Documentation 2026-03-12 21:07 UTC to 2026-03-13 21:07 UTC

85## See also85## See also

86 86 

87* [Interactive mode](/en/interactive-mode) - Keyboard shortcuts and session controls87* [Interactive mode](/en/interactive-mode) - Keyboard shortcuts and session controls

88* [Built-in commands](/en/interactive-mode#built-in-commands) - Accessing checkpoints using `/rewind`88* [Built-in commands](/en/commands) - Accessing checkpoints using `/rewind`

89* [CLI reference](/en/cli-reference) - Command-line options89* [CLI reference](/en/cli-reference) - Command-line options

11You can start sessions, pipe content, resume conversations, and manage updates with these commands:11You can start sessions, pipe content, resume conversations, and manage updates with these commands:

12 12 

13| Command | Description | Example |13| Command | Description | Example |

14| :------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------- |14| :------------------------------ | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------- |

15| `claude` | Start interactive session | `claude` |15| `claude` | Start interactive session | `claude` |

16| `claude "query"` | Start interactive session with initial prompt | `claude "explain this project"` |16| `claude "query"` | Start interactive session with initial prompt | `claude "explain this project"` |

17| `claude -p "query"` | Query via SDK, then exit | `claude -p "explain this function"` |17| `claude -p "query"` | Query via SDK, then exit | `claude -p "explain this function"` |

25| `claude auth status` | Show authentication status as JSON. Use `--text` for human-readable output. Exits with code 0 if logged in, 1 if not | `claude auth status` |25| `claude auth status` | Show authentication status as JSON. Use `--text` for human-readable output. Exits with code 0 if logged in, 1 if not | `claude auth status` |

26| `claude agents` | List all configured [subagents](/en/sub-agents), grouped by source | `claude agents` |26| `claude agents` | List all configured [subagents](/en/sub-agents), grouped by source | `claude agents` |

27| `claude mcp` | Configure Model Context Protocol (MCP) servers | See the [Claude Code MCP documentation](/en/mcp). |27| `claude mcp` | Configure Model Context Protocol (MCP) servers | See the [Claude Code MCP documentation](/en/mcp). |

28| `claude remote-control` | Start a [Remote Control session](/en/remote-control) to control Claude Code from Claude.ai or the Claude app while running locally. See [Remote Control](/en/remote-control) for flags | `claude remote-control` |28| `claude remote-control` | Start a [Remote Control](/en/remote-control) server to control Claude Code from Claude.ai or the Claude app. Runs in server mode (no local interactive session). See [Server mode flags](/en/remote-control#server-mode) | `claude remote-control --name "My Project"` |

29 29 

30## CLI flags30## CLI flags

31 31 

35| :------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------- |35| :------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------- |

36| `--add-dir` | Add additional working directories for Claude to access (validates each path exists as a directory) | `claude --add-dir ../apps ../lib` |36| `--add-dir` | Add additional working directories for Claude to access (validates each path exists as a directory) | `claude --add-dir ../apps ../lib` |

37| `--agent` | Specify an agent for the current session (overrides the `agent` setting) | `claude --agent my-custom-agent` |37| `--agent` | Specify an agent for the current session (overrides the `agent` setting) | `claude --agent my-custom-agent` |

38| `--agents` | Define custom [subagents](/en/sub-agents) dynamically via JSON (see below for format) | `claude --agents '{"reviewer":{"description":"Reviews code","prompt":"You are a code reviewer"}}'` |38| `--agents` | Define custom subagents dynamically via JSON. Uses the same field names as subagent [frontmatter](/en/sub-agents#supported-frontmatter-fields), plus a `prompt` field for the agent's instructions | `claude --agents '{"reviewer":{"description":"Reviews code","prompt":"You are a code reviewer"}}'` |

39| `--allow-dangerously-skip-permissions` | Enable permission bypassing as an option without immediately activating it. Allows composing with `--permission-mode` (use with caution) | `claude --permission-mode plan --allow-dangerously-skip-permissions` |39| `--allow-dangerously-skip-permissions` | Enable permission bypassing as an option without immediately activating it. Allows composing with `--permission-mode` (use with caution) | `claude --permission-mode plan --allow-dangerously-skip-permissions` |

40| `--allowedTools` | Tools that execute without prompting for permission. See [permission rule syntax](/en/settings#permission-rule-syntax) for pattern matching. To restrict which tools are available, use `--tools` instead | `"Bash(git log *)" "Bash(git diff *)" "Read"` |40| `--allowedTools` | Tools that execute without prompting for permission. See [permission rule syntax](/en/settings#permission-rule-syntax) for pattern matching. To restrict which tools are available, use `--tools` instead | `"Bash(git log *)" "Bash(git diff *)" "Read"` |

41| `--append-system-prompt` | Append custom text to the end of the default system prompt | `claude --append-system-prompt "Always use TypeScript"` |41| `--append-system-prompt` | Append custom text to the end of the default system prompt | `claude --append-system-prompt "Always use TypeScript"` |

69| `--plugin-dir` | Load plugins from directories for this session only (repeatable) | `claude --plugin-dir ./my-plugins` |69| `--plugin-dir` | Load plugins from directories for this session only (repeatable) | `claude --plugin-dir ./my-plugins` |

70| `--print`, `-p` | Print response without interactive mode (see [Agent SDK documentation](https://platform.claude.com/docs/en/agent-sdk/overview) for programmatic usage details) | `claude -p "query"` |70| `--print`, `-p` | Print response without interactive mode (see [Agent SDK documentation](https://platform.claude.com/docs/en/agent-sdk/overview) for programmatic usage details) | `claude -p "query"` |

71| `--remote` | Create a new [web session](/en/claude-code-on-the-web) on claude.ai with the provided task description | `claude --remote "Fix the login bug"` |71| `--remote` | Create a new [web session](/en/claude-code-on-the-web) on claude.ai with the provided task description | `claude --remote "Fix the login bug"` |

72| `--remote-control`, `--rc` | Start an interactive session with [Remote Control](/en/remote-control#interactive-session) enabled so you can also control it from claude.ai or the Claude app. Optionally pass a name for the session | `claude --remote-control "My Project"` |

72| `--resume`, `-r` | Resume a specific session by ID or name, or show an interactive picker to choose a session | `claude --resume auth-refactor` |73| `--resume`, `-r` | Resume a specific session by ID or name, or show an interactive picker to choose a session | `claude --resume auth-refactor` |

73| `--session-id` | Use a specific session ID for the conversation (must be a valid UUID) | `claude --session-id "550e8400-e29b-41d4-a716-446655440000"` |74| `--session-id` | Use a specific session ID for the conversation (must be a valid UUID) | `claude --session-id "550e8400-e29b-41d4-a716-446655440000"` |

74| `--setting-sources` | Comma-separated list of setting sources to load (`user`, `project`, `local`) | `claude --setting-sources user,project` |75| `--setting-sources` | Comma-separated list of setting sources to load (`user`, `project`, `local`) | `claude --setting-sources user,project` |

83| `--version`, `-v` | Output the version number | `claude -v` |84| `--version`, `-v` | Output the version number | `claude -v` |

84| `--worktree`, `-w` | Start Claude in an isolated [git worktree](/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees) at `<repo>/.claude/worktrees/<name>`. If no name is given, one is auto-generated | `claude -w feature-auth` |85| `--worktree`, `-w` | Start Claude in an isolated [git worktree](/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees) at `<repo>/.claude/worktrees/<name>`. If no name is given, one is auto-generated | `claude -w feature-auth` |

85 86 

86<Tip>

87 The `--output-format json` flag is particularly useful for scripting and

88 automation, allowing you to parse Claude's responses programmatically.

89</Tip>

90 

91### Agents flag format

92 

93The `--agents` flag accepts a JSON object that defines one or more custom subagents. Each subagent requires a unique name (as the key) and a definition object with the following fields:

94 

95| Field | Required | Description |

96| :---------------- | :------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

97| `description` | Yes | Natural language description of when the subagent should be invoked |

98| `prompt` | Yes | The system prompt that guides the subagent's behavior |

99| `tools` | No | Array of specific tools the subagent can use, for example `["Read", "Edit", "Bash"]`. If omitted, inherits all tools. Supports [`Agent(agent_type)`](/en/sub-agents#restrict-which-subagents-can-be-spawned) syntax |

100| `disallowedTools` | No | Array of tool names to explicitly deny for this subagent |

101| `model` | No | Model to use: a short alias (`sonnet`, `opus`, `haiku`), a full model ID (for example, `claude-opus-4-6`), or `inherit`. If omitted, defaults to `inherit` |

102| `skills` | No | Array of [skill](/en/skills) names to preload into the subagent's context |

103| `mcpServers` | No | Array of [MCP servers](/en/mcp) for this subagent. Each entry is a server name string or a `{name: config}` object |

104| `maxTurns` | No | Maximum number of agentic turns before the subagent stops |

105 

106Example:

107 

108```bash theme={null}

109claude --agents '{

110 "code-reviewer": {

111 "description": "Expert code reviewer. Use proactively after code changes.",

112 "prompt": "You are a senior code reviewer. Focus on code quality, security, and best practices.",

113 "tools": ["Read", "Grep", "Glob", "Bash"],

114 "model": "sonnet"

115 },

116 "debugger": {

117 "description": "Debugging specialist for errors and test failures.",

118 "prompt": "You are an expert debugger. Analyze errors, identify root causes, and provide fixes."

119 }

120}'

121```

122 

123For more details on creating and using subagents, see the [subagents documentation](/en/sub-agents).

124 

125### System prompt flags87### System prompt flags

126 88 

127Claude Code provides four flags for customizing the system prompt. All four work in both interactive and non-interactive modes.89Claude Code provides four flags for customizing the system prompt. All four work in both interactive and non-interactive modes.

128 90 

129| Flag | Behavior | Use case |91| Flag | Behavior | Example |

130| :---------------------------- | :------------------------------------------ | :------------------------------------------------------------------- |92| :---------------------------- | :------------------------------------------ | :------------------------------------------------------ |

131| `--system-prompt` | **Replaces** entire default prompt | Complete control over Claude's behavior and instructions |93| `--system-prompt` | Replaces the entire default prompt | `claude --system-prompt "You are a Python expert"` |

132| `--system-prompt-file` | **Replaces** with file contents | Load prompts from files for reproducibility and version control |94| `--system-prompt-file` | Replaces with file contents | `claude --system-prompt-file ./prompts/review.txt` |

133| `--append-system-prompt` | **Appends** to default prompt | Add specific instructions while keeping default Claude Code behavior |95| `--append-system-prompt` | Appends to the default prompt | `claude --append-system-prompt "Always use TypeScript"` |

134| `--append-system-prompt-file` | **Appends** file contents to default prompt | Load additional instructions from files while keeping defaults |96| `--append-system-prompt-file` | Appends file contents to the default prompt | `claude --append-system-prompt-file ./style-rules.txt` |

135 

136**When to use each:**

137 

138* **`--system-prompt`**: use when you need complete control over Claude's system prompt. This removes all default Claude Code instructions, giving you a blank slate.

139 ```bash theme={null}

140 claude --system-prompt "You are a Python expert who only writes type-annotated code"

141 ```

142 

143* **`--system-prompt-file`**: use when you want to load a custom prompt from a file, useful for team consistency or version-controlled prompt templates.

144 ```bash theme={null}

145 claude --system-prompt-file ./prompts/code-review.txt

146 ```

147 

148* **`--append-system-prompt`**: use when you want to add specific instructions while keeping Claude Code's default capabilities intact. This is the safest option for most use cases.

149 ```bash theme={null}

150 claude --append-system-prompt "Always use TypeScript and include JSDoc comments"

151 ```

152 

153* **`--append-system-prompt-file`**: use when you want to append instructions from a file while keeping Claude Code's defaults. Useful for version-controlled additions.

154 ```bash theme={null}

155 claude --append-system-prompt-file ./prompts/style-rules.txt

156 ```

157 97 

158`--system-prompt` and `--system-prompt-file` are mutually exclusive. The append flags can be used together with either replacement flag.98`--system-prompt` and `--system-prompt-file` are mutually exclusive. The append flags can be combined with either replacement flag.

159 99 

160For most use cases, `--append-system-prompt` or `--append-system-prompt-file` is recommended as they preserve Claude Code's built-in capabilities while adding your custom requirements. Use `--system-prompt` or `--system-prompt-file` only when you need complete control over the system prompt.100For most use cases, use an append flag. Appending preserves Claude Code's built-in capabilities while adding your requirements. Use a replacement flag only when you need complete control over the system prompt.

161 101 

162## See also102## See also

163 103 

25 25 

26## How reviews work26## How reviews work

27 27 

28Once an admin [enables Code Review](#set-up-code-review) for your organization, reviews run automatically when a pull request opens or updates. Multiple agents analyze the diff and surrounding code in parallel on Anthropic infrastructure. Each agent looks for a different class of issue, then a verification step checks candidates against actual code behavior to filter out false positives. The results are deduplicated, ranked by severity, and posted as inline comments on the specific lines where issues were found. If no issues are found, Claude posts a short confirmation comment on the PR.28Once an admin [enables Code Review](#set-up-code-review) for your organization, reviews trigger when a PR opens, on every push, or when manually requested, depending on the repository's configured behavior. Commenting `@claude review` [starts reviews on a PR](#manually-trigger-reviews) in any mode.

29 

30When a review runs, multiple agents analyze the diff and surrounding code in parallel on Anthropic infrastructure. Each agent looks for a different class of issue, then a verification step checks candidates against actual code behavior to filter out false positives. The results are deduplicated, ranked by severity, and posted as inline comments on the specific lines where issues were found. If no issues are found, Claude posts a short confirmation comment on the PR.

29 31 

30Reviews scale in cost with PR size and complexity, completing in 20 minutes on average. Admins can monitor review activity and spend via the [analytics dashboard](#view-usage).32Reviews scale in cost with PR size and complexity, completing in 20 minutes on average. Admins can monitor review activity and spend via the [analytics dashboard](#view-usage).

31 33 

73 </Step>75 </Step>

74 76 

75 <Step title="Set review triggers per repo">77 <Step title="Set review triggers per repo">

76 After setup completes, the Code Review section shows your repositories in a table. For each repository, use the dropdown to choose when reviews run:78 After setup completes, the Code Review section shows your repositories in a table. For each repository, use the **Review Behavior** dropdown to choose when reviews run:

77 79 

78 * **After PR creation only**: review runs once when a PR is opened or marked ready for review80 * **Once after PR creation**: review runs once when a PR is opened or marked ready for review

79 * **After every push to PR branch**: review runs on every push, catching new issues as the PR evolves and auto-resolving threads when you fix flagged issues81 * **After every push**: review runs on every push to the PR branch, catching new issues as the PR evolves and auto-resolving threads when you fix flagged issues

82 * **Manual**: reviews start only when someone [comments `@claude review` on a PR](#manually-trigger-reviews); subsequent pushes to that PR are then reviewed automatically

80 83 

81 Reviewing on every push runs more reviews and costs more. Start with PR creation only and switch to on-push for repos where you want continuous coverage and automatic thread cleanup.84 Reviewing on every push runs the most reviews and costs the most. Manual mode is useful for high-traffic repos where you want to opt specific PRs into review, or to only start reviewing your PRs once they're ready.

82 </Step>85 </Step>

83</Steps>86</Steps>

84 87 

85The repositories table also shows the average cost per review for each repo based on recent activity. Use the row actions menu to turn Code Review on or off per repository, or to remove a repository entirely.88The repositories table also shows the average cost per review for each repo based on recent activity. Use the row actions menu to turn Code Review on or off per repository, or to remove a repository entirely.

86 89 

87To verify setup, open a test PR. A check run named **Claude Code Review** appears within a few minutes. If it doesn't, confirm the repository is listed in your admin settings and the Claude GitHub App has access to it.90To verify setup, open a test PR. If you chose an automatic trigger, a check run named **Claude Code Review** appears within a few minutes. If you chose Manual, comment `@claude review` on the PR to start the first review. If no check run appears, confirm the repository is listed in your admin settings and the Claude GitHub App has access to it.

91 

92## Manually trigger reviews

93 

94Comment `@claude review` on a pull request to start a review and opt that PR into push-triggered reviews going forward. This works regardless of the repository's configured trigger: use it to opt specific PRs into review in Manual mode, or to get an immediate re-review in other modes. Either way, pushes to that PR trigger reviews from then on.

95 

96For the comment to trigger a review:

97 

98* Post it as a top-level PR comment, not an inline comment on a diff line

99* Put `@claude review` at the start of the comment

100* You must have owner, member, or collaborator access to the repository

101* The PR must be open and not a draft

102 

103If a review is already running on that PR, the request is queued until the in-progress review completes. You can monitor progress via the check run on the PR.

88 104 

89## Customize reviews105## Customize reviews

90 106 

150 166 

151The review trigger you choose affects total cost:167The review trigger you choose affects total cost:

152 168 

153* **After PR creation only**: runs once per PR169* **Once after PR creation**: runs once per PR

154* **After every push**: runs on each commit, multiplying cost by the number of pushes170* **After every push**: runs on each push, multiplying cost by the number of pushes

171* **Manual**: no reviews until someone comments `@claude review` on a PR

172 

173In any mode, commenting `@claude review` [opts the PR into push-triggered reviews](#manually-trigger-reviews), so additional cost accrues per push after that comment.

155 174 

156Costs appear on your Anthropic bill regardless of whether your organization uses AWS Bedrock or Google Vertex AI for other Claude Code features. To set a monthly spend cap for Code Review, go to [claude.ai/admin-settings/usage](https://claude.ai/admin-settings/usage) and configure the limit for the Claude Code Review service.175Costs appear on your Anthropic bill regardless of whether your organization uses AWS Bedrock or Google Vertex AI for other Claude Code features. To set a monthly spend cap for Code Review, go to [claude.ai/admin-settings/usage](https://claude.ai/admin-settings/usage) and configure the limit for the Claude Code Review service.

157 176 

1> ## Documentation Index

2> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt

3> Use this file to discover all available pages before exploring further.

4 

5# Built-in commands

6 

7> Complete reference for built-in commands available in Claude Code.

8 

9Type `/` in Claude Code to see all available commands, or type `/` followed by any letters to filter. Not all commands are visible to every user. Some depend on your platform, plan, or environment. For example, `/desktop` only appears on macOS and Windows, `/upgrade` and `/privacy-settings` are only available on Pro and Max plans, and `/terminal-setup` is hidden when your terminal natively supports its keybindings.

10 

11Claude Code also includes [bundled skills](/en/skills#bundled-skills) like `/simplify`, `/batch`, and `/debug` that appear alongside built-in commands when you type `/`. To create your own commands, see [skills](/en/skills).

12 

13In the table below, `<arg>` indicates a required argument and `[arg]` indicates an optional one.

14 

15| Command | Purpose |

16| :------------------------ | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

17| `/add-dir <path>` | Add a new working directory to the current session |

18| `/agents` | Manage [agent](/en/sub-agents) configurations |

19| `/btw <question>` | Ask a quick [side question](/en/interactive-mode#side-questions-with-btw) without adding to the conversation |

20| `/chrome` | Configure [Claude in Chrome](/en/chrome) settings |

21| `/clear` | Clear conversation history and free up context. Aliases: `/reset`, `/new` |

22| `/color [color\|default]` | Set the prompt bar color for the current session. Available colors: `red`, `blue`, `green`, `yellow`, `purple`, `orange`, `pink`, `cyan`. Use `default` to reset |

23| `/compact [instructions]` | Compact conversation with optional focus instructions |

24| `/config` | Open the [Settings](/en/settings) interface to adjust theme, model, [output style](/en/output-styles), and other preferences. Alias: `/settings` |

25| `/context` | Visualize current context usage as a colored grid. Shows optimization suggestions for context-heavy tools, memory bloat, and capacity warnings |

26| `/copy` | Copy the last assistant response to clipboard. When code blocks are present, shows an interactive picker to select individual blocks or the full response |

27| `/cost` | Show token usage statistics. See [cost tracking guide](/en/costs#using-the-cost-command) for subscription-specific details |

28| `/desktop` | Continue the current session in the Claude Code Desktop app. macOS and Windows only. Alias: `/app` |

29| `/diff` | Open an interactive diff viewer showing uncommitted changes and per-turn diffs. Use left/right arrows to switch between the current git diff and individual Claude turns, and up/down to browse files |

30| `/doctor` | Diagnose and verify your Claude Code installation and settings |

31| `/exit` | Exit the CLI. Alias: `/quit` |

32| `/export [filename]` | Export the current conversation as plain text. With a filename, writes directly to that file. Without, opens a dialog to copy to clipboard or save to a file |

33| `/extra-usage` | Configure extra usage to keep working when rate limits are hit |

34| `/fast [on\|off]` | Toggle [fast mode](/en/fast-mode) on or off |

35| `/feedback [report]` | Submit feedback about Claude Code. Alias: `/bug` |

36| `/fork [name]` | Create a fork of the current conversation at this point |

37| `/help` | Show help and available commands |

38| `/hooks` | Manage [hook](/en/hooks) configurations for tool events |

39| `/ide` | Manage IDE integrations and show status |

40| `/init` | Initialize project with `CLAUDE.md` guide |

41| `/insights` | Generate a report analyzing your Claude Code sessions, including project areas, interaction patterns, and friction points |

42| `/install-github-app` | Set up the [Claude GitHub Actions](/en/github-actions) app for a repository. Walks you through selecting a repo and configuring the integration |

43| `/install-slack-app` | Install the Claude Slack app. Opens a browser to complete the OAuth flow |

44| `/keybindings` | Open or create your keybindings configuration file |

45| `/login` | Sign in to your Anthropic account |

46| `/logout` | Sign out from your Anthropic account |

47| `/mcp` | Manage MCP server connections and OAuth authentication |

48| `/memory` | Edit `CLAUDE.md` memory files, enable or disable [auto-memory](/en/memory#auto-memory), and view auto-memory entries |

49| `/mobile` | Show QR code to download the Claude mobile app. Aliases: `/ios`, `/android` |

50| `/model [model]` | Select or change the AI model. For models that support it, use left/right arrows to [adjust effort level](/en/model-config#adjust-effort-level). The change takes effect immediately without waiting for the current response to finish |

51| `/passes` | Share a free week of Claude Code with friends. Only visible if your account is eligible |

52| `/permissions` | View or update [permissions](/en/permissions#manage-permissions). Alias: `/allowed-tools` |

53| `/plan` | Enter plan mode directly from the prompt |

54| `/plugin` | Manage Claude Code [plugins](/en/plugins) |

55| `/pr-comments [PR]` | Fetch and display comments from a GitHub pull request. Automatically detects the PR for the current branch, or pass a PR URL or number. Requires the `gh` CLI |

56| `/privacy-settings` | View and update your privacy settings. Only available for Pro and Max plan subscribers |

57| `/release-notes` | View the full changelog, with the most recent version closest to your prompt |

58| `/reload-plugins` | Reload all active [plugins](/en/plugins) to apply pending changes without restarting. Reports what was loaded and notes any changes that require a restart |

59| `/remote-control` | Make this session available for [remote control](/en/remote-control) from claude.ai. Alias: `/rc` |

60| `/remote-env` | Configure the default remote environment for [web sessions started with `--remote`](/en/claude-code-on-the-web#environment-configuration) |

61| `/rename [name]` | Rename the current session. Without a name, auto-generates one from conversation history |

62| `/resume [session]` | Resume a conversation by ID or name, or open the session picker. Alias: `/continue` |

63| `/review` | Deprecated. Install the [`code-review` plugin](https://github.com/anthropics/claude-code-marketplace/blob/main/code-review/README.md) instead: `claude plugin install code-review@claude-code-marketplace` |

64| `/rewind` | Rewind the conversation and/or code to a previous point, or summarize from a selected message. See [checkpointing](/en/checkpointing). Alias: `/checkpoint` |

65| `/sandbox` | Toggle [sandbox mode](/en/sandboxing). Available on supported platforms only |

66| `/security-review` | Analyze pending changes on the current branch for security vulnerabilities. Reviews the git diff and identifies risks like injection, auth issues, and data exposure |

67| `/skills` | List available [skills](/en/skills) |

68| `/stats` | Visualize daily usage, session history, streaks, and model preferences |

69| `/status` | Open the Settings interface (Status tab) showing version, model, account, and connectivity |

70| `/statusline` | Configure Claude Code's [status line](/en/statusline). Describe what you want, or run without arguments to auto-configure from your shell prompt |

71| `/stickers` | Order Claude Code stickers |

72| `/tasks` | List and manage background tasks |

73| `/terminal-setup` | Configure terminal keybindings for Shift+Enter and other shortcuts. Only visible in terminals that need it, like VS Code, Alacritty, or Warp |

74| `/theme` | Change the color theme. Includes light and dark variants, colorblind-accessible (daltonized) themes, and ANSI themes that use your terminal's color palette |

75| `/upgrade` | Open the upgrade page to switch to a higher plan tier |

76| `/usage` | Show plan usage limits and rate limit status |

77| `/vim` | Toggle between Vim and Normal editing modes |

78 

79## MCP prompts

80 

81MCP servers can expose prompts that appear as commands. These use the format `/mcp__<server>__<prompt>` and are dynamically discovered from connected servers. See [MCP prompts](/en/mcp#use-mcp-prompts-as-commands) for details.

82 

83## See also

84 

85* [Skills](/en/skills): create your own commands

86* [Interactive mode](/en/interactive-mode): keyboard shortcuts, Vim mode, and command history

87* [CLI reference](/en/cli-reference): launch-time flags

226 226 

227## Use Plan Mode for safe code analysis227## Use Plan Mode for safe code analysis

228 228 

229Plan Mode instructs Claude to create a plan by analyzing the codebase with read-only operations, perfect for exploring codebases, planning complex changes, or reviewing code safely. In Plan Mode, Claude uses [`AskUserQuestion`](/en/settings#tools-available-to-claude) to gather requirements and clarify your goals before proposing a plan.229Plan Mode instructs Claude to create a plan by analyzing the codebase with read-only operations, perfect for exploring codebases, planning complex changes, or reviewing code safely. In Plan Mode, Claude uses [`AskUserQuestion`](/en/tools-reference) to gather requirements and clarify your goals before proposing a plan.

230 230 

231### When to use Plan Mode231### When to use Plan Mode

232 232 

519Thinking is enabled by default, but you can adjust or disable it.519Thinking is enabled by default, but you can adjust or disable it.

520 520 

521| Scope | How to configure | Details |521| Scope | How to configure | Details |

522| ------------------------ | ------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |522| ------------------------ | -------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |

523| **Effort level** | Adjust in `/model` or set [`CLAUDE_CODE_EFFORT_LEVEL`](/en/settings#environment-variables) | Control thinking depth for Opus 4.6 and Sonnet 4.6: low, medium, high. See [Adjust effort level](/en/model-config#adjust-effort-level) |523| **Effort level** | Adjust in `/model` or set [`CLAUDE_CODE_EFFORT_LEVEL`](/en/env-vars) | Control thinking depth for Opus 4.6 and Sonnet 4.6: low, medium, high. See [Adjust effort level](/en/model-config#adjust-effort-level) |

524| **`ultrathink` keyword** | Include "ultrathink" anywhere in your prompt | Sets effort to high for that turn on Opus 4.6 and Sonnet 4.6. Useful for one-off tasks requiring deep reasoning without permanently changing your effort setting |524| **`ultrathink` keyword** | Include "ultrathink" anywhere in your prompt | Sets effort to high for that turn on Opus 4.6 and Sonnet 4.6. Useful for one-off tasks requiring deep reasoning without permanently changing your effort setting |

525| **Toggle shortcut** | Press `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle thinking on/off for the current session (all models). May require [terminal configuration](/en/terminal-config) to enable Option key shortcuts |525| **Toggle shortcut** | Press `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle thinking on/off for the current session (all models). May require [terminal configuration](/en/terminal-config) to enable Option key shortcuts |

526| **Global default** | Use `/config` to toggle thinking mode | Sets your default across all projects (all models).<br />Saved as `alwaysThinkingEnabled` in `~/.claude/settings.json` |526| **Global default** | Use `/config` to toggle thinking mode | Sets your default across all projects (all models).<br />Saved as `alwaysThinkingEnabled` in `~/.claude/settings.json` |

527| **Limit token budget** | Set [`MAX_THINKING_TOKENS`](/en/settings#environment-variables) environment variable | Limit the thinking budget to a specific number of tokens (ignored on Opus 4.6 unless set to 0). Example: `export MAX_THINKING_TOKENS=10000` |527| **Limit token budget** | Set [`MAX_THINKING_TOKENS`](/en/env-vars) environment variable | Limit the thinking budget to a specific number of tokens (ignored on Opus 4.6 unless set to 0). Example: `export MAX_THINKING_TOKENS=10000` |

528 528 

529To view Claude's thinking process, press `Ctrl+O` to toggle verbose mode and see the internal reasoning displayed as gray italic text.529To view Claude's thinking process, press `Ctrl+O` to toggle verbose mode and see the internal reasoning displayed as gray italic text.

530 530 

534 534 

535**With Opus 4.6**, thinking uses adaptive reasoning: the model dynamically allocates thinking tokens based on the [effort level](/en/model-config#adjust-effort-level) you select (low, medium, high). This is the recommended way to tune the tradeoff between speed and reasoning depth.535**With Opus 4.6**, thinking uses adaptive reasoning: the model dynamically allocates thinking tokens based on the [effort level](/en/model-config#adjust-effort-level) you select (low, medium, high). This is the recommended way to tune the tradeoff between speed and reasoning depth.

536 536 

537**With other models**, thinking uses a fixed budget of up to 31,999 tokens from your output budget. You can limit this with the [`MAX_THINKING_TOKENS`](/en/settings#environment-variables) environment variable, or disable thinking entirely via `/config` or the `Option+T`/`Alt+T` toggle.537**With other models**, thinking uses a fixed budget of up to 31,999 tokens from your output budget. You can limit this with the [`MAX_THINKING_TOKENS`](/en/env-vars) environment variable, or disable thinking entirely via `/config` or the `Option+T`/`Alt+T` toggle.

538 538 

539`MAX_THINKING_TOKENS` is ignored on Opus 4.6 and Sonnet 4.6, since adaptive reasoning controls thinking depth instead. The one exception: setting `MAX_THINKING_TOKENS=0` still disables thinking entirely on any model. To disable adaptive thinking and revert to the fixed thinking budget, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1`. See [environment variables](/en/settings#environment-variables).539`MAX_THINKING_TOKENS` is ignored on Opus 4.6 and Sonnet 4.6, since adaptive reasoning controls thinking depth instead. The one exception: setting `MAX_THINKING_TOKENS=0` still disables thinking entirely on any model. To disable adaptive thinking and revert to the fixed thinking budget, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1`. See [environment variables](/en/env-vars).

540 540 

541<Warning>541<Warning>

542 You're charged for all thinking tokens used, even though Claude 4 models show summarized thinking542 You're charged for all thinking tokens used, even though Claude 4 models show summarized thinking

168 168 

169### Use skills169### Use skills

170 170 

171[Skills](/en/skills) extend what Claude can do. Claude loads them automatically when relevant, or you can invoke one directly: type `/` in the prompt box or click the **+** button and select **Slash commands** to browse what's available. This includes [built-in commands](/en/interactive-mode#built-in-commands), your [custom skills](/en/skills#create-custom-skills), project skills from your codebase, and skills from any [installed plugins](/en/plugins). Select one and it appears highlighted in the input field. Type your task after it and send as usual.171[Skills](/en/skills) extend what Claude can do. Claude loads them automatically when relevant, or you can invoke one directly: type `/` in the prompt box or click the **+** button and select **Slash commands** to browse what's available. This includes [built-in commands](/en/commands), your [custom skills](/en/skills#create-custom-skills), project skills from your codebase, and skills from any [installed plugins](/en/plugins). Select one and it appears highlighted in the input field. Type your task after it and send as usual.

172 172 

173### Install plugins173### Install plugins

174 174 

383 383 

384You can also manage tasks by asking Claude in any Desktop session. For example, "pause my dependency-audit task", "delete the standup-prep task", or "show me my scheduled tasks."384You can also manage tasks by asking Claude in any Desktop session. For example, "pause my dependency-audit task", "delete the standup-prep task", or "show me my scheduled tasks."

385 385 

386To edit a task's prompt on disk, open `~/.claude/scheduled-tasks/<task-name>/SKILL.md` (or under [`CLAUDE_CONFIG_DIR`](/en/settings#environment-variables) if set). The file uses YAML frontmatter for `name` and `description`, with the prompt as the body. Changes take effect on the next run. Schedule, folder, model, and enabled state are not in this file: change them through the Edit form or ask Claude.386To edit a task's prompt on disk, open `~/.claude/scheduled-tasks/<task-name>/SKILL.md` (or under [`CLAUDE_CONFIG_DIR`](/en/env-vars) if set). The file uses YAML frontmatter for `name` and `description`, with the prompt as the body. Changes take effect on the next run. Schedule, folder, model, and enabled state are not in this file: change them through the Edit form or ask Claude.

387 387 

388## Environment configuration388## Environment configuration

389 389 

395 395 

396### Local sessions396### Local sessions

397 397 

398Local sessions inherit environment variables from your shell. If you need additional variables, set them in your shell profile, such as `~/.zshrc` or `~/.bashrc`, and restart the desktop app. See [environment variables](/en/settings#environment-variables) for the full list of supported variables.398Local sessions inherit environment variables from your shell. If you need additional variables, set them in your shell profile, such as `~/.zshrc` or `~/.bashrc`, and restart the desktop app. See [environment variables](/en/env-vars) for the full list of supported variables.

399 399 

400[Extended thinking](/en/common-workflows#use-extended-thinking-thinking-mode) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. To disable thinking entirely, set `MAX_THINKING_TOKENS=0` in your shell profile. On Opus, `MAX_THINKING_TOKENS` is ignored except for `0` because adaptive reasoning controls thinking depth instead.400[Extended thinking](/en/common-workflows#use-extended-thinking-thinking-mode) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. To disable thinking entirely, set `MAX_THINKING_TOKENS=0` in your shell profile. On Opus, `MAX_THINKING_TOKENS` is ignored except for `0` because adaptive reasoning controls thinking depth instead.

401 401 

111 111 

112**Give Claude more context.** Type `@filename` in the prompt box to pull a specific file into the conversation, attach images and PDFs using the attachment button, or drag and drop files directly into the prompt. The more context Claude has, the better the results. See [Add files and context](/en/desktop#add-files-and-context-to-prompts).112**Give Claude more context.** Type `@filename` in the prompt box to pull a specific file into the conversation, attach images and PDFs using the attachment button, or drag and drop files directly into the prompt. The more context Claude has, the better the results. See [Add files and context](/en/desktop#add-files-and-context-to-prompts).

113 113 

114**Use skills for repeatable tasks.** Type `/` or click **+** → **Slash commands** to browse [built-in commands](/en/interactive-mode#built-in-commands), [custom skills](/en/skills), and plugin skills. Skills are reusable prompts you can invoke whenever you need them, like code review checklists or deployment steps.114**Use skills for repeatable tasks.** Type `/` or click **+** → **Slash commands** to browse [built-in commands](/en/commands), [custom skills](/en/skills), and plugin skills. Skills are reusable prompts you can invoke whenever you need them, like code review checklists or deployment steps.

115 115 

116**Review changes before committing.** After Claude edits files, a `+12 -1` indicator appears. Click it to open the [diff view](/en/desktop#review-changes-with-diff-view), review modifications file by file, and comment on specific lines. Claude reads your comments and revises. Click **Review code** to have Claude evaluate the diffs itself and leave inline suggestions.116**Review changes before committing.** After Claude edits files, a `+12 -1` indicator appears. Click it to open the [diff view](/en/desktop#review-changes-with-diff-view), review modifications file by file, and comment on specific lines. Claude reads your comments and revises. Click **Review code** to have Claude evaluate the diffs itself and leave inline suggestions.

117 117 

1> ## Documentation Index

2> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt

3> Use this file to discover all available pages before exploring further.

4 

5# Environment variables

6 

7> Complete reference for environment variables that control Claude Code behavior.

8 

9Claude Code supports the following environment variables to control its behavior. Set them in your shell before launching `claude`, or configure them in [`settings.json`](/en/settings#available-settings) under the `env` key to apply them to every session or roll them out across your team.

10 

11| Variable | Purpose |

12| :--------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

13| `ANTHROPIC_API_KEY` | API key sent as `X-Api-Key` header, typically for the Claude SDK (for interactive usage, run `/login`) |

14| `ANTHROPIC_AUTH_TOKEN` | Custom value for the `Authorization` header (the value you set here will be prefixed with `Bearer `) |

15| `ANTHROPIC_CUSTOM_HEADERS` | Custom headers to add to requests (`Name: Value` format, newline-separated for multiple headers) |

16| `ANTHROPIC_DEFAULT_HAIKU_MODEL` | See [Model configuration](/en/model-config#environment-variables) |

17| `ANTHROPIC_DEFAULT_OPUS_MODEL` | See [Model configuration](/en/model-config#environment-variables) |

18| `ANTHROPIC_DEFAULT_SONNET_MODEL` | See [Model configuration](/en/model-config#environment-variables) |

19| `ANTHROPIC_FOUNDRY_API_KEY` | API key for Microsoft Foundry authentication (see [Microsoft Foundry](/en/microsoft-foundry)) |

20| `ANTHROPIC_FOUNDRY_BASE_URL` | Full base URL for the Foundry resource (for example, `https://my-resource.services.ai.azure.com/anthropic`). Alternative to `ANTHROPIC_FOUNDRY_RESOURCE` (see [Microsoft Foundry](/en/microsoft-foundry)) |

21| `ANTHROPIC_FOUNDRY_RESOURCE` | Foundry resource name (for example, `my-resource`). Required if `ANTHROPIC_FOUNDRY_BASE_URL` is not set (see [Microsoft Foundry](/en/microsoft-foundry)) |

22| `ANTHROPIC_MODEL` | Name of the model setting to use (see [Model Configuration](/en/model-config#environment-variables)) |

23| `ANTHROPIC_SMALL_FAST_MODEL` | \[DEPRECATED] Name of [Haiku-class model for background tasks](/en/costs) |

24| `ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION` | Override AWS region for the Haiku-class model when using Bedrock |

25| `AWS_BEARER_TOKEN_BEDROCK` | Bedrock API key for authentication (see [Bedrock API keys](https://aws.amazon.com/blogs/machine-learning/accelerate-ai-development-with-amazon-bedrock-api-keys/)) |

26| `BASH_DEFAULT_TIMEOUT_MS` | Default timeout for long-running bash commands |

27| `BASH_MAX_OUTPUT_LENGTH` | Maximum number of characters in bash outputs before they are middle-truncated |

28| `BASH_MAX_TIMEOUT_MS` | Maximum timeout the model can set for long-running bash commands |

29| `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` | Set the percentage of context capacity (1-100) at which auto-compaction triggers. By default, auto-compaction triggers at approximately 95% capacity. Use lower values like `50` to compact earlier. Values above the default threshold have no effect. Applies to both main conversations and subagents. This percentage aligns with the `context_window.used_percentage` field available in [status line](/en/statusline) |

30| `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR` | Return to the original working directory after each Bash command |

31| `CLAUDE_CODE_ACCOUNT_UUID` | Account UUID for the authenticated user. Used by SDK callers to provide account information synchronously, avoiding a race condition where early telemetry events lack account metadata. Requires `CLAUDE_CODE_USER_EMAIL` and `CLAUDE_CODE_ORGANIZATION_UUID` to also be set |

32| `CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD` | Set to `1` to load CLAUDE.md files from directories specified with `--add-dir`. By default, additional directories do not load memory files |

33| `CLAUDE_CODE_AUTO_COMPACT_WINDOW` | Set the context capacity in tokens used for auto-compaction calculations. Defaults to the model's context window: 200K for standard models or 1M for [extended context](/en/model-config#extended-context) models. Use a lower value like `500000` on a 1M model to treat the window as 500K for compaction purposes. The value is capped at the model's actual context window. `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` is applied as a percentage of this value. Setting this variable decouples the compaction threshold from the status line's `used_percentage`, which always uses the model's full context window |

34| `CLAUDE_CODE_API_KEY_HELPER_TTL_MS` | Interval in milliseconds at which credentials should be refreshed (when using [`apiKeyHelper`](/en/settings#available-settings)) |

35| `CLAUDE_CODE_CLIENT_CERT` | Path to client certificate file for mTLS authentication |

36| `CLAUDE_CODE_CLIENT_KEY` | Path to client private key file for mTLS authentication |

37| `CLAUDE_CODE_CLIENT_KEY_PASSPHRASE` | Passphrase for encrypted CLAUDE\_CODE\_CLIENT\_KEY (optional) |

38| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Set to `1` to disable [1M context window](/en/model-config#extended-context) support. When set, 1M model variants are unavailable in the model picker. Useful for enterprise environments with compliance requirements |

39| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/en/model-config#adjust-effort-level) for Opus 4.6 and Sonnet 4.6. When disabled, these models fall back to the fixed thinking budget controlled by `MAX_THINKING_TOKENS` |

40| `CLAUDE_CODE_DISABLE_AUTO_MEMORY` | Set to `1` to disable [auto memory](/en/memory#auto-memory). Set to `0` to force auto memory on during the gradual rollout. When disabled, Claude does not create or load auto memory files |

41| `CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS` | Set to `1` to remove built-in commit and PR workflow instructions from Claude's system prompt. Useful when using your own git workflow skills. Takes precedence over the [`includeGitInstructions`](/en/settings#available-settings) setting when set |

42| `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` | Set to `1` to disable all background task functionality, including the `run_in_background` parameter on Bash and subagent tools, auto-backgrounding, and the Ctrl+B shortcut |

43| `CLAUDE_CODE_DISABLE_CRON` | Set to `1` to disable [scheduled tasks](/en/scheduled-tasks). The `/loop` skill and cron tools become unavailable and any already-scheduled tasks stop firing, including tasks that are already running mid-session |

44| `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` | Set to `1` to disable Anthropic API-specific `anthropic-beta` headers. Use this if experiencing issues like "Unexpected value(s) for the `anthropic-beta` header" when using an LLM gateway with third-party providers |

45| `CLAUDE_CODE_DISABLE_FAST_MODE` | Set to `1` to disable [fast mode](/en/fast-mode) |

46| `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` | Set to `1` to disable the "How is Claude doing?" session quality surveys. Also disabled when using third-party providers or when telemetry is disabled. See [Session quality surveys](/en/data-usage#session-quality-surveys) |

47| `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` | Equivalent of setting `DISABLE_AUTOUPDATER`, `DISABLE_BUG_COMMAND`, `DISABLE_ERROR_REPORTING`, and `DISABLE_TELEMETRY` |

48| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Set to `1` to disable automatic terminal title updates based on conversation context |

49| `CLAUDE_CODE_EFFORT_LEVEL` | Set the effort level for supported models. Values: `low`, `medium`, `high`. Lower effort is faster and cheaper, higher effort provides deeper reasoning. Supported on Opus 4.6 and Sonnet 4.6. See [Adjust effort level](/en/model-config#adjust-effort-level) |

50| `CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION` | Set to `false` to disable prompt suggestions (the "Prompt suggestions" toggle in `/config`). These are the grayed-out predictions that appear in your prompt input after Claude responds. See [Prompt suggestions](/en/interactive-mode#prompt-suggestions) |

51| `CLAUDE_CODE_ENABLE_TASKS` | Set to `true` to enable the task tracking system in non-interactive mode (the `-p` flag). Tasks are on by default in interactive mode. See [Task list](/en/interactive-mode#task-list) |

52| `CLAUDE_CODE_ENABLE_TELEMETRY` | Set to `1` to enable OpenTelemetry data collection for metrics and logging. Required before configuring OTel exporters. See [Monitoring](/en/monitoring-usage) |

53| `CLAUDE_CODE_EXIT_AFTER_STOP_DELAY` | Time in milliseconds to wait after the query loop becomes idle before automatically exiting. Useful for automated workflows and scripts using SDK mode |

54| `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` | Set to `1` to enable [agent teams](/en/agent-teams). Agent teams are experimental and disabled by default |

55| `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS` | Override the default token limit for file reads. Useful when you need to read larger files in full |

56| `CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL` | Skip auto-installation of IDE extensions |

57| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Set the maximum number of output tokens for most requests. Default: 32,000. Maximum: 64,000. Increasing this value reduces the effective context window available before [auto-compaction](/en/costs#reduce-token-usage) triggers. |

58| `CLAUDE_CODE_ORGANIZATION_UUID` | Organization UUID for the authenticated user. Used by SDK callers to provide account information synchronously. Requires `CLAUDE_CODE_ACCOUNT_UUID` and `CLAUDE_CODE_USER_EMAIL` to also be set |

59| `CLAUDE_CODE_OTEL_HEADERS_HELPER_DEBOUNCE_MS` | Interval for refreshing dynamic OpenTelemetry headers in milliseconds (default: 1740000 / 29 minutes). See [Dynamic headers](/en/monitoring-usage#dynamic-headers) |

60| `CLAUDE_CODE_PLAN_MODE_REQUIRED` | Auto-set to `true` on [agent team](/en/agent-teams) teammates that require plan approval. Read-only: set by Claude Code when spawning teammates. See [require plan approval](/en/agent-teams#require-plan-approval-for-teammates) |

61| `CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS` | Timeout in milliseconds for git operations when installing or updating plugins (default: 120000). Increase this value for large repositories or slow network connections. See [Git operations time out](/en/plugin-marketplaces#git-operations-time-out) |

62| `CLAUDE_CODE_PROXY_RESOLVES_HOSTS` | Set to `true` to allow the proxy to perform DNS resolution instead of the caller. Opt-in for environments where the proxy should handle hostname resolution |

63| `CLAUDE_CODE_SESSIONEND_HOOKS_TIMEOUT_MS` | Maximum time in milliseconds for [SessionEnd](/en/hooks#sessionend) hooks to complete (default: `1500`). Applies to both session exit and `/clear`. Per-hook `timeout` values are also capped by this budget |

64| `CLAUDE_CODE_SHELL` | Override automatic shell detection. Useful when your login shell differs from your preferred working shell (for example, `bash` vs `zsh`) |

65| `CLAUDE_CODE_SHELL_PREFIX` | Command prefix to wrap all bash commands (for example, for logging or auditing). Example: `/path/to/logger.sh` will execute `/path/to/logger.sh <command>` |

66| `CLAUDE_CODE_SIMPLE` | Set to `1` to run with a minimal system prompt and only the Bash, file read, and file edit tools. Disables MCP tools, attachments, hooks, and CLAUDE.md files |

67| `CLAUDE_CODE_SKIP_BEDROCK_AUTH` | Skip AWS authentication for Bedrock (for example, when using an LLM gateway) |

68| `CLAUDE_CODE_SKIP_FOUNDRY_AUTH` | Skip Azure authentication for Microsoft Foundry (for example, when using an LLM gateway) |

69| `CLAUDE_CODE_SKIP_VERTEX_AUTH` | Skip Google authentication for Vertex (for example, when using an LLM gateway) |

70| `CLAUDE_CODE_SUBAGENT_MODEL` | See [Model configuration](/en/model-config) |

71| `CLAUDE_CODE_TASK_LIST_ID` | Share a task list across sessions. Set the same ID in multiple Claude Code instances to coordinate on a shared task list. See [Task list](/en/interactive-mode#task-list) |

72| `CLAUDE_CODE_TEAM_NAME` | Name of the agent team this teammate belongs to. Set automatically on [agent team](/en/agent-teams) members |

73| `CLAUDE_CODE_TMPDIR` | Override the temp directory used for internal temp files. Claude Code appends `/claude/` to this path. Default: `/tmp` on Unix/macOS, `os.tmpdir()` on Windows |

74| `CLAUDE_CODE_USER_EMAIL` | Email address for the authenticated user. Used by SDK callers to provide account information synchronously. Requires `CLAUDE_CODE_ACCOUNT_UUID` and `CLAUDE_CODE_ORGANIZATION_UUID` to also be set |

75| `CLAUDE_CODE_USE_BEDROCK` | Use [Bedrock](/en/amazon-bedrock) |

76| `CLAUDE_CODE_USE_FOUNDRY` | Use [Microsoft Foundry](/en/microsoft-foundry) |

77| `CLAUDE_CODE_USE_VERTEX` | Use [Vertex](/en/google-vertex-ai) |

78| `CLAUDE_CONFIG_DIR` | Customize where Claude Code stores its configuration and data files |

79| `CLAUDE_ENV_FILE` | Path to a shell script that Claude Code sources before each Bash command. Use to persist virtualenv or conda activation across commands. Also populated dynamically by [SessionStart hooks](/en/hooks#persist-environment-variables) |

80| `DISABLE_AUTOUPDATER` | Set to `1` to disable automatic updates. |

81| `DISABLE_BUG_COMMAND` | Set to `1` to disable the `/bug` command |

82| `DISABLE_COST_WARNINGS` | Set to `1` to disable cost warning messages |

83| `DISABLE_ERROR_REPORTING` | Set to `1` to opt out of Sentry error reporting |

84| `DISABLE_INSTALLATION_CHECKS` | Set to `1` to disable installation warnings. Use only when manually managing the installation location, as this can mask issues with standard installations |

85| `DISABLE_PROMPT_CACHING` | Set to `1` to disable prompt caching for all models (takes precedence over per-model settings) |

86| `DISABLE_PROMPT_CACHING_HAIKU` | Set to `1` to disable prompt caching for Haiku models |

87| `DISABLE_PROMPT_CACHING_OPUS` | Set to `1` to disable prompt caching for Opus models |

88| `DISABLE_PROMPT_CACHING_SONNET` | Set to `1` to disable prompt caching for Sonnet models |

89| `DISABLE_TELEMETRY` | Set to `1` to opt out of Statsig telemetry (note that Statsig events do not include user data like code, file paths, or bash commands) |

90| `ENABLE_CLAUDEAI_MCP_SERVERS` | Set to `false` to disable [claude.ai MCP servers](/en/mcp#use-mcp-servers-from-claudeai) in Claude Code. Enabled by default for logged-in users |

91| `ENABLE_TOOL_SEARCH` | Controls [MCP tool search](/en/mcp#scale-with-mcp-tool-search). Unset: enabled by default, but disabled when `ANTHROPIC_BASE_URL` points to a non-first-party host. Values: `true` (always on including proxies), `auto` (enables at 10% context), `auto:N` (custom threshold, e.g., `auto:5` for 5%), `false` (disabled) |

92| `FORCE_AUTOUPDATE_PLUGINS` | Set to `true` to force plugin auto-updates even when the main auto-updater is disabled via `DISABLE_AUTOUPDATER` |

93| `HTTP_PROXY` | Specify HTTP proxy server for network connections |

94| `HTTPS_PROXY` | Specify HTTPS proxy server for network connections |

95| `IS_DEMO` | Set to `true` to enable demo mode: hides email and organization from the UI, skips onboarding, and hides internal commands. Useful for streaming or recording sessions |

96| `MAX_MCP_OUTPUT_TOKENS` | Maximum number of tokens allowed in MCP tool responses. Claude Code displays a warning when output exceeds 10,000 tokens (default: 25000) |

97| `MAX_THINKING_TOKENS` | Override the [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) token budget. Thinking is enabled at max budget (31,999 tokens) by default. Use this to limit the budget (for example, `MAX_THINKING_TOKENS=10000`) or disable thinking entirely (`MAX_THINKING_TOKENS=0`). For Opus 4.6, thinking depth is controlled by [effort level](/en/model-config#adjust-effort-level) instead, and this variable is ignored unless set to `0` to disable thinking. |

98| `MCP_CLIENT_SECRET` | OAuth client secret for MCP servers that require [pre-configured credentials](/en/mcp#use-pre-configured-oauth-credentials). Avoids the interactive prompt when adding a server with `--client-secret` |

99| `MCP_OAUTH_CALLBACK_PORT` | Fixed port for the OAuth redirect callback, as an alternative to `--callback-port` when adding an MCP server with [pre-configured credentials](/en/mcp#use-pre-configured-oauth-credentials) |

100| `MCP_TIMEOUT` | Timeout in milliseconds for MCP server startup |

101| `MCP_TOOL_TIMEOUT` | Timeout in milliseconds for MCP tool execution |

102| `NO_PROXY` | List of domains and IPs to which requests will be directly issued, bypassing proxy |

103| `SLASH_COMMAND_TOOL_CHAR_BUDGET` | Override the character budget for skill metadata shown to the [Skill tool](/en/skills#control-who-invokes-a-skill). The budget scales dynamically at 2% of the context window, with a fallback of 16,000 characters. Legacy name kept for backwards compatibility |

104| `USE_BUILTIN_RIPGREP` | Set to `0` to use system-installed `rg` instead of `rg` included with Claude Code |

105| `VERTEX_REGION_CLAUDE_3_5_HAIKU` | Override region for Claude 3.5 Haiku when using Vertex AI |

106| `VERTEX_REGION_CLAUDE_3_7_SONNET` | Override region for Claude 3.7 Sonnet when using Vertex AI |

107| `VERTEX_REGION_CLAUDE_4_0_OPUS` | Override region for Claude 4.0 Opus when using Vertex AI |

108| `VERTEX_REGION_CLAUDE_4_0_SONNET` | Override region for Claude 4.0 Sonnet when using Vertex AI |

109| `VERTEX_REGION_CLAUDE_4_1_OPUS` | Override region for Claude 4.1 Opus when using Vertex AI |

110 

111## See also

112 

113* [Settings](/en/settings): configure environment variables in `settings.json` so they apply to every session

114* [CLI reference](/en/cli-reference): launch-time flags

115* [Network configuration](/en/network-config): proxy and TLS setup

109* **Console** (API customers): [Claude Code preferences](https://platform.claude.com/claude-code/preferences)109* **Console** (API customers): [Claude Code preferences](https://platform.claude.com/claude-code/preferences)

110* **Claude AI** (Teams and Enterprise): [Admin Settings > Claude Code](https://claude.ai/admin-settings/claude-code)110* **Claude AI** (Teams and Enterprise): [Admin Settings > Claude Code](https://claude.ai/admin-settings/claude-code)

111 111 

112Another option to disable fast mode entirely is to set `CLAUDE_CODE_DISABLE_FAST_MODE=1`. See [Environment variables](/en/settings#environment-variables).112Another option to disable fast mode entirely is to set `CLAUDE_CODE_DISABLE_FAST_MODE=1`. See [Environment variables](/en/env-vars).

113 113 

114### Require per-session opt-in114### Require per-session opt-in

115 115 

135 135 

136## 1M token context window136## 1M token context window

137 137 

138Claude Sonnet 4 and Sonnet 4.6 support the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window) on Vertex AI.138Claude Opus 4.6, Sonnet 4.6, Sonnet 4.5, and Sonnet 4 support the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window) on Vertex AI. Claude Code automatically enables the extended context window when you select a 1M model variant.

139 139 

140<Note>140To enable the 1M context window for your pinned model, append `[1m]` to the model ID. See [Pin models for third-party deployments](/en/model-config#pin-models-for-third-party-deployments) for details.

141 The 1M token context window is currently in beta. To use the extended context window, include the `context-1m-2025-08-07` beta header in your Vertex AI requests.

142</Note>

143 141 

144## Troubleshooting142## Troubleshooting

145 143 

115The `--allowedTools` flag uses [permission rule syntax](/en/settings#permission-rule-syntax). The trailing ` *` enables prefix matching, so `Bash(git diff *)` allows any command starting with `git diff`. The space before `*` is important: without it, `Bash(git diff*)` would also match `git diff-index`.115The `--allowedTools` flag uses [permission rule syntax](/en/settings#permission-rule-syntax). The trailing ` *` enables prefix matching, so `Bash(git diff *)` allows any command starting with `git diff`. The space before `*` is important: without it, `Bash(git diff*)` would also match `git diff-index`.

116 116 

117<Note>117<Note>

118 User-invoked [skills](/en/skills) like `/commit` and [built-in commands](/en/interactive-mode#built-in-commands) are only available in interactive mode. In `-p` mode, describe the task you want to accomplish instead.118 User-invoked [skills](/en/skills) like `/commit` and [built-in commands](/en/commands) are only available in interactive mode. In `-p` mode, describe the task you want to accomplish instead.

119</Note>119</Note>

120 120 

121### Customize the system prompt121### Customize the system prompt

925| `updatedInput` | Modifies the tool's input parameters before execution. Combine with `"allow"` to auto-approve, or `"ask"` to show the modified input to the user |925| `updatedInput` | Modifies the tool's input parameters before execution. Combine with `"allow"` to auto-approve, or `"ask"` to show the modified input to the user |

926| `additionalContext` | String added to Claude's context before the tool executes |926| `additionalContext` | String added to Claude's context before the tool executes |

927 927 

928When a hook returns `"ask"`, the permission prompt displayed to the user includes a label identifying where the hook came from: for example, `[User]`, `[Project]`, `[Plugin]`, or `[Local]`. This helps users understand which configuration source is requesting confirmation.

929 

928```json theme={null}930```json theme={null}

929{931{

930 "hookSpecificOutput": {932 "hookSpecificOutput": {

1766 1768 

1767After the background process exits, if the hook produced a JSON response with a `systemMessage` or `additionalContext` field, that content is delivered to Claude as context on the next conversation turn.1769After the background process exits, if the hook produced a JSON response with a `systemMessage` or `additionalContext` field, that content is delivered to Claude as context on the next conversation turn.

1768 1770 

1771Async hook completion notifications are suppressed by default. To see them, enable verbose mode with `Ctrl+O` or start Claude Code with `--verbose`.

1772 

1769### Example: run tests after file changes1773### Example: run tests after file changes

1770 1774 

1771This hook starts a test suite in the background whenever Claude writes a file, then reports the results back to Claude when the tests finish. Save this script to `.claude/hooks/run-tests-async.sh` in your project and make it executable with `chmod +x`:1775This hook starts a test suite in the background whenever Claude writes a file, then reports the results back to Claude when the tests finish. Save this script to `.claude/hooks/run-tests-async.sh` in your project and make it executable with `chmod +x`:

44| **Web** | Search the web, fetch documentation, look up error messages |44| **Web** | Search the web, fetch documentation, look up error messages |

45| **Code intelligence** | See type errors and warnings after edits, jump to definitions, find references (requires [code intelligence plugins](/en/discover-plugins#code-intelligence)) |45| **Code intelligence** | See type errors and warnings after edits, jump to definitions, find references (requires [code intelligence plugins](/en/discover-plugins#code-intelligence)) |

46 46 

47These are the primary capabilities. Claude also has tools for spawning subagents, asking you questions, and other orchestration tasks. See [Tools available to Claude](/en/settings#tools-available-to-claude) for the complete list.47These are the primary capabilities. Claude also has tools for spawning subagents, asking you questions, and other orchestration tasks. See [Tools available to Claude](/en/tools-reference) for the complete list.

48 48 

49Claude chooses which tools to use based on your prompt and what it learns along the way. When you say "fix the failing tests," Claude might:49Claude chooses which tools to use based on your prompt and what it learns along the way. When you say "fix the failing tests," Claude might:

50 50 

86 86 

87## Built-in commands87## Built-in commands

88 88 

89Type `/` in Claude Code to see all available commands, or type `/` followed by any letters to filter. Not all commands are visible to every user. Some depend on your platform, plan, or environment. For example, `/desktop` only appears on macOS and Windows, `/upgrade` and `/privacy-settings` are only available on Pro and Max plans, and `/terminal-setup` is hidden when your terminal natively supports its keybindings.89Type `/` in Claude Code to see all available commands, or type `/` followed by any letters to filter. The `/` menu shows both built-in commands and [bundled skills](/en/skills#bundled-skills) like `/simplify`. Not all commands are visible to every user since some depend on your platform or plan.

90 90 

91Claude Code also ships with [bundled skills](/en/skills#bundled-skills) like `/simplify`, `/batch`, and `/debug` that appear alongside built-in commands when you type `/`. To create your own commands, see [skills](/en/skills).91See the [commands reference](/en/commands) for the full list of built-in commands. To create your own commands, see [skills](/en/skills).

92 

93In the table below, `<arg>` indicates a required argument and `[arg]` indicates an optional one.

94 

95| Command | Purpose |

96| :------------------------ | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

97| `/add-dir <path>` | Add a new working directory to the current session |

98| `/agents` | Manage [agent](/en/sub-agents) configurations |

99| `/btw <question>` | Ask a quick [side question](#side-questions-with-%2Fbtw) without adding to the conversation |

100| `/chrome` | Configure [Claude in Chrome](/en/chrome) settings |

101| `/clear` | Clear conversation history and free up context. Aliases: `/reset`, `/new` |

102| `/compact [instructions]` | Compact conversation with optional focus instructions |

103| `/config` | Open the [Settings](/en/settings) interface to adjust theme, model, [output style](/en/output-styles), and other preferences. Alias: `/settings` |

104| `/context` | Visualize current context usage as a colored grid. Shows optimization suggestions for context-heavy tools, memory bloat, and capacity warnings |

105| `/copy` | Copy the last assistant response to clipboard. When code blocks are present, shows an interactive picker to select individual blocks or the full response |

106| `/cost` | Show token usage statistics. See [cost tracking guide](/en/costs#using-the-cost-command) for subscription-specific details |

107| `/desktop` | Continue the current session in the Claude Code Desktop app. macOS and Windows only. Alias: `/app` |

108| `/diff` | Open an interactive diff viewer showing uncommitted changes and per-turn diffs. Use left/right arrows to switch between the current git diff and individual Claude turns, and up/down to browse files |

109| `/doctor` | Diagnose and verify your Claude Code installation and settings |

110| `/exit` | Exit the CLI. Alias: `/quit` |

111| `/export [filename]` | Export the current conversation as plain text. With a filename, writes directly to that file. Without, opens a dialog to copy to clipboard or save to a file |

112| `/extra-usage` | Configure extra usage to keep working when rate limits are hit |

113| `/fast [on\|off]` | Toggle [fast mode](/en/fast-mode) on or off |

114| `/feedback [report]` | Submit feedback about Claude Code. Alias: `/bug` |

115| `/fork [name]` | Create a fork of the current conversation at this point |

116| `/help` | Show help and available commands |

117| `/hooks` | Manage [hook](/en/hooks) configurations for tool events |

118| `/ide` | Manage IDE integrations and show status |

119| `/init` | Initialize project with `CLAUDE.md` guide |

120| `/insights` | Generate a report analyzing your Claude Code sessions, including project areas, interaction patterns, and friction points |

121| `/install-github-app` | Set up the [Claude GitHub Actions](/en/github-actions) app for a repository. Walks you through selecting a repo and configuring the integration |

122| `/install-slack-app` | Install the Claude Slack app. Opens a browser to complete the OAuth flow |

123| `/keybindings` | Open or create your keybindings configuration file |

124| `/login` | Sign in to your Anthropic account |

125| `/logout` | Sign out from your Anthropic account |

126| `/mcp` | Manage MCP server connections and OAuth authentication |

127| `/memory` | Edit `CLAUDE.md` memory files, enable or disable [auto-memory](/en/memory#auto-memory), and view auto-memory entries |

128| `/mobile` | Show QR code to download the Claude mobile app. Aliases: `/ios`, `/android` |

129| `/model [model]` | Select or change the AI model. For models that support it, use left/right arrows to [adjust effort level](/en/model-config#adjust-effort-level). The change takes effect immediately without waiting for the current response to finish |

130| `/passes` | Share a free week of Claude Code with friends. Only visible if your account is eligible |

131| `/permissions` | View or update [permissions](/en/permissions#manage-permissions). Alias: `/allowed-tools` |

132| `/plan` | Enter plan mode directly from the prompt |

133| `/plugin` | Manage Claude Code [plugins](/en/plugins) |

134| `/pr-comments [PR]` | Fetch and display comments from a GitHub pull request. Automatically detects the PR for the current branch, or pass a PR URL or number. Requires the `gh` CLI |

135| `/privacy-settings` | View and update your privacy settings. Only available for Pro and Max plan subscribers |

136| `/release-notes` | View the full changelog, with the most recent version closest to your prompt |

137| `/reload-plugins` | Reload all active [plugins](/en/plugins) to apply pending changes without restarting. Reports what was loaded and notes any changes that require a restart |

138| `/remote-control` | Make this session available for [remote control](/en/remote-control) from claude.ai. Alias: `/rc` |

139| `/remote-env` | Configure the default remote environment for [teleport sessions](/en/claude-code-on-the-web#teleport-a-web-session-to-your-terminal) |

140| `/rename [name]` | Rename the current session. Without a name, auto-generates one from conversation history |

141| `/resume [session]` | Resume a conversation by ID or name, or open the session picker. Alias: `/continue` |

142| `/review` | Deprecated. Install the [`code-review` plugin](https://github.com/anthropics/claude-code-marketplace/blob/main/code-review/README.md) instead: `claude plugin install code-review@claude-code-marketplace` |

143| `/rewind` | Rewind the conversation and/or code to a previous point, or summarize from a selected message. See [checkpointing](/en/checkpointing). Alias: `/checkpoint` |

144| `/sandbox` | Toggle [sandbox mode](/en/sandboxing). Available on supported platforms only |

145| `/security-review` | Analyze pending changes on the current branch for security vulnerabilities. Reviews the git diff and identifies risks like injection, auth issues, and data exposure |

146| `/skills` | List available [skills](/en/skills) |

147| `/stats` | Visualize daily usage, session history, streaks, and model preferences |

148| `/status` | Open the Settings interface (Status tab) showing version, model, account, and connectivity |

149| `/statusline` | Configure Claude Code's [status line](/en/statusline). Describe what you want, or run without arguments to auto-configure from your shell prompt |

150| `/stickers` | Order Claude Code stickers |

151| `/tasks` | List and manage background tasks |

152| `/terminal-setup` | Configure terminal keybindings for Shift+Enter and other shortcuts. Only visible in terminals that need it, like VS Code, Alacritty, or Warp |

153| `/theme` | Change the color theme. Includes light and dark variants, colorblind-accessible (daltonized) themes, and ANSI themes that use your terminal's color palette |

154| `/upgrade` | Open the upgrade page to switch to a higher plan tier |

155| `/usage` | Show plan usage limits and rate limit status |

156| `/vim` | Toggle between Vim and Normal editing modes |

157 

158### MCP prompts

159 

160MCP servers can expose prompts that appear as commands. These use the format `/mcp__<server>__<prompt>` and are dynamically discovered from connected servers. See [MCP prompts](/en/mcp#use-mcp-prompts-as-commands) for details.

161 92 

162## Vim editor mode93## Vim editor mode

163 94 

277* Background tasks have unique IDs for tracking and output retrieval208* Background tasks have unique IDs for tracking and output retrieval

278* Background tasks are automatically cleaned up when Claude Code exits209* Background tasks are automatically cleaned up when Claude Code exits

279 210 

280To disable all background task functionality, set the `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` environment variable to `1`. See [Environment variables](/en/settings#environment-variables) for details.211To disable all background task functionality, set the `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` environment variable to `1`. See [Environment variables](/en/env-vars) for details.

281 212 

282**Common backgrounded commands:**213**Common backgrounded commands:**

283 214 

321 321 

322### Claude isn't following my CLAUDE.md322### Claude isn't following my CLAUDE.md

323 323 

324CLAUDE.md is context, not enforcement. Claude reads it and tries to follow it, but there's no guarantee of strict compliance, especially for vague or conflicting instructions.324CLAUDE.md content is delivered as a user message after the system prompt, not as part of the system prompt itself. Claude reads it and tries to follow it, but there's no guarantee of strict compliance, especially for vague or conflicting instructions.

325 325 

326To debug:326To debug:

327 327 

330* Make instructions more specific. "Use 2-space indentation" works better than "format code nicely."330* Make instructions more specific. "Use 2-space indentation" works better than "format code nicely."

331* Look for conflicting instructions across CLAUDE.md files. If two files give different guidance for the same behavior, Claude may pick one arbitrarily.331* Look for conflicting instructions across CLAUDE.md files. If two files give different guidance for the same behavior, Claude may pick one arbitrarily.

332 332 

333For instructions you want at the system prompt level, use [`--append-system-prompt`](/en/cli-reference#system-prompt-flags). This must be passed every invocation, so it's better suited to scripts and automation than interactive use.

334 

333<Tip>335<Tip>

334 Use the [`InstructionsLoaded` hook](/en/hooks#instructionsloaded) to log exactly which instruction files are loaded, when they load, and why. This is useful for debugging path-specific rules or lazy-loaded files in subdirectories.336 Use the [`InstructionsLoaded` hook](/en/hooks#instructionsloaded) to log exactly which instruction files are loaded, when they load, and why. This is useful for debugging path-specific rules or lazy-loaded files in subdirectories.

335</Tip>337</Tip>

29| **`opus`** | Uses the latest Opus model (currently Opus 4.6) for complex reasoning tasks |29| **`opus`** | Uses the latest Opus model (currently Opus 4.6) for complex reasoning tasks |

30| **`haiku`** | Uses the fast and efficient Haiku model for simple tasks |30| **`haiku`** | Uses the fast and efficient Haiku model for simple tasks |

31| **`sonnet[1m]`** | Uses Sonnet with a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window) for long sessions |31| **`sonnet[1m]`** | Uses Sonnet with a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window) for long sessions |

32| **`opus[1m]`** | Uses Opus with a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window) for long sessions |

32| **`opusplan`** | Special mode that uses `opus` during plan mode, then switches to `sonnet` for execution |33| **`opusplan`** | Special mode that uses `opus` during plan mode, then switches to `sonnet` for execution |

33 34 

34Aliases always point to the latest version. To pin to a specific version, use the full model name (for example, `claude-opus-4-6`) or set the corresponding environment variable like `ANTHROPIC_DEFAULT_OPUS_MODEL`.35Aliases always point to the latest version. To pin to a specific version, use the full model name (for example, `claude-opus-4-6`) or set the corresponding environment variable like `ANTHROPIC_DEFAULT_OPUS_MODEL`.

140 141 

141Effort is supported on Opus 4.6 and Sonnet 4.6. The effort slider appears in `/model` when a supported model is selected. The current effort level is also displayed next to the logo and spinner (for example, "with low effort"), so you can confirm which setting is active without opening `/model`.142Effort is supported on Opus 4.6 and Sonnet 4.6. The effort slider appears in `/model` when a supported model is selected. The current effort level is also displayed next to the logo and spinner (for example, "with low effort"), so you can confirm which setting is active without opening `/model`.

142 143 

143To disable adaptive reasoning on Opus 4.6 and Sonnet 4.6 and revert to the previous fixed thinking budget, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1`. When disabled, these models use the fixed budget controlled by `MAX_THINKING_TOKENS`. See [environment variables](/en/settings#environment-variables).144To disable adaptive reasoning on Opus 4.6 and Sonnet 4.6 and revert to the previous fixed thinking budget, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1`. When disabled, these models use the fixed budget controlled by `MAX_THINKING_TOKENS`. See [environment variables](/en/env-vars).

144 145 

145### Extended context146### Extended context

146 147 

147Opus 4.6 and Sonnet 4.6 support a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window) for long sessions with large codebases.148Opus 4.6 and Sonnet 4.6 support a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#1m-token-context-window) for long sessions with large codebases.

148 149 

149<Note>150Availability varies by model and plan. On Max, Team, and Enterprise plans, Opus is automatically upgraded to 1M context with no additional configuration. This applies to both Team Standard and Team Premium seats.

150 The 1M context window is currently in beta. Features, pricing, and availability may change.

151</Note>

152 151 

153Extended context is available for:152| Plan | Opus 4.6 with 1M context | Sonnet 4.6 with 1M context |

153| ------------------------- | --------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |

154| Max, Team, and Enterprise | Included with subscription | Requires [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

155| Pro | Requires [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) | Requires [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) |

156| API and pay-as-you-go | Full access | Full access |

154 157 

155* **API and pay-as-you-go users**: full access to 1M context158To disable 1M context entirely, set `CLAUDE_CODE_DISABLE_1M_CONTEXT=1`. This removes 1M model variants from the model picker. See [environment variables](/en/env-vars).

156* **Pro, Max, Teams, and Enterprise subscribers**: available with [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) enabled

157 159 

158To disable 1M context entirely, set `CLAUDE_CODE_DISABLE_1M_CONTEXT=1`. This removes 1M model variants from the model picker. See [environment variables](/en/settings#environment-variables).160The 1M context window uses standard model pricing with no premium for tokens beyond 200K. For plans where extended context is included with your subscription, usage remains covered by your subscription. For plans that access extended context through extra usage, tokens are billed to extra usage.

159 

160Selecting a 1M model does not immediately change billing. Your session uses standard rates until it exceeds 200K tokens of context. Beyond 200K tokens, requests are charged at [long-context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing) with dedicated [rate limits](https://platform.claude.com/docs/en/api/rate-limits#long-context-rate-limits). For subscribers, tokens beyond 200K are billed as extra usage rather than through the subscription.

161 161 

162If your account supports 1M context, the option appears in the model picker (`/model`) in the latest versions of Claude Code. If you don't see it, try restarting your session.162If your account supports 1M context, the option appears in the model picker (`/model`) in the latest versions of Claude Code. If you don't see it, try restarting your session.

163 163 

164You can also use the `[1m]` suffix with model aliases or full model names:164You can also use the `[1m]` suffix with model aliases or full model names:

165 165 

166```bash theme={null}166```bash theme={null}

167# Use the sonnet[1m] alias167# Use the opus[1m] or sonnet[1m] alias

168/model opus[1m]

168/model sonnet[1m]169/model sonnet[1m]

169 170 

170# Or append [1m] to a full model name171# Or append [1m] to a full model name

171/model claude-sonnet-4-6[1m]172/model claude-opus-4-6[1m]

172```173```

173 174 

174## Checking your current model175## Checking your current model

213 214 

214Apply the same pattern for `ANTHROPIC_DEFAULT_SONNET_MODEL` and `ANTHROPIC_DEFAULT_HAIKU_MODEL`. For current and legacy model IDs across all providers, see [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview). To upgrade users to a new model version, update these environment variables and redeploy.215Apply the same pattern for `ANTHROPIC_DEFAULT_SONNET_MODEL` and `ANTHROPIC_DEFAULT_HAIKU_MODEL`. For current and legacy model IDs across all providers, see [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview). To upgrade users to a new model version, update these environment variables and redeploy.

215 216 

217To enable [extended context](#extended-context) for a pinned model, append `[1m]` to the model ID in `ANTHROPIC_DEFAULT_OPUS_MODEL` or `ANTHROPIC_DEFAULT_SONNET_MODEL`:

218 

219```bash theme={null}

220export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-6[1m]'

221```

222 

223The `[1m]` suffix applies the 1M context window to all usage of that alias, including `opusplan`. Claude Code strips the suffix before sending the model ID to your provider. Only append `[1m]` when the underlying model supports 1M context, such as Opus 4.6 or Sonnet 4.6.

224 

216<Note>225<Note>

217 The `settings.availableModels` allowlist still applies when using third-party providers. Filtering matches on the model alias (`opus`, `sonnet`, `haiku`), not the provider-specific model ID.226 The `settings.availableModels` allowlist still applies when using third-party providers. Filtering matches on the model alias (`opus`, `sonnet`, `haiku`), not the provider-specific model ID.

218</Note>227</Note>

86 86 

87Ensure these URLs are allowlisted in your proxy configuration and firewall rules. This is especially important when using Claude Code in containerized or restricted network environments.87Ensure these URLs are allowlisted in your proxy configuration and firewall rules. This is especially important when using Claude Code in containerized or restricted network environments.

88 88 

89[Claude Code on the web](/en/claude-code-on-the-web) and [Code Review](/en/code-review) connect to your repositories from Anthropic-managed infrastructure. If your GitHub Enterprise Cloud organization restricts access by IP address, enable [IP allow list inheritance for installed GitHub Apps](https://docs.github.com/en/enterprise-cloud@latest/organizations/keeping-your-organization-secure/managing-security-settings-for-your-organization/managing-allowed-ip-addresses-for-your-organization#allowing-access-by-github-apps). The Claude GitHub App registers its IP ranges, so enabling this setting allows access without manual configuration. To [add the ranges to your allow list manually](https://docs.github.com/en/enterprise-cloud@latest/organizations/keeping-your-organization-secure/managing-security-settings-for-your-organization/managing-allowed-ip-addresses-for-your-organization#adding-an-allowed-ip-address) instead, or to configure other firewalls, see the [Anthropic API IP addresses](https://platform.claude.com/docs/en/api/ip-addresses).

90 

89## Additional resources91## Additional resources

90 92 

91* [Claude Code settings](/en/settings)93* [Claude Code settings](/en/settings)

92* [Environment variables reference](/en/settings#environment-variables)94* [Environment variables reference](/en/env-vars)

93* [Troubleshooting guide](/en/troubleshooting)95* [Troubleshooting guide](/en/troubleshooting)

36 36 

37## Start a Remote Control session37## Start a Remote Control session

38 38 

39You can start a new session directly in Remote Control, or connect a session that's already running.39You can start a dedicated Remote Control server, start an interactive session with Remote Control enabled, or connect a session that's already running.

40 40 

41<Tabs>41<Tabs>

42 <Tab title="New session">42 <Tab title="Server mode">

43 Navigate to your project directory and run:43 Navigate to your project directory and run:

44 44 

45 ```bash theme={null}45 ```bash theme={null}

46 claude remote-control46 claude remote-control

47 ```47 ```

48 48 

49 The process stays running in your terminal, waiting for remote connections. It displays a session URL you can use to [connect from another device](#connect-from-another-device), and you can press spacebar to show a QR code for quick access from your phone. While a remote session is active, the terminal shows connection status and tool activity.49 The process stays running in your terminal in server mode, waiting for remote connections. It displays a session URL you can use to [connect from another device](#connect-from-another-device), and you can press spacebar to show a QR code for quick access from your phone. While a remote session is active, the terminal shows connection status and tool activity.

50 50 

51 This command supports the following flags:51 Available flags:

52 52 

53 * **`--name "My Project"`**: set a custom session title visible in the session list at claude.ai/code. You can also pass the name as a positional argument: `claude remote-control "My Project"`53 | Flag | Description |

54 * **`--verbose`**: show detailed connection and session logs54 | ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

55 * **`--sandbox`** / **`--no-sandbox`**: enable or disable [sandboxing](/en/sandboxing) for filesystem and network isolation during the session. Sandboxing is off by default.55 | `--name "My Project"` | Set a custom session title visible in the session list at claude.ai/code. |

56 | `--spawn <mode>` | How concurrent sessions are created. Press `w` at runtime to toggle.<br />• `same-dir` (default): all sessions share the current working directory, so they can conflict if editing the same files.<br />• `worktree`: each on-demand session gets its own [git worktree](/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees). Requires a git repository. |

57 | `--capacity <N>` | Maximum number of concurrent sessions. Default is 32. |

58 | `--verbose` | Show detailed connection and session logs. |

59 | `--sandbox` / `--no-sandbox` | Enable or disable [sandboxing](/en/sandboxing) for filesystem and network isolation. Off by default. |

60 </Tab>

61 

62 <Tab title="Interactive session">

63 To start a normal interactive Claude Code session with Remote Control enabled, use the `--remote-control` flag (or `--rc`):

64 

65 ```bash theme={null}

66 claude --remote-control

67 ```

68 

69 Optionally pass a name for the session:

70 

71 ```bash theme={null}

72 claude --remote-control "My Project"

73 ```

74 

75 This gives you a full interactive session in your terminal that you can also control from claude.ai or the Claude app. Unlike `claude remote-control` (server mode), you can type messages locally while the session is also available remotely.

56 </Tab>76 </Tab>

57 77 

58 <Tab title="From an existing session">78 <Tab title="From an existing session">

86 106 

87### Enable Remote Control for all sessions107### Enable Remote Control for all sessions

88 108 

89By default, Remote Control only activates when you explicitly run `claude remote-control` or `/remote-control`. To enable it automatically for every session, run `/config` inside Claude Code and set **Enable Remote Control for all sessions** to `true`. Set it back to `false` to disable.109By default, Remote Control only activates when you explicitly run `claude remote-control`, `claude --remote-control`, or `/remote-control`. To enable it automatically for every interactive session, run `/config` inside Claude Code and set **Enable Remote Control for all sessions** to `true`. Set it back to `false` to disable.

90 110 

91Each Claude Code instance supports one remote session at a time. If you run multiple instances, each one gets its own environment and session.111With this setting on, each interactive Claude Code process registers one remote session. If you run multiple instances, each one gets its own environment and session. To run multiple concurrent sessions from a single process, use server mode with `--spawn` instead.

92 112 

93## Connection and security113## Connection and security

94 114 

104 124 

105## Limitations125## Limitations

106 126 

107* **One remote session at a time**: each Claude Code session supports one remote connection.127* **One remote session per interactive process**: outside of server mode, each Claude Code instance supports one remote session at a time. Use server mode with `--spawn` to run multiple concurrent sessions from a single process.

108* **Terminal must stay open**: Remote Control runs as a local process. If you close the terminal or stop the `claude` process, the session ends. Run `claude remote-control` again to start a new one.128* **Terminal must stay open**: Remote Control runs as a local process. If you close the terminal or stop the `claude` process, the session ends. Run `claude remote-control` again to start a new one.

109* **Extended network outage**: if your machine is awake but unable to reach the network for more than roughly 10 minutes, the session times out and the process exits. Run `claude remote-control` again to start a new session.129* **Extended network outage**: if your machine is awake but unable to reach the network for more than roughly 10 minutes, the session times out and the process exits. Run `claude remote-control` again to start a new session.

110 130 

120 120 

121## Disable scheduled tasks121## Disable scheduled tasks

122 122 

123Set `CLAUDE_CODE_DISABLE_CRON=1` in your environment to disable the scheduler entirely. The cron tools and `/loop` become unavailable, and any already-scheduled tasks stop firing. See [Environment variables](/en/settings#environment-variables) for the full list of disable flags.123Set `CLAUDE_CODE_DISABLE_CRON=1` in your environment to disable the scheduler entirely. The cron tools and `/loop` become unavailable, and any already-scheduled tasks stop firing. See [Environment variables](/en/env-vars) for the full list of disable flags.

124 124 

125## Limitations125## Limitations

126 126 

66| Feature | User location | Project location | Local location |66| Feature | User location | Project location | Local location |

67| :-------------- | :------------------------ | :--------------------------------- | :----------------------------- |67| :-------------- | :------------------------ | :--------------------------------- | :----------------------------- |

68| **Settings** | `~/.claude/settings.json` | `.claude/settings.json` | `.claude/settings.local.json` |68| **Settings** | `~/.claude/settings.json` | `.claude/settings.json` | `.claude/settings.local.json` |

69| **Subagents** | `~/.claude/agents/` | `.claude/agents/` | — |69| **Subagents** | `~/.claude/agents/` | `.claude/agents/` | None |

70| **MCP servers** | `~/.claude.json` | `.mcp.json` | `~/.claude.json` (per-project) |70| **MCP servers** | `~/.claude.json` | `.mcp.json` | `~/.claude.json` (per-project) |

71| **Plugins** | `~/.claude/settings.json` | `.claude/settings.json` | `.claude/settings.local.json` |71| **Plugins** | `~/.claude/settings.json` | `.claude/settings.json` | `.claude/settings.local.json` |

72| **CLAUDE.md** | `~/.claude/CLAUDE.md` | `CLAUDE.md` or `.claude/CLAUDE.md` | — |72| **CLAUDE.md** | `~/.claude/CLAUDE.md` | `CLAUDE.md` or `.claude/CLAUDE.md` | None |

73 73 

74***74***

75 75 

76## Settings files76## Settings files

77 77 

78The `settings.json` file is our official mechanism for configuring Claude78The `settings.json` file is the official mechanism for configuring Claude

79Code through hierarchical settings:79Code through hierarchical settings:

80 80 

81* **User settings** are defined in `~/.claude/settings.json` and apply to all81* **User settings** are defined in `~/.claude/settings.json` and apply to all

95 * Linux and WSL: `/etc/claude-code/`96 * Linux and WSL: `/etc/claude-code/`

96 * Windows: `C:\Program Files\ClaudeCode\`97 * Windows: `C:\Program Files\ClaudeCode\`

97 98 

99 <Warning>

100 The legacy Windows path `C:\ProgramData\ClaudeCode\managed-settings.json` is no longer supported as of v2.1.75. Administrators who deployed settings to that location must migrate files to `C:\Program Files\ClaudeCode\managed-settings.json`.

101 </Warning>

102 

98 See [managed settings](/en/permissions#managed-only-settings) and [Managed MCP configuration](/en/mcp#managed-mcp-configuration) for details.103 See [managed settings](/en/permissions#managed-only-settings) and [Managed MCP configuration](/en/mcp#managed-mcp-configuration) for details.

99 104 

100 <Note>105 <Note>

797 802 

798## Environment variables803## Environment variables

799 804 

800Claude Code supports the following environment variables to control its behavior:805Environment variables let you control Claude Code behavior without editing settings files. Any variable can also be configured in [`settings.json`](#available-settings) under the `env` key to apply it to every session or roll it out to your team.

801 

802<Note>

803 All environment variables can also be configured in [`settings.json`](#available-settings). This is useful as a way to automatically set environment variables for each session, or to roll out a set of environment variables for your whole team or organization.

804</Note>

805 806 

806| Variable | Purpose | |807See the [environment variables reference](/en/env-vars) for the full list.

807| :--------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --- |

808| `ANTHROPIC_API_KEY` | API key sent as `X-Api-Key` header, typically for the Claude SDK (for interactive usage, run `/login`) | |

809| `ANTHROPIC_AUTH_TOKEN` | Custom value for the `Authorization` header (the value you set here will be prefixed with `Bearer `) | |

810| `ANTHROPIC_CUSTOM_HEADERS` | Custom headers to add to requests (`Name: Value` format, newline-separated for multiple headers) | |

811| `ANTHROPIC_DEFAULT_HAIKU_MODEL` | See [Model configuration](/en/model-config#environment-variables) | |

812| `ANTHROPIC_DEFAULT_OPUS_MODEL` | See [Model configuration](/en/model-config#environment-variables) | |

813| `ANTHROPIC_DEFAULT_SONNET_MODEL` | See [Model configuration](/en/model-config#environment-variables) | |

814| `ANTHROPIC_FOUNDRY_API_KEY` | API key for Microsoft Foundry authentication (see [Microsoft Foundry](/en/microsoft-foundry)) | |

815| `ANTHROPIC_FOUNDRY_BASE_URL` | Full base URL for the Foundry resource (for example, `https://my-resource.services.ai.azure.com/anthropic`). Alternative to `ANTHROPIC_FOUNDRY_RESOURCE` (see [Microsoft Foundry](/en/microsoft-foundry)) | |

816| `ANTHROPIC_FOUNDRY_RESOURCE` | Foundry resource name (for example, `my-resource`). Required if `ANTHROPIC_FOUNDRY_BASE_URL` is not set (see [Microsoft Foundry](/en/microsoft-foundry)) | |

817| `ANTHROPIC_MODEL` | Name of the model setting to use (see [Model Configuration](/en/model-config#environment-variables)) | |

818| `ANTHROPIC_SMALL_FAST_MODEL` | \[DEPRECATED] Name of [Haiku-class model for background tasks](/en/costs) | |

819| `ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION` | Override AWS region for the Haiku-class model when using Bedrock | |

820| `AWS_BEARER_TOKEN_BEDROCK` | Bedrock API key for authentication (see [Bedrock API keys](https://aws.amazon.com/blogs/machine-learning/accelerate-ai-development-with-amazon-bedrock-api-keys/)) | |

821| `BASH_DEFAULT_TIMEOUT_MS` | Default timeout for long-running bash commands | |

822| `BASH_MAX_OUTPUT_LENGTH` | Maximum number of characters in bash outputs before they are middle-truncated | |

823| `BASH_MAX_TIMEOUT_MS` | Maximum timeout the model can set for long-running bash commands | |

824| `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` | Set the percentage of context capacity (1-100) at which auto-compaction triggers. By default, auto-compaction triggers at approximately 95% capacity. Use lower values like `50` to compact earlier. Values above the default threshold have no effect. Applies to both main conversations and subagents. This percentage aligns with the `context_window.used_percentage` field available in [status line](/en/statusline) | |

825| `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR` | Return to the original working directory after each Bash command | |

826| `CLAUDE_CODE_ACCOUNT_UUID` | Account UUID for the authenticated user. Used by SDK callers to provide account information synchronously, avoiding a race condition where early telemetry events lack account metadata. Requires `CLAUDE_CODE_USER_EMAIL` and `CLAUDE_CODE_ORGANIZATION_UUID` to also be set | |

827| `CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD` | Set to `1` to load CLAUDE.md files from directories specified with `--add-dir`. By default, additional directories do not load memory files | `1` |

828| `CLAUDE_CODE_API_KEY_HELPER_TTL_MS` | Interval in milliseconds at which credentials should be refreshed (when using `apiKeyHelper`) | |

829| `CLAUDE_CODE_CLIENT_CERT` | Path to client certificate file for mTLS authentication | |

830| `CLAUDE_CODE_CLIENT_KEY` | Path to client private key file for mTLS authentication | |

831| `CLAUDE_CODE_CLIENT_KEY_PASSPHRASE` | Passphrase for encrypted CLAUDE\_CODE\_CLIENT\_KEY (optional) | |

832| `CLAUDE_CODE_DISABLE_1M_CONTEXT` | Set to `1` to disable [1M context window](/en/model-config#extended-context) support. When set, 1M model variants are unavailable in the model picker. Useful for enterprise environments with compliance requirements | |

833| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/en/model-config#adjust-effort-level) for Opus 4.6 and Sonnet 4.6. When disabled, these models fall back to the fixed thinking budget controlled by `MAX_THINKING_TOKENS` | |

834| `CLAUDE_CODE_DISABLE_AUTO_MEMORY` | Set to `1` to disable [auto memory](/en/memory#auto-memory). Set to `0` to force auto memory on during the gradual rollout. When disabled, Claude does not create or load auto memory files | |

835| `CLAUDE_CODE_DISABLE_GIT_INSTRUCTIONS` | Set to `1` to remove built-in commit and PR workflow instructions from Claude's system prompt. Useful when using your own git workflow skills. Takes precedence over the [`includeGitInstructions`](#available-settings) setting when set | |

836| `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` | Set to `1` to disable all background task functionality, including the `run_in_background` parameter on Bash and subagent tools, auto-backgrounding, and the Ctrl+B shortcut | |

837| `CLAUDE_CODE_DISABLE_CRON` | Set to `1` to disable [scheduled tasks](/en/scheduled-tasks). The `/loop` skill and cron tools become unavailable and any already-scheduled tasks stop firing, including tasks that are already running mid-session | |

838| `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` | Set to `1` to disable Anthropic API-specific `anthropic-beta` headers. Use this if experiencing issues like "Unexpected value(s) for the `anthropic-beta` header" when using an LLM gateway with third-party providers | |

839| `CLAUDE_CODE_DISABLE_FAST_MODE` | Set to `1` to disable [fast mode](/en/fast-mode) | |

840| `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` | Set to `1` to disable the "How is Claude doing?" session quality surveys. Also disabled when using third-party providers or when telemetry is disabled. See [Session quality surveys](/en/data-usage#session-quality-surveys) | |

841| `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` | Equivalent of setting `DISABLE_AUTOUPDATER`, `DISABLE_BUG_COMMAND`, `DISABLE_ERROR_REPORTING`, and `DISABLE_TELEMETRY` | |

842| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Set to `1` to disable automatic terminal title updates based on conversation context | |

843| `CLAUDE_CODE_EFFORT_LEVEL` | Set the effort level for supported models. Values: `low`, `medium`, `high`. Lower effort is faster and cheaper, higher effort provides deeper reasoning. Supported on Opus 4.6 and Sonnet 4.6. See [Adjust effort level](/en/model-config#adjust-effort-level) | |

844| `CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION` | Set to `false` to disable prompt suggestions (the "Prompt suggestions" toggle in `/config`). These are the grayed-out predictions that appear in your prompt input after Claude responds. See [Prompt suggestions](/en/interactive-mode#prompt-suggestions) | |

845| `CLAUDE_CODE_ENABLE_TASKS` | Set to `true` to enable the task tracking system in non-interactive mode (the `-p` flag). Tasks are on by default in interactive mode. See [Task list](/en/interactive-mode#task-list) | |

846| `CLAUDE_CODE_ENABLE_TELEMETRY` | Set to `1` to enable OpenTelemetry data collection for metrics and logging. Required before configuring OTel exporters. See [Monitoring](/en/monitoring-usage) | |

847| `CLAUDE_CODE_EXIT_AFTER_STOP_DELAY` | Time in milliseconds to wait after the query loop becomes idle before automatically exiting. Useful for automated workflows and scripts using SDK mode | |

848| `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` | Set to `1` to enable [agent teams](/en/agent-teams). Agent teams are experimental and disabled by default | |

849| `CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS` | Override the default token limit for file reads. Useful when you need to read larger files in full | |

850| `CLAUDE_CODE_HIDE_ACCOUNT_INFO` | Set to `1` to hide your email address and organization name from the Claude Code UI. Useful when streaming or recording | |

851| `CLAUDE_CODE_IDE_SKIP_AUTO_INSTALL` | Skip auto-installation of IDE extensions | |

852| `CLAUDE_CODE_MAX_OUTPUT_TOKENS` | Set the maximum number of output tokens for most requests. Default: 32,000. Maximum: 64,000. Increasing this value reduces the effective context window available before [auto-compaction](/en/costs#reduce-token-usage) triggers. | |

853| `CLAUDE_CODE_ORGANIZATION_UUID` | Organization UUID for the authenticated user. Used by SDK callers to provide account information synchronously. Requires `CLAUDE_CODE_ACCOUNT_UUID` and `CLAUDE_CODE_USER_EMAIL` to also be set | |

854| `CLAUDE_CODE_OTEL_HEADERS_HELPER_DEBOUNCE_MS` | Interval for refreshing dynamic OpenTelemetry headers in milliseconds (default: 1740000 / 29 minutes). See [Dynamic headers](/en/monitoring-usage#dynamic-headers) | |

855| `CLAUDE_CODE_PLAN_MODE_REQUIRED` | Auto-set to `true` on [agent team](/en/agent-teams) teammates that require plan approval. Read-only: set by Claude Code when spawning teammates. See [require plan approval](/en/agent-teams#require-plan-approval-for-teammates) | |

856| `CLAUDE_CODE_PLUGIN_GIT_TIMEOUT_MS` | Timeout in milliseconds for git operations when installing or updating plugins (default: 120000). Increase this value for large repositories or slow network connections. See [Git operations time out](/en/plugin-marketplaces#git-operations-time-out) | |

857| `CLAUDE_CODE_PROXY_RESOLVES_HOSTS` | Set to `true` to allow the proxy to perform DNS resolution instead of the caller. Opt-in for environments where the proxy should handle hostname resolution | |

858| `CLAUDE_CODE_SESSIONEND_HOOKS_TIMEOUT_MS` | Maximum time in milliseconds for [SessionEnd](/en/hooks#sessionend) hooks to complete (default: `1500`). Applies to both session exit and `/clear`. Per-hook `timeout` values are also capped by this budget | |

859| `CLAUDE_CODE_SHELL` | Override automatic shell detection. Useful when your login shell differs from your preferred working shell (for example, `bash` vs `zsh`) | |

860| `CLAUDE_CODE_SHELL_PREFIX` | Command prefix to wrap all bash commands (for example, for logging or auditing). Example: `/path/to/logger.sh` will execute `/path/to/logger.sh <command>` | |

861| `CLAUDE_CODE_SIMPLE` | Set to `1` to run with a minimal system prompt and only the Bash, file read, and file edit tools. Disables MCP tools, attachments, hooks, and CLAUDE.md files | |

862| `CLAUDE_CODE_SKIP_BEDROCK_AUTH` | Skip AWS authentication for Bedrock (for example, when using an LLM gateway) | |

863| `CLAUDE_CODE_SKIP_FOUNDRY_AUTH` | Skip Azure authentication for Microsoft Foundry (for example, when using an LLM gateway) | |

864| `CLAUDE_CODE_SKIP_VERTEX_AUTH` | Skip Google authentication for Vertex (for example, when using an LLM gateway) | |

865| `CLAUDE_CODE_SUBAGENT_MODEL` | See [Model configuration](/en/model-config) | |

866| `CLAUDE_CODE_TASK_LIST_ID` | Share a task list across sessions. Set the same ID in multiple Claude Code instances to coordinate on a shared task list. See [Task list](/en/interactive-mode#task-list) | |

867| `CLAUDE_CODE_TEAM_NAME` | Name of the agent team this teammate belongs to. Set automatically on [agent team](/en/agent-teams) members | |

868| `CLAUDE_CODE_TMPDIR` | Override the temp directory used for internal temp files. Claude Code appends `/claude/` to this path. Default: `/tmp` on Unix/macOS, `os.tmpdir()` on Windows | |

869| `CLAUDE_CODE_USER_EMAIL` | Email address for the authenticated user. Used by SDK callers to provide account information synchronously. Requires `CLAUDE_CODE_ACCOUNT_UUID` and `CLAUDE_CODE_ORGANIZATION_UUID` to also be set | |

870| `CLAUDE_CODE_USE_BEDROCK` | Use [Bedrock](/en/amazon-bedrock) | |

871| `CLAUDE_CODE_USE_FOUNDRY` | Use [Microsoft Foundry](/en/microsoft-foundry) | |

872| `CLAUDE_CODE_USE_VERTEX` | Use [Vertex](/en/google-vertex-ai) | |

873| `CLAUDE_CONFIG_DIR` | Customize where Claude Code stores its configuration and data files | |

874| `DISABLE_AUTOUPDATER` | Set to `1` to disable automatic updates. | |

875| `DISABLE_BUG_COMMAND` | Set to `1` to disable the `/bug` command | |

876| `DISABLE_COST_WARNINGS` | Set to `1` to disable cost warning messages | |

877| `DISABLE_ERROR_REPORTING` | Set to `1` to opt out of Sentry error reporting | |

878| `DISABLE_INSTALLATION_CHECKS` | Set to `1` to disable installation warnings. Use only when manually managing the installation location, as this can mask issues with standard installations | |

879| `DISABLE_NON_ESSENTIAL_MODEL_CALLS` | Set to `1` to disable model calls for non-critical paths like flavor text | |

880| `DISABLE_PROMPT_CACHING` | Set to `1` to disable prompt caching for all models (takes precedence over per-model settings) | |

881| `DISABLE_PROMPT_CACHING_HAIKU` | Set to `1` to disable prompt caching for Haiku models | |

882| `DISABLE_PROMPT_CACHING_OPUS` | Set to `1` to disable prompt caching for Opus models | |

883| `DISABLE_PROMPT_CACHING_SONNET` | Set to `1` to disable prompt caching for Sonnet models | |

884| `DISABLE_TELEMETRY` | Set to `1` to opt out of Statsig telemetry (note that Statsig events do not include user data like code, file paths, or bash commands) | |

885| `ENABLE_CLAUDEAI_MCP_SERVERS` | Set to `false` to disable [claude.ai MCP servers](/en/mcp#use-mcp-servers-from-claudeai) in Claude Code. Enabled by default for logged-in users | |

886| `ENABLE_TOOL_SEARCH` | Controls [MCP tool search](/en/mcp#scale-with-mcp-tool-search). Unset: enabled by default, but disabled when `ANTHROPIC_BASE_URL` points to a non-first-party host. Values: `true` (always on including proxies), `auto` (enables at 10% context), `auto:N` (custom threshold, e.g., `auto:5` for 5%), `false` (disabled) | |

887| `FORCE_AUTOUPDATE_PLUGINS` | Set to `true` to force plugin auto-updates even when the main auto-updater is disabled via `DISABLE_AUTOUPDATER` | |

888| `HTTP_PROXY` | Specify HTTP proxy server for network connections | |

889| `HTTPS_PROXY` | Specify HTTPS proxy server for network connections | |

890| `IS_DEMO` | Set to `true` to enable demo mode: hides email and organization from the UI, skips onboarding, and hides internal commands. Useful for streaming or recording sessions | |

891| `MAX_MCP_OUTPUT_TOKENS` | Maximum number of tokens allowed in MCP tool responses. Claude Code displays a warning when output exceeds 10,000 tokens (default: 25000) | |

892| `MAX_THINKING_TOKENS` | Override the [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) token budget. Thinking is enabled at max budget (31,999 tokens) by default. Use this to limit the budget (for example, `MAX_THINKING_TOKENS=10000`) or disable thinking entirely (`MAX_THINKING_TOKENS=0`). For Opus 4.6, thinking depth is controlled by [effort level](/en/model-config#adjust-effort-level) instead, and this variable is ignored unless set to `0` to disable thinking. | |

893| `MCP_CLIENT_SECRET` | OAuth client secret for MCP servers that require [pre-configured credentials](/en/mcp#use-pre-configured-oauth-credentials). Avoids the interactive prompt when adding a server with `--client-secret` | |

894| `MCP_OAUTH_CALLBACK_PORT` | Fixed port for the OAuth redirect callback, as an alternative to `--callback-port` when adding an MCP server with [pre-configured credentials](/en/mcp#use-pre-configured-oauth-credentials) | |

895| `MCP_TIMEOUT` | Timeout in milliseconds for MCP server startup | |

896| `MCP_TOOL_TIMEOUT` | Timeout in milliseconds for MCP tool execution | |

897| `NO_PROXY` | List of domains and IPs to which requests will be directly issued, bypassing proxy | |

898| `SLASH_COMMAND_TOOL_CHAR_BUDGET` | Override the character budget for skill metadata shown to the [Skill tool](/en/skills#control-who-invokes-a-skill). The budget scales dynamically at 2% of the context window, with a fallback of 16,000 characters. Legacy name kept for backwards compatibility | |

899| `USE_BUILTIN_RIPGREP` | Set to `0` to use system-installed `rg` instead of `rg` included with Claude Code | |

900| `VERTEX_REGION_CLAUDE_3_5_HAIKU` | Override region for Claude 3.5 Haiku when using Vertex AI | |

901| `VERTEX_REGION_CLAUDE_3_7_SONNET` | Override region for Claude 3.7 Sonnet when using Vertex AI | |

902| `VERTEX_REGION_CLAUDE_4_0_OPUS` | Override region for Claude 4.0 Opus when using Vertex AI | |

903| `VERTEX_REGION_CLAUDE_4_0_SONNET` | Override region for Claude 4.0 Sonnet when using Vertex AI | |

904| `VERTEX_REGION_CLAUDE_4_1_OPUS` | Override region for Claude 4.1 Opus when using Vertex AI | |

905 808 

906## Tools available to Claude809## Tools available to Claude

907 810 

908Claude Code has access to a set of powerful tools that help it understand and modify your codebase:811Claude Code has access to a set of tools for reading, editing, searching, running commands, and orchestrating subagents. Tool names are the exact strings you use in permission rules and hook matchers.

909 

910| Tool | Description | Permission Required |

911| :----------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------ |

912| **Agent** | Spawns a [subagent](/en/sub-agents) with its own context window to handle a task | No |

913| **AskUserQuestion** | Asks multiple-choice questions to gather requirements or clarify ambiguity | No |

914| **Bash** | Executes shell commands in your environment. See [Bash tool behavior](#bash-tool-behavior) | Yes |

915| **CronCreate** | Schedules a recurring or one-shot prompt within the current session (gone when Claude exits). See [scheduled tasks](/en/scheduled-tasks) | No |

916| **CronDelete** | Cancels a scheduled task by ID | No |

917| **CronList** | Lists all scheduled tasks in the session | No |

918| **Edit** | Makes targeted edits to specific files | Yes |

919| **EnterPlanMode** | Switches to plan mode to design an approach before coding | No |

920| **EnterWorktree** | Creates an isolated [git worktree](/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees) and switches into it | No |

921| **ExitPlanMode** | Presents a plan for approval and exits plan mode | Yes |

922| **ExitWorktree** | Exits a worktree session and returns to the original directory | No |

923| **Glob** | Finds files based on pattern matching | No |

924| **Grep** | Searches for patterns in file contents | No |

925| **ListMcpResourcesTool** | Lists resources exposed by connected [MCP servers](/en/mcp) | No |

926| **LSP** | Code intelligence via language servers. Reports type errors and warnings automatically after file edits. Also supports navigation operations: jump to definitions, find references, get type info, list symbols, find implementations, trace call hierarchies. Requires a [code intelligence plugin](/en/discover-plugins#code-intelligence) and its language server binary | No |

927| **NotebookEdit** | Modifies Jupyter notebook cells | Yes |

928| **Read** | Reads the contents of files | No |

929| **ReadMcpResourceTool** | Reads a specific MCP resource by URI | No |

930| **Skill** | Executes a [skill](/en/skills#control-who-invokes-a-skill) within the main conversation | Yes |

931| **TaskCreate** | Creates a new task in the task list | No |

932| **TaskGet** | Retrieves full details for a specific task | No |

933| **TaskList** | Lists all tasks with their current status | No |

934| **TaskOutput** | Retrieves output from a background task | No |

935| **TaskStop** | Kills a running background task by ID | No |

936| **TaskUpdate** | Updates task status, dependencies, details, or deletes tasks | No |

937| **TodoWrite** | Manages the session task checklist. Available in non-interactive mode and the [Agent SDK](/en/headless); interactive sessions use TaskCreate, TaskGet, TaskList, and TaskUpdate instead | No |

938| **ToolSearch** | Searches for and loads deferred tools when [tool search](/en/mcp#scale-with-mcp-tool-search) is enabled | No |

939| **WebFetch** | Fetches content from a specified URL | Yes |

940| **WebSearch** | Performs web searches | Yes |

941| **Write** | Creates or overwrites files | Yes |

942 

943Permission rules can be configured using `/allowed-tools` or in [permission settings](/en/settings#available-settings). Also see [Tool-specific permission rules](/en/permissions#tool-specific-permission-rules).

944 

945### Bash tool behavior

946 

947The Bash tool executes shell commands with the following persistence behavior:

948 

949* **Working directory persists**: When Claude changes the working directory (for example, `cd /path/to/dir`), subsequent Bash commands will execute in that directory. You can use `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR=1` to reset to the project directory after each command.

950* **Environment variables do NOT persist**: Environment variables set in one Bash command (for example, `export MY_VAR=value`) are **not** available in subsequent Bash commands. Each Bash command runs in a fresh shell environment.

951 

952To make environment variables available in Bash commands, you have **three options**:

953 

954**Option 1: Activate environment before starting Claude Code** (simplest approach)

955 

956Activate your virtual environment in your terminal before launching Claude Code:

957 

958```bash theme={null}

959conda activate myenv

960# or: source /path/to/venv/bin/activate

961claude

962```

963 

964This works for shell environments but environment variables set within Claude's Bash commands will not persist between commands.

965 

966**Option 2: Set CLAUDE\_ENV\_FILE before starting Claude Code** (persistent environment setup)

967 

968Export the path to a shell script containing your environment setup:

969 

970```bash theme={null}

971export CLAUDE_ENV_FILE=/path/to/env-setup.sh

972claude

973```

974 

975Where `/path/to/env-setup.sh` contains:

976 

977```bash theme={null}

978conda activate myenv

979# or: source /path/to/venv/bin/activate

980# or: export MY_VAR=value

981```

982 

983Claude Code will source this file before each Bash command, making the environment persistent across all commands.

984 

985**Option 3: Use a SessionStart hook** (project-specific configuration)

986 

987Configure in `.claude/settings.json`:

988 

989```json theme={null}

990{

991 "hooks": {

992 "SessionStart": [{

993 "matcher": "startup",

994 "hooks": [{

995 "type": "command",

996 "command": "echo 'conda activate myenv' >> \"$CLAUDE_ENV_FILE\""

997 }]

998 }]

999 }

1000}

1001```

1002 

1003The hook writes to `$CLAUDE_ENV_FILE`, which is then sourced before each Bash command. This is ideal for team-shared project configurations.

1004 

1005See [SessionStart hooks](/en/hooks#persist-environment-variables) for more details on Option 3.

1006 

1007### Extending tools with hooks

1008 

1009You can run custom commands before or after any tool executes using

1010[Claude Code hooks](/en/hooks-guide).

1011 812 

1012For example, you could automatically run a Python formatter after Claude813See the [tools reference](/en/tools-reference) for the full list and Bash tool behavior details.

1013modifies Python files, or prevent modifications to production configuration

1014files by blocking Write operations to certain paths.

1015 814 

1016## See also815## See also

1017 816 

125apk add libgcc libstdc++ ripgrep125apk add libgcc libstdc++ ripgrep

126```126```

127 127 

128Then set `USE_BUILTIN_RIPGREP` to `0` in your [settings.json file](/en/settings#environment-variables):128Then set `USE_BUILTIN_RIPGREP` to `0` in your [`settings.json`](/en/settings#available-settings) file:

129 129 

130```json theme={null}130```json theme={null}

131{131{

190 190 

191### Disable auto-updates191### Disable auto-updates

192 192 

193Set `DISABLE_AUTOUPDATER` to `"1"` in the `env` key of your [settings.json file](/en/settings#environment-variables):193Set `DISABLE_AUTOUPDATER` to `"1"` in the `env` key of your [`settings.json`](/en/settings#available-settings) file:

194 194 

195```json theme={null}195```json theme={null}

196{196{

9Skills extend what Claude can do. Create a `SKILL.md` file with instructions, and Claude adds it to its toolkit. Claude uses skills when relevant, or you can invoke one directly with `/skill-name`.9Skills extend what Claude can do. Create a `SKILL.md` file with instructions, and Claude adds it to its toolkit. Claude uses skills when relevant, or you can invoke one directly with `/skill-name`.

10 10 

11<Note>11<Note>

12 For built-in commands like `/help` and `/compact`, see [interactive mode](/en/interactive-mode#built-in-commands).12 For built-in commands like `/help` and `/compact`, see the [built-in commands reference](/en/commands).

13 13 

14 **Custom commands have been merged into skills.** A file at `.claude/commands/deploy.md` and a skill at `.claude/skills/deploy/SKILL.md` both create `/deploy` and work the same way. Your existing `.claude/commands/` files keep working. Skills add optional features: a directory for supporting files, frontmatter to [control whether you or Claude invokes them](#control-who-invokes-a-skill), and the ability for Claude to load them automatically when relevant.14 **Custom commands have been merged into skills.** A file at `.claude/commands/deploy.md` and a skill at `.claude/skills/deploy/SKILL.md` both create `/deploy` and work the same way. Your existing `.claude/commands/` files keep working. Skills add optional features: a directory for supporting files, frontmatter to [control whether you or Claude invokes them](#control-who-invokes-a-skill), and the ability for Claude to load them automatically when relevant.

15</Note>15</Note>

18 18 

19## Bundled skills19## Bundled skills

20 20 

21Bundled skills ship with Claude Code and are available in every session. Unlike [built-in commands](/en/interactive-mode#built-in-commands), which execute fixed logic directly, bundled skills are prompt-based: they give Claude a detailed playbook and let it orchestrate the work using its tools. This means bundled skills can spawn parallel agents, read files, and adapt to your codebase.21Bundled skills ship with Claude Code and are available in every session. Unlike [built-in commands](/en/commands), which execute fixed logic directly, bundled skills are prompt-based: they give Claude a detailed playbook and let it orchestrate the work using its tools. This means bundled skills can spawn parallel agents, read files, and adapt to your codebase.

22 22 

23You invoke bundled skills the same way as any other skill: type `/` followed by the skill name.23You invoke bundled skills the same way as any other skill: type `/` followed by the skill name. In the table below, `<arg>` indicates a required argument and `[arg]` indicates an optional one.

24 24 

25* **`/simplify`**: reviews your recently changed files for code reuse, quality, and efficiency issues, then fixes them. Run it after implementing a feature or bug fix to clean up your work. It spawns three review agents in parallel (code reuse, code quality, efficiency), aggregates their findings, and applies fixes. Pass optional text to focus on specific concerns: `/simplify focus on memory efficiency`.25| Skill | Purpose |

26 26| :-------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

27* **`/batch <instruction>`**: orchestrates large-scale changes across a codebase in parallel. Provide a description of the change and `/batch` researches the codebase, decomposes the work into 5 to 30 independent units, and presents a plan for your approval. Once approved, it spawns one background agent per unit, each in an isolated [git worktree](/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees). Each agent implements its unit, runs tests, and opens a pull request. Requires a git repository. Example: `/batch migrate src/ from Solid to React`.27| `/batch <instruction>` | Orchestrate large-scale changes across a codebase in parallel. Researches the codebase, decomposes the work into 5 to 30 independent units, and presents a plan. Once approved, spawns one background agent per unit in an isolated [git worktree](/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees). Each agent implements its unit, runs tests, and opens a pull request. Requires a git repository. Example: `/batch migrate src/ from Solid to React` |

28 28| `/claude-api` | Load Claude API reference material for your project's language (Python, TypeScript, Java, Go, Ruby, C#, PHP, or cURL) and Agent SDK reference for Python and TypeScript. Covers tool use, streaming, batches, structured outputs, and common pitfalls. Also activates automatically when your code imports `anthropic`, `@anthropic-ai/sdk`, or `claude_agent_sdk` |

29* **`/debug [description]`**: troubleshoots your current Claude Code session by reading the session debug log. Optionally describe the issue to focus the analysis.29| `/debug [description]` | Troubleshoot your current Claude Code session by reading the session debug log. Optionally describe the issue to focus the analysis |

30 30| `/loop [interval] <prompt>` | Run a prompt repeatedly on an interval while the session stays open. Useful for polling a deployment, babysitting a PR, or periodically re-running another skill. Example: `/loop 5m check if the deploy finished`. See [Run prompts on a schedule](/en/scheduled-tasks) |

31* **`/loop [interval] <prompt>`**: runs a prompt repeatedly on an interval while the session stays open. Claude parses the interval, schedules a recurring cron task, and confirms the cadence. Useful for polling a deployment, babysitting a PR, or periodically re-running another skill. Example: `/loop 5m check if the deploy finished`. See [Run prompts on a schedule](/en/scheduled-tasks).31| `/simplify [focus]` | Review your recently changed files for code reuse, quality, and efficiency issues, then fix them. Spawns three review agents in parallel, aggregates their findings, and applies fixes. Pass text to focus on specific concerns: `/simplify focus on memory efficiency` |

32 

33* **`/claude-api`**: loads Claude API reference material for your project's language (Python, TypeScript, Java, Go, Ruby, C#, PHP, or cURL) and Agent SDK reference for Python and TypeScript. Covers tool use, streaming, batches, structured outputs, and common pitfalls. Also activates automatically when your code imports `anthropic`, `@anthropic-ai/sdk`, or `claude_agent_sdk`.

34 32 

35## Getting started33## Getting started

36 34 

691* **[Plugins](/en/plugins)**: package and distribute skills with other extensions689* **[Plugins](/en/plugins)**: package and distribute skills with other extensions

692* **[Hooks](/en/hooks)**: automate workflows around tool events690* **[Hooks](/en/hooks)**: automate workflows around tool events

693* **[Memory](/en/memory)**: manage CLAUDE.md files for persistent context691* **[Memory](/en/memory)**: manage CLAUDE.md files for persistent context

694* **[Interactive mode](/en/interactive-mode#built-in-commands)**: built-in commands and shortcuts692* **[Built-in commands](/en/commands)**: reference for built-in `/` commands

695* **[Permissions](/en/permissions)**: control tool and skill access693* **[Permissions](/en/permissions)**: control tool and skill access

163 163 

164**User subagents** (`~/.claude/agents/`) are personal subagents available in all your projects.164**User subagents** (`~/.claude/agents/`) are personal subagents available in all your projects.

165 165 

166**CLI-defined subagents** are passed as JSON when launching Claude Code. They exist only for that session and aren't saved to disk, making them useful for quick testing or automation scripts:166**CLI-defined subagents** are passed as JSON when launching Claude Code. They exist only for that session and aren't saved to disk, making them useful for quick testing or automation scripts. You can define multiple subagents in a single `--agents` call:

167 167 

168```bash theme={null}168```bash theme={null}

169claude --agents '{169claude --agents '{

172 "prompt": "You are a senior code reviewer. Focus on code quality, security, and best practices.",172 "prompt": "You are a senior code reviewer. Focus on code quality, security, and best practices.",

173 "tools": ["Read", "Grep", "Glob", "Bash"],173 "tools": ["Read", "Grep", "Glob", "Bash"],

174 "model": "sonnet"174 "model": "sonnet"

175 },

176 "debugger": {

177 "description": "Debugging specialist for errors and test failures.",

178 "prompt": "You are an expert debugger. Analyze errors, identify root causes, and provide fixes."

175 }179 }

176}'180}'

177```181```

178 182 

179The `--agents` flag accepts JSON with the same [frontmatter](#supported-frontmatter-fields) fields as file-based subagents: `description`, `prompt`, `tools`, `disallowedTools`, `model`, `permissionMode`, `mcpServers`, `hooks`, `maxTurns`, `skills`, and `memory`. Use `prompt` for the system prompt, equivalent to the markdown body in file-based subagents. See the [CLI reference](/en/cli-reference#agents-flag-format) for the full JSON format.183The `--agents` flag accepts JSON with the same [frontmatter](#supported-frontmatter-fields) fields as file-based subagents: `description`, `prompt`, `tools`, `disallowedTools`, `model`, `permissionMode`, `mcpServers`, `hooks`, `maxTurns`, `skills`, and `memory`. Use `prompt` for the system prompt, equivalent to the markdown body in file-based subagents.

180 184 

181**Plugin subagents** come from [plugins](/en/plugins) you've installed. They appear in `/agents` alongside your custom subagents. See the [plugin components reference](/en/plugins-reference#agents) for details on creating plugin subagents.185**Plugin subagents** come from [plugins](/en/plugins) you've installed. They appear in `/agents` alongside your custom subagents. See the [plugin components reference](/en/plugins-reference#agents) for details on creating plugin subagents.

182 186 

237 241 

238#### Available tools242#### Available tools

239 243 

240Subagents can use any of Claude Code's [internal tools](/en/settings#tools-available-to-claude). By default, subagents inherit all tools from the main conversation, including MCP tools.244Subagents can use any of Claude Code's [internal tools](/en/tools-reference). By default, subagents inherit all tools from the main conversation, including MCP tools.

241 245 

242To restrict tools, use the `tools` field (allowlist) or `disallowedTools` field (denylist):246To restrict tools, use the `tools` field (allowlist) or `disallowedTools` field (denylist):

243 247 

537 541 

538Subagents can run in the foreground (blocking) or background (concurrent):542Subagents can run in the foreground (blocking) or background (concurrent):

539 543 

540* **Foreground subagents** block the main conversation until complete. Permission prompts and clarifying questions (like [`AskUserQuestion`](/en/settings#tools-available-to-claude)) are passed through to you.544* **Foreground subagents** block the main conversation until complete. Permission prompts and clarifying questions (like [`AskUserQuestion`](/en/tools-reference)) are passed through to you.

541* **Background subagents** run concurrently while you continue working. Before launching, Claude Code prompts for any tool permissions the subagent will need, ensuring it has the necessary approvals upfront. Once running, the subagent inherits these permissions and auto-denies anything not pre-approved. If a background subagent needs to ask clarifying questions, that tool call fails but the subagent continues.545* **Background subagents** run concurrently while you continue working. Before launching, Claude Code prompts for any tool permissions the subagent will need, ensuring it has the necessary approvals upfront. Once running, the subagent inherits these permissions and auto-denies anything not pre-approved. If a background subagent needs to ask clarifying questions, that tool call fails but the subagent continues.

542 546 

543If a background subagent fails due to missing permissions, you can [resume it](#resume-subagents) in the foreground to retry with interactive prompts.547If a background subagent fails due to missing permissions, you can [resume it](#resume-subagents) in the foreground to retry with interactive prompts.

547* Ask Claude to "run this in the background"551* Ask Claude to "run this in the background"

548* Press **Ctrl+B** to background a running task552* Press **Ctrl+B** to background a running task

549 553 

550To disable all background task functionality, set the `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` environment variable to `1`. See [Environment variables](/en/settings#environment-variables).554To disable all background task functionality, set the `CLAUDE_CODE_DISABLE_BACKGROUND_TASKS` environment variable to `1`. See [Environment variables](/en/env-vars).

551 555 

552### Common patterns556### Common patterns

553 557 

634 638 

635#### Auto-compaction639#### Auto-compaction

636 640 

637Subagents support automatic compaction using the same logic as the main conversation. By default, auto-compaction triggers at approximately 95% capacity. To trigger compaction earlier, set `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` to a lower percentage (for example, `50`). See [environment variables](/en/settings#environment-variables) for details.641Subagents support automatic compaction using the same logic as the main conversation. By default, auto-compaction triggers at approximately 95% capacity. To trigger compaction earlier, set `CLAUDE_AUTOCOMPACT_PCT_OVERRIDE` to a lower percentage (for example, `50`). See [environment variables](/en/env-vars) for details.

638 642 

639Compaction events are logged in subagent transcript files:643Compaction events are logged in subagent transcript files:

640 644 

128 128 

129<Tabs>129<Tabs>

130 <Tab title="Corporate proxy">130 <Tab title="Corporate proxy">

131 Route Bedrock traffic through your corporate proxy by setting the following [environment variables](/en/settings#environment-variables):131 Route Bedrock traffic through your corporate proxy by setting the following [environment variables](/en/env-vars):

132 132 

133 ```bash theme={null}133 ```bash theme={null}

134 # Enable Bedrock134 # Enable Bedrock

141 </Tab>141 </Tab>

142 142 

143 <Tab title="LLM Gateway">143 <Tab title="LLM Gateway">

144 Route Bedrock traffic through your LLM gateway by setting the following [environment variables](/en/settings#environment-variables):144 Route Bedrock traffic through your LLM gateway by setting the following [environment variables](/en/env-vars):

145 145 

146 ```bash theme={null}146 ```bash theme={null}

147 # Enable Bedrock147 # Enable Bedrock

158 158 

159<Tabs>159<Tabs>

160 <Tab title="Corporate proxy">160 <Tab title="Corporate proxy">

161 Route Foundry traffic through your corporate proxy by setting the following [environment variables](/en/settings#environment-variables):161 Route Foundry traffic through your corporate proxy by setting the following [environment variables](/en/env-vars):

162 162 

163 ```bash theme={null}163 ```bash theme={null}

164 # Enable Microsoft Foundry164 # Enable Microsoft Foundry

172 </Tab>172 </Tab>

173 173 

174 <Tab title="LLM Gateway">174 <Tab title="LLM Gateway">

175 Route Foundry traffic through your LLM gateway by setting the following [environment variables](/en/settings#environment-variables):175 Route Foundry traffic through your LLM gateway by setting the following [environment variables](/en/env-vars):

176 176 

177 ```bash theme={null}177 ```bash theme={null}

178 # Enable Microsoft Foundry178 # Enable Microsoft Foundry

189 189 

190<Tabs>190<Tabs>

191 <Tab title="Corporate proxy">191 <Tab title="Corporate proxy">

192 Route Vertex AI traffic through your corporate proxy by setting the following [environment variables](/en/settings#environment-variables):192 Route Vertex AI traffic through your corporate proxy by setting the following [environment variables](/en/env-vars):

193 193 

194 ```bash theme={null}194 ```bash theme={null}

195 # Enable Vertex195 # Enable Vertex

203 </Tab>203 </Tab>

204 204 

205 <Tab title="LLM Gateway">205 <Tab title="LLM Gateway">

206 Route Vertex AI traffic through your LLM gateway by setting the following [environment variables](/en/settings#environment-variables):206 Route Vertex AI traffic through your LLM gateway by setting the following [environment variables](/en/env-vars):

207 207 

208 ```bash theme={null}208 ```bash theme={null}

209 # Enable Vertex209 # Enable Vertex

1> ## Documentation Index

2> Fetch the complete documentation index at: https://code.claude.com/docs/llms.txt

3> Use this file to discover all available pages before exploring further.

4 

5# Tools reference

6 

7> Complete reference for the tools Claude Code can use, including permission requirements.

8 

9Claude Code has access to a set of tools that help it understand and modify your codebase. The tool names below are the exact strings you use in [permission rules](/en/permissions#tool-specific-permission-rules), [subagent tool lists](/en/sub-agents), and [hook matchers](/en/hooks).

10 

11| Tool | Description | Permission Required |

12| :--------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------ |

13| `Agent` | Spawns a [subagent](/en/sub-agents) with its own context window to handle a task | No |

14| `AskUserQuestion` | Asks multiple-choice questions to gather requirements or clarify ambiguity | No |

15| `Bash` | Executes shell commands in your environment. See [Bash tool behavior](#bash-tool-behavior) | Yes |

16| `CronCreate` | Schedules a recurring or one-shot prompt within the current session (gone when Claude exits). See [scheduled tasks](/en/scheduled-tasks) | No |

17| `CronDelete` | Cancels a scheduled task by ID | No |

18| `CronList` | Lists all scheduled tasks in the session | No |

19| `Edit` | Makes targeted edits to specific files | Yes |

20| `EnterPlanMode` | Switches to plan mode to design an approach before coding | No |

21| `EnterWorktree` | Creates an isolated [git worktree](/en/common-workflows#run-parallel-claude-code-sessions-with-git-worktrees) and switches into it | No |

22| `ExitPlanMode` | Presents a plan for approval and exits plan mode | Yes |

23| `ExitWorktree` | Exits a worktree session and returns to the original directory | No |

24| `Glob` | Finds files based on pattern matching | No |

25| `Grep` | Searches for patterns in file contents | No |

26| `ListMcpResourcesTool` | Lists resources exposed by connected [MCP servers](/en/mcp) | No |

27| `LSP` | Code intelligence via language servers. Reports type errors and warnings automatically after file edits. Also supports navigation operations: jump to definitions, find references, get type info, list symbols, find implementations, trace call hierarchies. Requires a [code intelligence plugin](/en/discover-plugins#code-intelligence) and its language server binary | No |

28| `NotebookEdit` | Modifies Jupyter notebook cells | Yes |

29| `Read` | Reads the contents of files | No |

30| `ReadMcpResourceTool` | Reads a specific MCP resource by URI | No |

31| `Skill` | Executes a [skill](/en/skills#control-who-invokes-a-skill) within the main conversation | Yes |

32| `TaskCreate` | Creates a new task in the task list | No |

33| `TaskGet` | Retrieves full details for a specific task | No |

34| `TaskList` | Lists all tasks with their current status | No |

35| `TaskOutput` | Retrieves output from a background task | No |

36| `TaskStop` | Kills a running background task by ID | No |

37| `TaskUpdate` | Updates task status, dependencies, details, or deletes tasks | No |

38| `TodoWrite` | Manages the session task checklist. Available in non-interactive mode and the [Agent SDK](/en/headless); interactive sessions use TaskCreate, TaskGet, TaskList, and TaskUpdate instead | No |

39| `ToolSearch` | Searches for and loads deferred tools when [tool search](/en/mcp#scale-with-mcp-tool-search) is enabled | No |

40| `WebFetch` | Fetches content from a specified URL | Yes |

41| `WebSearch` | Performs web searches | Yes |

42| `Write` | Creates or overwrites files | Yes |

43 

44Permission rules can be configured using `/permissions` or in [permission settings](/en/settings#available-settings). Also see [Tool-specific permission rules](/en/permissions#tool-specific-permission-rules).

45 

46## Bash tool behavior

47 

48The Bash tool runs each command in a separate process with the following persistence behavior:

49 

50* Working directory persists across commands. Set `CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR=1` to reset to the project directory after each command.

51* Environment variables do not persist. An `export` in one command will not be available in the next.

52 

53Activate your virtualenv or conda environment before launching Claude Code. To make environment variables persist across Bash commands, set [`CLAUDE_ENV_FILE`](/en/env-vars) to a shell script before launching Claude Code, or use a [SessionStart hook](/en/hooks#persist-environment-variables) to populate it dynamically.

54 

55## See also

56 

57* [Permissions](/en/permissions): permission system, rule syntax, and tool-specific patterns

58* [Subagents](/en/sub-agents): configure tool access for subagents

59* [Hooks](/en/hooks-guide): run custom commands before or after tool execution

733pacman -S ripgrep733pacman -S ripgrep

734```734```

735 735 

736Then set `USE_BUILTIN_RIPGREP=0` in your [environment](/en/settings#environment-variables).736Then set `USE_BUILTIN_RIPGREP=0` in your [environment](/en/env-vars).

737 737 

738### Slow or incomplete search results on WSL738### Slow or incomplete search results on WSL

739 739 

268Claude Code is available as both a VS Code extension (graphical panel) and a CLI (command-line interface in the terminal). Some features are only available in the CLI. If you need a CLI-only feature, run `claude` in VS Code's integrated terminal.268Claude Code is available as both a VS Code extension (graphical panel) and a CLI (command-line interface in the terminal). Some features are only available in the CLI. If you need a CLI-only feature, run `claude` in VS Code's integrated terminal.

269 269 

270| Feature | CLI | VS Code Extension |270| Feature | CLI | VS Code Extension |

271| ------------------- | --------------------------------------------- | ------------------------------------------------------------------------------------ |271| ------------------- | ------------------- | ------------------------------------------------------------------------------------ |

272| Commands and skills | [All](/en/interactive-mode#built-in-commands) | Subset (type `/` to see available) |272| Commands and skills | [All](/en/commands) | Subset (type `/` to see available) |

273| MCP server config | Yes | Partial (add servers via CLI; manage existing servers with `/mcp` in the chat panel) |273| MCP server config | Yes | Partial (add servers via CLI; manage existing servers with `/mcp` in the chat panel) |

274| Checkpoints | Yes | Yes |274| Checkpoints | Yes | Yes |

275| `!` bash shortcut | Yes | No |275| `!` bash shortcut | Yes | No |