) number input from Japanese IME in option selection prompts. Not checked yet Adds automatic Python virtual environment activation in the VS Code extension, ensuring python and pip use the correct interpreter (configurable via claudeCode.usePythonEnvironment). Not checked yet Improves read/search progress indicators to show Reading… while in progress and Read when complete. Not checked yet Improves Claude's preference for file operation tools (Read, Edit, Write) over bash equivalents (cat, sed, awk). Not checked yet
4 details in Everything
Claude Code v2.1.20 adds PR review status in the footer, vim history nav, TaskUpdate deletions, and per-directory CLAUDE.md loading.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.20 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.20
└──▷ TRY IT
Load project-specific CLAUDE.md instructions from a shared config directory alongside the default working directory.
copy
$ CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD=1 claude --add-dir /path/to/shared-config
Adds arrow key history navigation in vim normal mode when the cursor cannot move further. Not checked yet Adds external editor shortcut (Ctrl+G) to the help menu for easier discovery. Not checked yet Adds PR review status indicator to the prompt footer showing the current branch's PR state (approved, changes requested, pending, or draft) as a colored dot with a clickable link. Not checked yet Supports loading CLAUDE.md files from additional directories specified via --add-dir (requires CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD=1). Not checked yet Adds ability to delete tasks via the TaskUpdate tool. Not checked yet
+7 more
show less
Improves /sandbox command UI to show dependency status with installation instructions when dependencies are missing. Not checked yet Enables the /commit-push-pr skill to automatically post PR URLs to configured Slack channels via MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tools. Not checked yet Makes the /copy command available to all users. Not checked yet Changes background agents to prompt for tool permissions before launching. Not checked yet Accepts wildcard permission rules like Bash(*) and treats them as equivalent to Bash . Not checked yet Renders teammate messages with rich Markdown formatting (bold, code blocks, lists, etc.) instead of plain text. Not checked yet Changes ToolSearch results to appear as a brief notification instead of inline in the conversation. Not checked yet
12 details in Everything
Claude Code v2.1.19 adds a Tasks system, argument shorthands for custom commands, and session forking/rewind for all VS Code users.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.19 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.19
└──▷ TRY IT
Use positional argument shorthands in a custom command to pass the first two arguments directly, e.g. a file path and a label.
copy
$ # In a custom command definition:
# Analyze $0 and tag the result as $1
analyze_file $0 --tag $1
Adds $0, $1, etc. shorthand syntax for accessing individual arguments in custom commands. Not checked yet Changes indexed argument syntax from $ARGUMENTS.0 to $ARGUMENTS[0] (bracket notation). Not checked yet Skills without additional permissions or hooks are now allowed without requiring approval. Not checked yet [SDK] Adds replay of queued_command attachment messages as SDKUserMessageReplay events when replayUserMessages is enabled. Not checked yet [VS Code] Session forking and rewind functionality is now enabled for all users. Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! Indexed argument syntax for custom commands changed from $ARGUMENTS.0 to $ARGUMENTS[0]; existing custom commands using the old dot notation will need to be updated.
Claude Code v2.1.16 adds task management with dependency tracking, native VSCode plugin management, and remote session browsing for OAuth users.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.16 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.16
New task management system with dependency tracking between tasks. Not checked yet [VSCode] Native plugin management support added to the IDE extension. Not checked yet [VSCode] OAuth users can now browse and resume remote Claude sessions from the Sessions dialog. Not checked yet
3 details in Everything
Claude Code v2.1.14 adds history-based Tab autocomplete in bash mode, plugin search, SHA pinning, and a VSCode /usage command.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.14 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.14
└──▷ TRY IT
Quickly re-run a recent shell command in bash mode without retyping it — type the start of the command after ! and press Tab to pull from history.
copy
$ ! git log --on<Tab> # completes to a previously run git command from your bash history
Adds history-based Tab autocomplete in bash mode (!) — type a partial command and press Tab to complete from your shell history. Not checked yet Adds search/filter to the installed plugins list — type to filter by plugin name or description. Not checked yet Supports pinning plugins to specific git commit SHAs, enabling marketplace entries to install exact versions. Not checked yet Improves backspace to delete pasted text as a single token rather than one character at a time. Not checked yet [VSCode] Adds /usage command to display current plan usage. Not checked yet
5 details in Everything
Claude Code v2.1.9 adds auto:N MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. threshold syntax, plansDirectory setting, external editor in prompts, and richer hook/skill APIs.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.9 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.9
└──▷ USE IT
Store plan files in a project-local directory so plans are version-controlled alongside your code.
json
copy
# In your Claude Code settings (settings.json)
{ "plansDirectory": ".claude/plans" }
Inject the current session ID into a skill command so downstream scripts can correlate activity back to the Claude session.
json
copy
# In a skill definition
{ "command": "my-audit-tool --session ${CLAUDE_SESSION_ID}" }
Adds auto:N syntax to set the MCP tool search auto-enable threshold as a context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. percentage (0–100). Not checked yet Adds plansDirectory setting to customize where plan files are stored. Not checked yet Adds external editor support (Ctrl+G) inside AskUserQuestion Other input fields. Not checked yet Adds session URL attribution to commits and PRs created from web sessions. Not checked yet Enables PreToolUse hooks to return additionalContext directly to the model. Not checked yet
+1 more
show less
Adds ${CLAUDE_SESSION_ID} string substitution so skills can access the current session ID. Not checked yet
6 details in Everything
Claude Code v2.1.7 adds MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. tool search auto mode, permission feedback, and task notification previews.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.7 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.7
└──▷ TRY IT
Opt out of MCP tool search auto mode if you need all tool descriptions loaded upfront rather than discovered on demand.
copy
$ claude config set disallowedTools '["MCPSearch"]'
Adds showTurnDuration setting to hide turn-duration messages like Cooked for 1m 6s . Not checked yet Enables feedback submission when accepting permission prompts. Not checked yet Adds inline display of the agent's final response in task notifications, so results are visible without opening the full transcript. Not checked yet Enables MCP tool search auto mode by default: when MCP tool descriptions exceed 10% of the context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. , they are deferred and discovered on-demand via the MCPSearch tool, reducing upfront context consumption for users with many MCP tools. Not checked yet Updates OAuth and API Console URLs from console.anthropic.com to platform.claude.com. Not checked yet
5 details in Everything
└──▷ BREAKING ON UPGRADE
! MCP tool search auto mode is now on by default; users who relied on all MCP tool descriptions being loaded upfront must add MCPSearch to disallowedTools in their settings to restore the previous behaviour.
Claude Code v2.1.6 adds config search, date-ranged stats, nested skills discovery, and richer context window context window The maximum amount of text, counted in tokens, a model can take in and produce in one request. Everything the model knows about the task has to fit inside it. metrics.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.6 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.6
└──▷ TRY IT
Review spending or usage trends over the last week vs. month without leaving the terminal.
copy
$ /stats # then press 'r' to cycle through Last 7 days / Last 30 days / All time
Display remaining context window capacity in the status line by referencing the new percentage fields.
copy
$ # In your status line config, reference the new fields:
# context_window.used_percentage
# context_window.remaining_percentage
Adds search/filter functionality inside the /config command for quickly locating settings. Not checked yet Adds an Updates section to /doctor showing the auto-update channel and available npm versions (stable/latest). Not checked yet Adds date range filtering to /stats — press r to cycle between Last 7 days, Last 30 days, and All time. Not checked yet Adds automatic discovery of skills from nested .claude/skills directories when working with files in subdirectories. Not checked yet Adds context_window.used_percentage and context_window.remaining_percentage fields to the status line for easier context window display. Not checked yet
+5 more
show less
Improves the external CLAUDE.md imports approval dialog to show which files are being imported and from where. Not checked yet Improves /tasks dialog to go directly to task details when only one background task is running. Not checked yet Improves @ autocomplete with icons for different suggestion types and single-line formatting. Not checked yet Changes terminal title to Claude Code on startup for better window identification. Not checked yet Caps task notification display at 3 lines with an overflow summary when multiple background tasks complete simultaneously. Not checked yet
10 details in Everything
└──▷ BREAKING ON UPGRADE
! The ability to @-mention MCP MCP Model Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers to enable/disable them has been removed — use /mcp enable <name> instead.
Claude Code v2.1.4 adds env var to fully disable background tasks and the Ctrl+B shortcut.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.4 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.4
└──▷ TRY IT
Prevent Claude Code from ever backgrounding tasks — useful in CI pipelines or restricted environments where background processes are undesirable.
copy
$ CLAUDE_CODE_DISABLE_BACKGROUND_TASKS=1 claude
Claude Code v2.1.3 adds release channel switching, unreachable-rule warnings, and a 10-minute hook timeout.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.3 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.3
└──▷ TRY IT
Switch between stable and latest release channels without leaving the CLI.
Audit your permission rules for unreachable entries and get fix guidance before they silently do nothing.
Adds release channel toggle (stable or latest) to /config, letting you switch update tracks in-product. Not checked yet New detection and warnings for unreachable permission rules surfaced in /doctor and after saving rules, with source attribution and actionable fix guidance. Not checked yet Extends tool hook execution timeout from 60 seconds to 10 minutes, enabling longer-running hook scripts. Not checked yet [VSCode] Adds clickable destination selector for permission requests, letting you choose where settings are saved: this project, all projects, shared with team, or session only. Not checked yet Merges slash commands and skills into a unified concept, simplifying the mental model. Not checked yet
5 details in Everything
Claude Code v2.1.2 adds OSC 8 hyperlinks, winget support, plan-mode shortcut, and full large-output persistence to disk.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.1.2 https://github.com/anthropics/claude-code.git
$ git checkout v2.1.2
└──▷ TRY IT
Force plugin autoupdates in CI or locked-down environments where the main auto-updater is disabled.
copy
$ FORCE_AUTOUPDATE_PLUGINS=1 claude
Adds clickable OSC 8 hyperlinks for file paths in tool output in supported terminals (e.g., iTerm). Not checked yet Adds Windows Package Manager (winget) installation detection with automatic update instructions. Not checked yet Adds Shift+Tab keyboard shortcut in plan mode to instantly select the auto-accept edits option. Not checked yet Adds FORCE_AUTOUPDATE_PLUGINS environment variable to enable plugin autoupdate even when the main auto-updater is disabled. Not checked yet Adds agent_type field to SessionStart hook input when --agent is specified. Not checked yet
+3 more
show less
Adds source path metadata to images dragged onto the terminal so Claude knows where images originated. Not checked yet Large bash command outputs and tool outputs are now saved to disk instead of truncated, giving Claude access to full content via file references. Not checked yet Unifies plugins and MCPs in the /plugins installed tab with scope-based grouping. Not checked yet
8 details in Everything
└──▷ BREAKING ON UPGRADE
! The Windows managed settings path C:\ProgramData\ClaudeCode\managed-settings.json is deprecated; administrators must migrate to C:\Program Files\ClaudeCode\managed-settings.json.! The minimum zod peer dependency is now ^4.0.0 (SDK).
Claude Code v2.0.74 adds LSP LSP Language Server Protocol, the standard way editors get code intelligence such as completions, go-to-definition and errors from a separate per-language server. Coding agents use it to understand code. code-intelligence tools, expands terminal setup support, and improves theme controls.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.0.74 https://github.com/anthropics/claude-code.git
$ git checkout v2.0.74
└──▷ TRY IT
Configure optimal key bindings and shell integration for Kitty, Alacritty, Zed, or Warp in one step.
Quickly toggle syntax highlighting off for a distraction-free diff review while browsing themes.
copy
$ /theme # then press ctrl+t to toggle syntax highlighting on/off
Adds LSP (Language Server Protocol Language Server Protocol Language Server Protocol, the standard way editors get code intelligence such as completions, go-to-definition and errors from a separate per-language server. Coding agents use it to understand code. ) tool enabling code-intelligence features: go-to-definition, find references, and hover documentation. Not checked yet Adds /terminal-setup support for Kitty, Alacritty, Zed, and Warp terminals. Not checked yet Adds ctrl+t shortcut in /theme to toggle syntax highlighting on/off. Not checked yet Adds syntax highlighting info display inside the theme picker. Not checked yet Improves /context command visualization with skills and agents grouped by source, slash commands listed, and token counts sorted. Not checked yet
5 details in Everything
Claude Code v2.0.73 adds clickable image links, kill-ring cycling, plugin search, custom fork session IDs, and VS Code tab badges.
└──▷ GET THIS VERSION
copy
$ git clone --branch v2.0.73 https://github.com/anthropics/claude-code.git
$ git checkout v2.0.73
└──▷ TRY IT
Fork an existing session and assign a meaningful custom ID so you can reference it later by name rather than an auto-generated hash.
copy
$ claude --resume <existing-session-id> --fork-session --session-id my-audit-branch
Adds clickable [Image #N] links in the terminal that open attached images in the default viewer. Not checked yet Adds alt-y yank-pop to cycle through kill-ring history after a ctrl-y yank. Not checked yet Adds search filtering to the plugin discover screen — filter by name, description, or marketplace in real time. Not checked yet Supports custom session IDs when forking sessions via --session-id combined with --resume or --continue and --fork-session. Not checked yet Improves /theme command to open the theme picker directly. Not checked yet
+1 more
show less
[VS Code] Adds tab icon badges showing pending permissions (blue) and unread completions (orange). Not checked yet
6 details in Everything