Documentation 2026-03-11 03:43 UTC to 2026-03-12 21:07 UTC

14 14 

15Unlike [subagents](/en/sub-agents), which run within a single session and can only report back to the main agent, you can also interact with individual teammates directly without going through the lead.15Unlike [subagents](/en/sub-agents), which run within a single session and can only report back to the main agent, you can also interact with individual teammates directly without going through the lead.

16 16 

17<Note>

18 Agent teams require Claude Code v2.1.32 or later. Check your version with `claude --version`.

19</Note>

20 

17This page covers:21This page covers:

18 22 

19* [When to use agent teams](#when-to-use-agent-teams), including best use cases and how they compare with subagents23* [When to use agent teams](#when-to-use-agent-teams), including best use cases and how they compare with subagents

163 163 

164<Note>[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) may not be available in all regions.</Note>164<Note>[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) may not be available in all regions.</Note>

165 165 

166#### Map each model version to an inference profile

167 

168The `ANTHROPIC_DEFAULT_*_MODEL` environment variables configure one inference profile per model family. If your organization needs to expose several versions of the same family in the `/model` picker, each routed to its own application inference profile ARN, use the `modelOverrides` setting in your [settings file](/en/settings#settings-files) instead.

169 

170This example maps three Opus versions to distinct ARNs so users can switch between them without bypassing your organization's inference profiles:

171 

172```json theme={null}

173{

174 "modelOverrides": {

175 "claude-opus-4-6": "arn:aws:bedrock:us-east-2:123456789012:application-inference-profile/opus-46-prod",

176 "claude-opus-4-5-20251101": "arn:aws:bedrock:us-east-2:123456789012:application-inference-profile/opus-45-prod",

177 "claude-opus-4-1-20250805": "arn:aws:bedrock:us-east-2:123456789012:application-inference-profile/opus-41-prod"

178 }

179}

180```

181 

182When a user selects one of these versions in `/model`, Claude Code calls Bedrock with the mapped ARN. Versions without an override fall back to the built-in Bedrock model ID or any matching inference profile discovered at startup. See [Override model IDs per version](/en/model-config#override-model-ids-per-version) for details on how overrides interact with `availableModels` and other model settings.

183 

166## IAM configuration184## IAM configuration

167 185 

168Create an IAM policy with the required permissions for Claude Code:186Create an IAM policy with the required permissions for Claude Code:

540 540 

541Use `--verbose` for debugging during development, and turn it off in production.541Use `--verbose` for debugging during development, and turn it off in production.

542 542 

543### Safe autonomous mode

544 

545Use `claude --dangerously-skip-permissions` to bypass all permission checks and let Claude work uninterrupted. This works well for workflows like fixing lint errors or generating boilerplate code.

546 

547<Warning>

548 Letting Claude run arbitrary commands is risky and can result in data loss, system corruption, or data exfiltration (e.g., via prompt injection attacks). To minimize these risks, use `--dangerously-skip-permissions` in a container without internet access.

549 

550 With sandboxing enabled (`/sandbox`), you get similar autonomy with better security. Sandbox defines upfront boundaries rather than bypassing all checks.

551</Warning>

552 

553***543***

554 544 

555## Avoid common failure patterns545## Avoid common failure patterns

98| `prompt` | Yes | The system prompt that guides the subagent's behavior |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 |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 |100| `disallowedTools` | No | Array of tool names to explicitly deny for this subagent |

101| `model` | No | Model alias to use: `sonnet`, `opus`, `haiku`, or `inherit`. If omitted, defaults to `inherit` |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 |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 |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 |104| `maxTurns` | No | Maximum number of agentic turns before the subagent stops |

146 146 

147## Pricing147## Pricing

148 148 

149Code Review is billed based on token usage. Reviews average \$15-25, scaling with PR size, codebase complexity, and how many issues require verification.149Code Review is billed based on token usage. Reviews average \$15-25, scaling with PR size, codebase complexity, and how many issues require verification. Code Review usage is billed separately through [extra usage](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) and does not count against your plan's included usage.

150 150 

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

152 152 

59 59 

60The diagram below shows how Claude Code connects to external services during installation and normal operation. Solid lines indicate required connections, while dashed lines represent optional or user-initiated data flows.60The diagram below shows how Claude Code connects to external services during installation and normal operation. Solid lines indicate required connections, while dashed lines represent optional or user-initiated data flows.

61 61 

62<img src="https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/claude-code-data-flow.svg?fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=e0239c69a0bbae485b726338e50f1082" alt="Diagram showing Claude Code's external connections: install/update connects to NPM, and user requests connect to Anthropic services including Console auth, public-api, and optionally Statsig, Sentry, and bug reporting" width="720" height="520" data-path="images/claude-code-data-flow.svg" />62<img src="https://mintcdn.com/claude-code/c5r9_6tjPMzFdDDT/images/claude-code-data-flow.svg?fit=max&auto=format&n=c5r9_6tjPMzFdDDT&q=85&s=b3f71c69d743bff63343207dfb7ad6ce" alt="Diagram showing Claude Code's external connections: install/update connects to NPM, and user requests connect to Anthropic services including Console auth, public-api, and optionally Statsig, Sentry, and bug reporting" width="720" height="520" data-path="images/claude-code-data-flow.svg" />

63 63 

64Claude Code is installed from [NPM](https://www.npmjs.com/package/@anthropic-ai/claude-code). Claude Code runs locally. In order to interact with the LLM, Claude Code sends data over the network. This data includes all user prompts and model outputs. The data is encrypted in transit via TLS and is not encrypted at rest. Claude Code is compatible with most popular VPNs and LLM proxies.64Claude Code is installed from [NPM](https://www.npmjs.com/package/@anthropic-ai/claude-code). Claude Code runs locally. In order to interact with the LLM, Claude Code sends data over the network. This data includes all user prompts and model outputs. The data is encrypted in transit via TLS and is not encrypted at rest. Claude Code is compatible with most popular VPNs and LLM proxies.

65 65 

14 14 

15Fast mode is not a different model. It uses the same Opus 4.6 with a different API configuration that prioritizes speed over cost efficiency. You get identical quality and capabilities, just faster responses.15Fast mode is not a different model. It uses the same Opus 4.6 with a different API configuration that prioritizes speed over cost efficiency. You get identical quality and capabilities, just faster responses.

16 16 

17<Note>

18 Fast mode requires Claude Code v2.1.36 or later. Check your version with `claude --version`.

19</Note>

20 

17What to know:21What to know:

18 22 

19* Use `/fast` to toggle on fast mode in Claude Code CLI. Also available via `/fast` in Claude Code VS Code Extension.23* Use `/fast` to toggle on fast mode in Claude Code CLI. Also available via `/fast` in Claude Code VS Code Extension.

188 188 

189Each feature loads at different points in your session. The tabs below explain when each one loads and what goes into context.189Each feature loads at different points in your session. The tabs below explain when each one loads and what goes into context.

190 190 

191<img src="https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/context-loading.svg?fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=43114d93ae62bdc1ab6aa64660e2ba3b" alt="Context loading: CLAUDE.md and MCP load at session start and stay in every request. Skills load descriptions at start, full content on invocation. Subagents get isolated context. Hooks run externally." width="720" height="410" data-path="images/context-loading.svg" />191<img src="https://mintcdn.com/claude-code/c5r9_6tjPMzFdDDT/images/context-loading.svg?fit=max&auto=format&n=c5r9_6tjPMzFdDDT&q=85&s=729b5b634ba831d1d64772c6c9485b30" alt="Context loading: CLAUDE.md and MCP load at session start and stay in every request. Skills load descriptions at start, full content on invocation. Subagents get isolated context. Hooks run externally." width="720" height="410" data-path="images/context-loading.svg" />

192 192 

193<Tabs>193<Tabs>

194 <Tab title="CLAUDE.md">194 <Tab title="CLAUDE.md">

18 18 

19<div style={{maxWidth: "500px", margin: "0 auto"}}>19<div style={{maxWidth: "500px", margin: "0 auto"}}>

20 <Frame>20 <Frame>

21 <img src="https://mintcdn.com/claude-code/JWoaQLhotXStH4d2/images/hooks-lifecycle.svg?fit=max&auto=format&n=JWoaQLhotXStH4d2&q=85&s=9310bd002ef90ca32ac668455f5580a0" alt="Hook lifecycle diagram showing the sequence of hooks from SessionStart through the agentic loop to SessionEnd, with WorktreeCreate, WorktreeRemove, and InstructionsLoaded as standalone async events" width="520" height="1020" data-path="images/hooks-lifecycle.svg" />21 <img src="https://mintcdn.com/claude-code/c5r9_6tjPMzFdDDT/images/hooks-lifecycle.svg?fit=max&auto=format&n=c5r9_6tjPMzFdDDT&q=85&s=996ed41d03e106ab6bc9a8fdd4ebcf26" alt="Hook lifecycle diagram showing the sequence of hooks from SessionStart through the agentic loop to SessionEnd, with WorktreeCreate, WorktreeRemove, and InstructionsLoaded as standalone async events" width="520" height="1020" data-path="images/hooks-lifecycle.svg" />

22 </Frame>22 </Frame>

23</div>23</div>

24 24 

90Now suppose Claude Code decides to run `Bash "rm -rf /tmp/build"`. Here's what happens:90Now suppose Claude Code decides to run `Bash "rm -rf /tmp/build"`. Here's what happens:

91 91 

92<Frame>92<Frame>

93 <img src="https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/hook-resolution.svg?fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=5bb890134390ecd0581477cf41ef730b" alt="Hook resolution flow: PreToolUse event fires, matcher checks for Bash match, hook handler runs, result returns to Claude Code" width="780" height="290" data-path="images/hook-resolution.svg" />93 <img src="https://mintcdn.com/claude-code/c5r9_6tjPMzFdDDT/images/hook-resolution.svg?fit=max&auto=format&n=c5r9_6tjPMzFdDDT&q=85&s=ad667ee6d86ab2276aa48a4e73e220df" alt="Hook resolution flow: PreToolUse event fires, matcher checks for Bash match, hook handler runs, result returns to Claude Code" width="780" height="290" data-path="images/hook-resolution.svg" />

94</Frame>94</Frame>

95 95 

96<Steps>96<Steps>

1570 1570 

1571SessionEnd hooks have no decision control. They cannot block session termination but can perform cleanup tasks.1571SessionEnd hooks have no decision control. They cannot block session termination but can perform cleanup tasks.

1572 1572 

1573SessionEnd hooks have a default timeout of 1.5 seconds. This applies to both session exit and `/clear`. If your hooks need more time, set the `CLAUDE_CODE_SESSIONEND_HOOKS_TIMEOUT_MS` environment variable to a higher value in milliseconds. Any per-hook `timeout` setting is also capped by this value.

1574 

1575```bash theme={null}

1576CLAUDE_CODE_SESSIONEND_HOOKS_TIMEOUT_MS=5000 claude

1577```

1578 

1573## Prompt-based hooks1579## Prompt-based hooks

1574 1580 

1575In addition to command and HTTP hooks, Claude Code supports prompt-based hooks (`type: "prompt"`) that use an LLM to evaluate whether to allow or block an action, and agent hooks (`type: "agent"`) that spawn an agentic verifier with tool access. Not all events support every hook type.1581In addition to command and HTTP hooks, Claude Code supports prompt-based hooks (`type: "prompt"`) that use an LLM to evaluate whether to allow or block an action, and agent hooks (`type: "agent"`) that spawn an agentic verifier with tool access. Not all events support every hook type.

14 14 

15When you give Claude a task, it works through three phases: **gather context**, **take action**, and **verify results**. These phases blend together. Claude uses tools throughout, whether searching files to understand your code, editing to make changes, or running tests to check its work.15When you give Claude a task, it works through three phases: **gather context**, **take action**, and **verify results**. These phases blend together. Claude uses tools throughout, whether searching files to understand your code, editing to make changes, or running tests to check its work.

16 16 

17<img src="https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/agentic-loop.svg?fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=9d9cdb2102f397a0f57450ca5ca2a969" alt="The agentic loop: Your prompt leads to Claude gathering context, taking action, verifying results, and repeating until task complete. You can interrupt at any point." width="720" height="280" data-path="images/agentic-loop.svg" />17<img src="https://mintcdn.com/claude-code/c5r9_6tjPMzFdDDT/images/agentic-loop.svg?fit=max&auto=format&n=c5r9_6tjPMzFdDDT&q=85&s=5f1827dec8539f38adee90ead3a85a38" alt="The agentic loop: Your prompt leads to Claude gathering context, taking action, verifying results, and repeating until task complete. You can interrupt at any point." width="720" height="280" data-path="images/agentic-loop.svg" />

18 18 

19The loop adapts to what you ask. A question about your codebase might only need context gathering. A bug fix cycles through all three phases repeatedly. A refactor might involve extensive verification. Claude decides what each step requires based on what it learned from the previous step, chaining dozens of actions together and course-correcting along the way.19The loop adapts to what you ask. A question about your codebase might only need context gathering. A bug fix cycles through all three phases repeatedly. A refactor might involve extensive verification. Claude decides what each step requires based on what it learned from the previous step, chaining dozens of actions together and course-correcting along the way.

20 20 

110 110 

111When you resume a session with `claude --continue` or `claude --resume`, you pick up where you left off using the same session ID. New messages append to the existing conversation. Your full conversation history is restored, but session-scoped permissions are not. You'll need to re-approve those.111When you resume a session with `claude --continue` or `claude --resume`, you pick up where you left off using the same session ID. New messages append to the existing conversation. Your full conversation history is restored, but session-scoped permissions are not. You'll need to re-approve those.

112 112 

113<img src="https://mintcdn.com/claude-code/TBPmHzr19mDCuhZi/images/session-continuity.svg?fit=max&auto=format&n=TBPmHzr19mDCuhZi&q=85&s=808da1b213c731bf98874c75981d688b" alt="Session continuity: resume continues the same session, fork creates a new branch with a new ID." width="560" height="280" data-path="images/session-continuity.svg" />113<img src="https://mintcdn.com/claude-code/c5r9_6tjPMzFdDDT/images/session-continuity.svg?fit=max&auto=format&n=c5r9_6tjPMzFdDDT&q=85&s=fa41d12bfb57579cabfeece907151d30" alt="Session continuity: resume continues the same session, fork creates a new branch with a new ID." width="560" height="280" data-path="images/session-continuity.svg" />

114 114 

115To branch off and try a different approach without affecting the original session, use the `--fork-session` flag:115To branch off and try a different approach without affecting the original session, use the `--fork-session` flag:

116 116 

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

94 94 

95| Command | Purpose |95| Command | Purpose |

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

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

98| `/agents` | Manage [agent](/en/sub-agents) configurations |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 |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 |100| `/chrome` | Configure [Claude in Chrome](/en/chrome) settings |

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

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

103| `/config` | Open the [Settings](/en/settings) interface (Config tab). Alias: `/settings` |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 |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 |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 |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` |107| `/desktop` | Continue the current session in the Claude Code Desktop app. macOS and Windows only. Alias: `/app` |

127| `/memory` | Edit `CLAUDE.md` memory files, enable or disable [auto-memory](/en/memory#auto-memory), and view auto-memory entries |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` |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 |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| `/output-style [style]` | Switch between [output styles](/en/output-styles). **Default** is standard behavior, **Explanatory** adds educational insights about implementation choices and codebase patterns, and **Learning** pauses to ask you to write small code pieces for hands-on practice. You can also [create custom output styles](/en/output-styles#create-a-custom-output-style) |

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

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

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

355* To see all tasks or clear them, ask Claude directly: "show me all tasks" or "clear all tasks"354* To see all tasks or clear them, ask Claude directly: "show me all tasks" or "clear all tasks"

356* Tasks persist across context compactions, helping Claude stay organized on larger projects355* Tasks persist across context compactions, helping Claude stay organized on larger projects

357* To share a task list across sessions, set `CLAUDE_CODE_TASK_LIST_ID` to use a named directory in `~/.claude/tasks/`: `CLAUDE_CODE_TASK_LIST_ID=my-project claude`356* To share a task list across sessions, set `CLAUDE_CODE_TASK_LIST_ID` to use a named directory in `~/.claude/tasks/`: `CLAUDE_CODE_TASK_LIST_ID=my-project claude`

358* To revert to the previous TODO list, set `CLAUDE_CODE_ENABLE_TASKS=false`.

359 357 

360## PR review status358## PR review status

361 359 

6 6 

7> Customize keyboard shortcuts in Claude Code with a keybindings configuration file.7> Customize keyboard shortcuts in Claude Code with a keybindings configuration file.

8 8 

9<Note>

10 Customizable keyboard shortcuts require Claude Code v2.1.18 or later. Check your version with `claude --version`.

11</Note>

12 

9Claude Code supports customizable keyboard shortcuts. Run `/keybindings` to create or open your configuration file at `~/.claude/keybindings.json`.13Claude Code supports customizable keyboard shortcuts. Run `/keybindings` to create or open your configuration file at `~/.claude/keybindings.json`.

10 14 

11## Configuration file15## Configuration file

221 225 

222| Action | Default | Description |226| Action | Default | Description |

223| :----------------------- | :---------------------------------------- | :---------------- |227| :----------------------- | :---------------------------------------- | :---------------- |

224| `messageSelector:up` | Up, K | Move up in list |228| `messageSelector:up` | Up, K, Ctrl+P | Move up in list |

225| `messageSelector:down` | Down, J | Move down in list |229| `messageSelector:down` | Down, J, Ctrl+N | Move down in list |

226| `messageSelector:top` | Ctrl+Up, Shift+Up, Meta+Up, Shift+K | Jump to top |230| `messageSelector:top` | Ctrl+Up, Shift+Up, Meta+Up, Shift+K | Jump to top |

227| `messageSelector:bottom` | Ctrl+Down, Shift+Down, Meta+Down, Shift+J | Jump to bottom |231| `messageSelector:bottom` | Ctrl+Down, Shift+Down, Meta+Down, Shift+J | Jump to bottom |

228| `messageSelector:select` | Enter | Select message |232| `messageSelector:select` | Enter | Select message |

1010 1010 

1011### Configure tool search1011### Configure tool search

1012 1012 

1013Tool search runs in auto mode by default, meaning it activates only when your MCP tool definitions exceed the context threshold. If you have few tools, they load normally without tool search. This feature requires models that support `tool_reference` blocks: Sonnet 4 and later, or Opus 4 and later. Haiku models do not support tool search.1013Tool search is enabled by default: MCP tools are deferred and discovered on demand. When `ANTHROPIC_BASE_URL` points to a non-first-party host, tool search is disabled by default because most proxies do not forward `tool_reference` blocks. Set `ENABLE_TOOL_SEARCH` explicitly if your proxy does. This feature requires models that support `tool_reference` blocks: Sonnet 4 and later, or Opus 4 and later. Haiku models do not support tool search.

1014 1014 

1015Control tool search behavior with the `ENABLE_TOOL_SEARCH` environment variable:1015Control tool search behavior with the `ENABLE_TOOL_SEARCH` environment variable:

1016 1016 

1017| Value | Behavior |1017| Value | Behavior |

1018| :--------- | :--------------------------------------------------------------------------------- |1018| :--------- | :--------------------------------------------------------------------------------- |

1019| `auto` | Activates when MCP tools exceed 10% of context (default) |1019| (unset) | Enabled by default. Disabled when `ANTHROPIC_BASE_URL` is a non-first-party host |

1020| `true` | Always enabled, including for non-first-party `ANTHROPIC_BASE_URL` |

1021| `auto` | Activates when MCP tools exceed 10% of context |

1020| `auto:<N>` | Activates at custom threshold, where `<N>` is a percentage (e.g., `auto:5` for 5%) |1022| `auto:<N>` | Activates at custom threshold, where `<N>` is a percentage (e.g., `auto:5` for 5%) |

1021| `true` | Always enabled |

1022| `false` | Disabled, all MCP tools loaded upfront |1023| `false` | Disabled, all MCP tools loaded upfront |

1023 1024 

1024```bash theme={null}1025```bash theme={null}

251 251 

252Auto memory lets Claude accumulate knowledge across sessions without you writing anything. Claude saves notes for itself as it works: build commands, debugging insights, architecture notes, code style preferences, and workflow habits. Claude doesn't save something every session. It decides what's worth remembering based on whether the information would be useful in a future conversation.252Auto memory lets Claude accumulate knowledge across sessions without you writing anything. Claude saves notes for itself as it works: build commands, debugging insights, architecture notes, code style preferences, and workflow habits. Claude doesn't save something every session. It decides what's worth remembering based on whether the information would be useful in a future conversation.

253 253 

254<Note>

255 Auto memory requires Claude Code v2.1.59 or later. Check your version with `claude --version`.

256</Note>

257 

254### Enable or disable auto memory258### Enable or disable auto memory

255 259 

256Auto memory is on by default. To toggle it, open `/memory` in a session and use the auto memory toggle, or set `autoMemoryEnabled` in your project settings:260Auto memory is on by default. To toggle it, open `/memory` in a session and use the auto memory toggle, or set `autoMemoryEnabled` in your project settings:

267 271 

268Each project gets its own memory directory at `~/.claude/projects/<project>/memory/`. The `<project>` path is derived from the git repository, so all worktrees and subdirectories within the same repo share one auto memory directory. Outside a git repo, the project root is used instead.272Each project gets its own memory directory at `~/.claude/projects/<project>/memory/`. The `<project>` path is derived from the git repository, so all worktrees and subdirectories within the same repo share one auto memory directory. Outside a git repo, the project root is used instead.

269 273 

274To store auto memory in a different location, set `autoMemoryDirectory` in your user or local settings:

275 

276```json theme={null}

277{

278 "autoMemoryDirectory": "~/my-custom-memory-dir"

279}

280```

281 

282This setting is accepted from policy, local, and user settings. It is not accepted from project settings (`.claude/settings.json`) to prevent a shared project from redirecting auto memory writes to sensitive locations.

283 

270The directory contains a `MEMORY.md` entrypoint and optional topic files:284The directory contains a `MEMORY.md` entrypoint and optional topic files:

271 285 

272```text theme={null}286```text theme={null}

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.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.

218</Note>218</Note>

219 219 

220### Override model IDs per version

221 

222The family-level environment variables above configure one model ID per family alias. If you need to map several versions within the same family to distinct provider IDs, use the `modelOverrides` setting instead.

223 

224`modelOverrides` maps individual Anthropic model IDs to the provider-specific strings that Claude Code sends to your provider's API. When a user selects a mapped model in the `/model` picker, Claude Code uses your configured value instead of the built-in default.

225 

226This lets enterprise administrators route each model version to a specific Bedrock inference profile ARN, Vertex AI version name, or Foundry deployment name for governance, cost allocation, or regional routing.

227 

228Set `modelOverrides` in your [settings file](/en/settings#settings-files):

229 

230```json theme={null}

231{

232 "modelOverrides": {

233 "claude-opus-4-6": "arn:aws:bedrock:us-east-2:123456789012:application-inference-profile/opus-prod",

234 "claude-opus-4-5-20251101": "arn:aws:bedrock:us-east-2:123456789012:application-inference-profile/opus-45-prod",

235 "claude-sonnet-4-6": "arn:aws:bedrock:us-east-2:123456789012:application-inference-profile/sonnet-prod"

236 }

237}

238```

239 

240Keys must be Anthropic model IDs as listed in the [Models overview](https://platform.claude.com/docs/en/about-claude/models/overview). For dated model IDs, include the date suffix exactly as it appears there. Unknown keys are ignored.

241 

242Overrides replace the built-in model IDs that back each entry in the `/model` picker. On Bedrock, overrides take precedence over any inference profiles that Claude Code discovers automatically at startup. Values you supply directly through `ANTHROPIC_MODEL`, `--model`, or the `ANTHROPIC_DEFAULT_*_MODEL` environment variables are passed to the provider as-is and are not transformed by `modelOverrides`.

243 

244`modelOverrides` works alongside `availableModels`. The allowlist is evaluated against the Anthropic model ID, not the override value, so an entry like `"opus"` in `availableModels` continues to match even when Opus versions are mapped to ARNs.

245 

220### Prompt caching configuration246### Prompt caching configuration

221 247 

222Claude Code automatically uses [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) to optimize performance and reduce costs. You can disable prompt caching globally or for specific model tiers:248Claude Code automatically uses [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) to optimize performance and reduce costs. You can disable prompt caching globally or for specific model tiers:

42 42 

43## Change your output style43## Change your output style

44 44 

45You can either:45Run `/config` and select **Output style** to pick a style from a menu. Your

46selection is saved to `.claude/settings.local.json` at the

47[local project level](/en/settings).

46 48 

47* Run `/output-style` to access a menu and select your output style (this can49To set a style without the menu, edit the `outputStyle` field directly in a

48 also be accessed from the `/config` menu)50settings file:

49 51 

50* Run `/output-style [style]`, such as `/output-style explanatory`, to directly52```json theme={null}

51 switch to a style53{

54 "outputStyle": "Explanatory"

55}

56```

52 57 

53These changes apply to the [local project level](/en/settings) and are saved in58Because the output style is set in the system prompt at session start,

54`.claude/settings.local.json`. You can also directly edit the `outputStyle`59changes take effect the next time you start a new session. This keeps the system

55field in a settings file at a different level.60prompt stable throughout a conversation so prompt caching can reduce latency and

61cost.

56 62 

57## Create a custom output style63## Create a custom output style

58 64 

81 87 

82### Frontmatter88### Frontmatter

83 89 

84Output style files support frontmatter, useful for specifying metadata about the90Output style files support frontmatter for specifying metadata:

85command:

86 91 

87| Frontmatter | Purpose | Default |92| Frontmatter | Purpose | Default |

88| :------------------------- | :-------------------------------------------------------------------------- | :---------------------- |93| :------------------------- | :-------------------------------------------------------------------------- | :---------------------- |

89| `name` | Name of the output style, if not the file name | Inherits from file name |94| `name` | Name of the output style, if not the file name | Inherits from file name |

90| `description` | Description of the output style. Used only in the UI of `/output-style` | None |95| `description` | Description of the output style, shown in the `/config` picker | None |

91| `keep-coding-instructions` | Whether to keep the parts of Claude Code's system prompt related to coding. | false |96| `keep-coding-instructions` | Whether to keep the parts of Claude Code's system prompt related to coding. | false |

92 97 

93## Comparisons to related features98## Comparisons to related features

239 239 

240### Relative paths240### Relative paths

241 241 

242For plugins in the same repository:242For plugins in the same repository, use a path starting with `./`:

243 243 

244```json theme={null}244```json theme={null}

245{245{

248}248}

249```249```

250 250 

251Paths resolve relative to the marketplace root, which is the directory containing `.claude-plugin/`. In the example above, `./plugins/my-plugin` points to `<repo>/plugins/my-plugin`, even though `marketplace.json` lives at `<repo>/.claude-plugin/marketplace.json`. Do not use `../` to climb out of `.claude-plugin/`.

252 

251<Note>253<Note>

252 Relative paths only work when users add your marketplace via Git (GitHub, GitLab, or git URL). If users add your marketplace via a direct URL to the `marketplace.json` file, relative paths will not resolve correctly. For URL-based distribution, use GitHub, npm, or git URL sources instead. See [Troubleshooting](#plugins-with-relative-paths-fail-in-url-based-marketplaces) for details.254 Relative paths only work when users add your marketplace via Git (GitHub, GitLab, or git URL). If users add your marketplace via a direct URL to the `marketplace.json` file, relative paths will not resolve correctly. For URL-based distribution, use GitHub, npm, or git URL sources instead. See [Troubleshooting](#plugins-with-relative-paths-fail-in-url-based-marketplaces) for details.

253</Note>255</Note>

311```313```

312 314 

313| Field | Type | Description |315| Field | Type | Description |

314| :---- | :----- | :-------------------------------------------------------------------- |316| :---- | :----- | :------------------------------------------------------------------------------------------------------------------------------------------------------- |

315| `url` | string | Required. Full git repository URL (must end with `.git`) |317| `url` | string | Required. Full git repository URL (`https://` or `git@`). The `.git` suffix is optional, so Azure DevOps and AWS CodeCommit URLs without the suffix work |

316| `ref` | string | Optional. Git branch or tag (defaults to repository default branch) |318| `ref` | string | Optional. Git branch or tag (defaults to repository default branch) |

317| `sha` | string | Optional. Full 40-character git commit SHA to pin to an exact version |319| `sha` | string | Optional. Full 40-character git commit SHA to pin to an exact version |

318 320 

628 630 

629Use `".*"` as the `pathPattern` to allow any filesystem path while still controlling network sources with `hostPattern`.631Use `".*"` as the `pathPattern` to allow any filesystem path while still controlling network sources with `hostPattern`.

630 632 

633<Note>

634 `strictKnownMarketplaces` restricts what users can add, but does not register marketplaces on its own. To make allowed marketplaces available automatically without users running `/plugin marketplace add`, pair it with [`extraKnownMarketplaces`](/en/settings#extraknownmarketplaces) in the same `managed-settings.json`. See [Using both together](/en/settings#strictknownmarketplaces).

635</Note>

636 

631#### How restrictions work637#### How restrictions work

632 638 

633Restrictions are validated early in the plugin installation process, before any network requests or filesystem operations occur. This prevents unauthorized marketplace access attempts.639Restrictions are validated early in the plugin installation process, before any network requests or filesystem operations occur. This prevents unauthorized marketplace access attempts.

773Run `claude plugin validate .` or `/plugin validate .` from your marketplace directory to check for issues. Common errors:779Run `claude plugin validate .` or `/plugin validate .` from your marketplace directory to check for issues. Common errors:

774 780 

775| Error | Cause | Solution |781| Error | Cause | Solution |

776| :------------------------------------------------ | :------------------------------ | :------------------------------------------------------------ |782| :------------------------------------------------ | :------------------------------ | :--------------------------------------------------------------------------------------------- |

777| `File not found: .claude-plugin/marketplace.json` | Missing manifest | Create `.claude-plugin/marketplace.json` with required fields |783| `File not found: .claude-plugin/marketplace.json` | Missing manifest | Create `.claude-plugin/marketplace.json` with required fields |

778| `Invalid JSON syntax: Unexpected token...` | JSON syntax error | Check for missing commas, extra commas, or unquoted strings |784| `Invalid JSON syntax: Unexpected token...` | JSON syntax error | Check for missing commas, extra commas, or unquoted strings |

779| `Duplicate plugin name "x" found in marketplace` | Two plugins share the same name | Give each plugin a unique `name` value |785| `Duplicate plugin name "x" found in marketplace` | Two plugins share the same name | Give each plugin a unique `name` value |

780| `plugins[0].source: Path traversal not allowed` | Source path contains `..` | Use paths relative to marketplace root without `..` |786| `plugins[0].source: Path contains ".."` | Source path contains `..` | Use paths relative to the marketplace root without `..`. See [Relative paths](#relative-paths) |

781 787 

782**Warnings** (non-blocking):788**Warnings** (non-blocking):

783 789 

281claude --plugin-dir ./my-plugin281claude --plugin-dir ./my-plugin

282```282```

283 283 

284When a `--plugin-dir` plugin has the same name as an installed marketplace plugin, the local copy takes precedence for that session. This lets you test changes to a plugin you already have installed without uninstalling it first. Marketplace plugins force-enabled by managed settings are the only exception and cannot be overridden.

285 

284As you make changes to your plugin, run `/reload-plugins` to pick up the updates without restarting. Changes to LSP server configuration still require a full restart. Test your plugin components:286As you make changes to your plugin, run `/reload-plugins` to pick up the updates without restarting. Changes to LSP server configuration still require a full restart. Test your plugin components:

285 287 

286* Try your skills with `/plugin-name:skill-name`288* Try your skills with `/plugin-name:skill-name`

20 20 

21Unlike [Claude Code on the web](/en/claude-code-on-the-web), which runs on cloud infrastructure, Remote Control sessions run directly on your machine and interact with your local filesystem. The web and mobile interfaces are just a window into that local session.21Unlike [Claude Code on the web](/en/claude-code-on-the-web), which runs on cloud infrastructure, Remote Control sessions run directly on your machine and interact with your local filesystem. The web and mobile interfaces are just a window into that local session.

22 22 

23<Note>

24 Remote Control requires Claude Code v2.1.51 or later. Check your version with `claude --version`.

25</Note>

26 

23This page covers setup, how to start and connect to sessions, and how Remote Control compares to Claude Code on the web.27This page covers setup, how to start and connect to sessions, and how Remote Control compares to Claude Code on the web.

24 28 

25## Requirements29## Requirements

6 6 

7> Use /loop and the cron scheduling tools to run prompts repeatedly, poll for status, or set one-time reminders within a Claude Code session.7> Use /loop and the cron scheduling tools to run prompts repeatedly, poll for status, or set one-time reminders within a Claude Code session.

8 8 

9<Note>

10 Scheduled tasks require Claude Code v2.1.72 or later. Check your version with `claude --version`.

11</Note>

12 

9Scheduled tasks let Claude re-run a prompt automatically on an interval. Use them to poll a deployment, babysit a PR, check back on a long-running build, or remind yourself to do something later in the session.13Scheduled tasks let Claude re-run a prompt automatically on an interval. Use them to poll a deployment, babysit a PR, check back on a long-running build, or remind yourself to do something later in the session.

10 14 

11Tasks are session-scoped: they live in the current Claude Code process and are gone when you exit. For durable scheduling that survives restarts and runs without an active terminal session, see [Desktop scheduled tasks](/en/desktop#schedule-recurring-tasks) or [GitHub Actions](/en/github-actions).15Tasks are session-scoped: they live in the current Claude Code process and are gone when you exit. For durable scheduling that survives restarts and runs without an active terminal session, see [Desktop scheduled tasks](/en/desktop#schedule-recurring-tasks) or [GitHub Actions](/en/github-actions).

142`settings.json` supports a number of options:142`settings.json` supports a number of options:

143 143 

144| Key | Description | Example |144| Key | Description | Example |

145| :-------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------- |145| :-------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------- |

146| `apiKeyHelper` | Custom script, to be executed in `/bin/sh`, to generate an auth value. This value will be sent as `X-Api-Key` and `Authorization: Bearer` headers for model requests | `/bin/generate_temp_api_key.sh` |146| `apiKeyHelper` | Custom script, to be executed in `/bin/sh`, to generate an auth value. This value will be sent as `X-Api-Key` and `Authorization: Bearer` headers for model requests | `/bin/generate_temp_api_key.sh` |

147| `cleanupPeriodDays` | Sessions inactive for longer than this period are deleted at startup. Setting to `0` immediately deletes all sessions. (default: 30 days) | `20` |147| `autoMemoryDirectory` | Custom directory for [auto memory](/en/memory#storage-location) storage. Accepts `~/`-expanded paths. Not accepted in project settings (`.claude/settings.json`) to prevent shared repos from redirecting memory writes to sensitive locations. Accepted from policy, local, and user settings | `"~/my-memory-dir"` |

148| `cleanupPeriodDays` | Sessions inactive for longer than this period are deleted at startup (default: 30 days).<br /><br />Setting to `0` deletes all existing transcripts at startup and disables session persistence entirely. No new `.jsonl` files are written, `/resume` shows no conversations, and hooks receive an empty `transcript_path`. | `20` |

148| `companyAnnouncements` | Announcement to display to users at startup. If multiple announcements are provided, they will be cycled through at random. | `["Welcome to Acme Corp! Review our code guidelines at docs.acme.com"]` |149| `companyAnnouncements` | Announcement to display to users at startup. If multiple announcements are provided, they will be cycled through at random. | `["Welcome to Acme Corp! Review our code guidelines at docs.acme.com"]` |

149| `env` | Environment variables that will be applied to every session | `{"FOO": "bar"}` |150| `env` | Environment variables that will be applied to every session | `{"FOO": "bar"}` |

150| `attribution` | Customize attribution for git commits and pull requests. See [Attribution settings](#attribution-settings) | `{"commit": "🤖 Generated with Claude Code", "pr": ""}` |151| `attribution` | Customize attribution for git commits and pull requests. See [Attribution settings](#attribution-settings) | `{"commit": "🤖 Generated with Claude Code", "pr": ""}` |

160| `allowManagedMcpServersOnly` | (Managed settings only) Only `allowedMcpServers` from managed settings are respected. `deniedMcpServers` still merges from all sources. Users can still add MCP servers, but only the admin-defined allowlist applies. See [Managed MCP configuration](/en/mcp#managed-mcp-configuration) | `true` |161| `allowManagedMcpServersOnly` | (Managed settings only) Only `allowedMcpServers` from managed settings are respected. `deniedMcpServers` still merges from all sources. Users can still add MCP servers, but only the admin-defined allowlist applies. See [Managed MCP configuration](/en/mcp#managed-mcp-configuration) | `true` |

161| `model` | Override the default model to use for Claude Code | `"claude-sonnet-4-6"` |162| `model` | Override the default model to use for Claude Code | `"claude-sonnet-4-6"` |

162| `availableModels` | Restrict which models users can select via `/model`, `--model`, Config tool, or `ANTHROPIC_MODEL`. Does not affect the Default option. See [Restrict model selection](/en/model-config#restrict-model-selection) | `["sonnet", "haiku"]` |163| `availableModels` | Restrict which models users can select via `/model`, `--model`, Config tool, or `ANTHROPIC_MODEL`. Does not affect the Default option. See [Restrict model selection](/en/model-config#restrict-model-selection) | `["sonnet", "haiku"]` |

164| `modelOverrides` | Map Anthropic model IDs to provider-specific model IDs such as Bedrock inference profile ARNs. Each model picker entry uses its mapped value when calling the provider API. See [Override model IDs per version](/en/model-config#override-model-ids-per-version) | `{"claude-opus-4-6": "arn:aws:bedrock:..."}` |

163| `otelHeadersHelper` | Script to generate dynamic OpenTelemetry headers. Runs at startup and periodically (see [Dynamic headers](/en/monitoring-usage#dynamic-headers)) | `/bin/generate_otel_headers.sh` |165| `otelHeadersHelper` | Script to generate dynamic OpenTelemetry headers. Runs at startup and periodically (see [Dynamic headers](/en/monitoring-usage#dynamic-headers)) | `/bin/generate_otel_headers.sh` |

164| `statusLine` | Configure a custom status line to display context. See [`statusLine` documentation](/en/statusline) | `{"type": "command", "command": "~/.claude/statusline.sh"}` |166| `statusLine` | Configure a custom status line to display context. See [`statusLine` documentation](/en/statusline) | `{"type": "command", "command": "~/.claude/statusline.sh"}` |

165| `fileSuggestion` | Configure a custom script for `@` file autocomplete. See [File suggestion settings](#file-suggestion-settings) | `{"type": "command", "command": "~/.claude/file-suggestion.sh"}` |167| `fileSuggestion` | Configure a custom script for `@` file autocomplete. See [File suggestion settings](#file-suggestion-settings) | `{"type": "command", "command": "~/.claude/file-suggestion.sh"}` |

753}755}

754```756```

755 757 

758**Using both together**:

759 

760`strictKnownMarketplaces` is a policy gate: it controls what users may add but does not register any marketplaces. To both restrict and pre-register a marketplace for all users, set both in `managed-settings.json`:

761 

762```json theme={null}

763{

764 "strictKnownMarketplaces": [

765 { "source": "github", "repo": "acme-corp/plugins" }

766 ],

767 "extraKnownMarketplaces": {

768 "acme-tools": {

769 "source": { "source": "github", "repo": "acme-corp/plugins" }

770 }

771 }

772}

773```

774 

775With only `strictKnownMarketplaces` set, users can still add the allowed marketplace manually via `/plugin marketplace add`, but it is not available automatically.

776 

756**Important notes**:777**Important notes**:

757 778 

758* Restrictions are checked BEFORE any network requests or filesystem operations779* Restrictions are checked BEFORE any network requests or filesystem operations

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

822| `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) | |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) | |

823| `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) | |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) | |

824| `CLAUDE_CODE_ENABLE_TASKS` | Set to `false` to temporarily revert to the previous TODO list instead of the task tracking system. Default: `true`. See [Task list](/en/interactive-mode#task-list) | |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) | |

825| `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) | |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) | |

826| `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 | |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 | |

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

834| `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) | |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) | |

835| `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) | |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) | |

836| `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 | |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 | |

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

838| `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>` | |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>` | |

839| `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 | |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 | |

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

862| `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) | |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) | |

863| `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 | |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 | |

864| `ENABLE_TOOL_SEARCH` | Controls [MCP tool search](/en/mcp#scale-with-mcp-tool-search). Values: `auto` (default, enables at 10% context), `auto:N` (custom threshold, e.g., `auto:5` for 5%), `true` (always on), `false` (disabled) | |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) | |

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

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

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

212| `description` | Yes | When Claude should delegate to this subagent |212| `description` | Yes | When Claude should delegate to this subagent |

213| `tools` | No | [Tools](#available-tools) the subagent can use. Inherits all tools if omitted |213| `tools` | No | [Tools](#available-tools) the subagent can use. Inherits all tools if omitted |

214| `disallowedTools` | No | Tools to deny, removed from inherited or specified list |214| `disallowedTools` | No | Tools to deny, removed from inherited or specified list |

215| `model` | No | [Model](#choose-a-model) to use: `sonnet`, `opus`, `haiku`, or `inherit`. Defaults to `inherit` |215| `model` | No | [Model](#choose-a-model) to use: `sonnet`, `opus`, `haiku`, a full model ID (for example, `claude-opus-4-6`), or `inherit`. Defaults to `inherit` |

216| `permissionMode` | No | [Permission mode](#permission-modes): `default`, `acceptEdits`, `dontAsk`, `bypassPermissions`, or `plan` |216| `permissionMode` | No | [Permission mode](#permission-modes): `default`, `acceptEdits`, `dontAsk`, `bypassPermissions`, or `plan` |

217| `maxTurns` | No | Maximum number of agentic turns before the subagent stops |217| `maxTurns` | No | Maximum number of agentic turns before the subagent stops |

218| `skills` | No | [Skills](/en/skills) to load into the subagent's context at startup. The full skill content is injected, not just made available for invocation. Subagents don't inherit skills from the parent conversation |218| `skills` | No | [Skills](/en/skills) to load into the subagent's context at startup. The full skill content is injected, not just made available for invocation. Subagents don't inherit skills from the parent conversation |

227The `model` field controls which [AI model](/en/model-config) the subagent uses:227The `model` field controls which [AI model](/en/model-config) the subagent uses:

228 228 

229* **Model alias**: Use one of the available aliases: `sonnet`, `opus`, or `haiku`229* **Model alias**: Use one of the available aliases: `sonnet`, `opus`, or `haiku`

230* **Full model ID**: Use a full model ID such as `claude-opus-4-6` or `claude-sonnet-4-6`. Accepts the same values as the `--model` flag

230* **inherit**: Use the same model as the main conversation231* **inherit**: Use the same model as the main conversation

231* **Omitted**: If not specified, defaults to `inherit` (uses the same model as the main conversation)232* **Omitted**: If not specified, defaults to `inherit` (uses the same model as the main conversation)

232 233 

273 274 

274If `Agent` is omitted from the `tools` list entirely, the agent cannot spawn any subagents. This restriction only applies to agents running as the main thread with `claude --agent`. Subagents cannot spawn other subagents, so `Agent(agent_type)` has no effect in subagent definitions.275If `Agent` is omitted from the `tools` list entirely, the agent cannot spawn any subagents. This restriction only applies to agents running as the main thread with `claude --agent`. Subagents cannot spawn other subagents, so `Agent(agent_type)` has no effect in subagent definitions.

275 276 

277#### Scope MCP servers to a subagent

278 

279Use the `mcpServers` field to give a subagent access to [MCP](/en/mcp) servers that aren't available in the main conversation. Inline servers defined here are connected when the subagent starts and disconnected when it finishes. String references share the parent session's connection.

280 

281Each entry in the list is either an inline server definition or a string referencing an MCP server already configured in your session:

282 

283```yaml theme={null}

284---

285name: browser-tester

286description: Tests features in a real browser using Playwright

287mcpServers:

288 # Inline definition: scoped to this subagent only

289 - playwright:

290 type: stdio

291 command: npx

292 args: ["-y", "@playwright/mcp@latest"]

293 # Reference by name: reuses an already-configured server

294 - github

295---

296 

297Use the Playwright tools to navigate, screenshot, and interact with pages.

298```

299 

300Inline definitions use the same schema as `.mcp.json` server entries (`stdio`, `http`, `sse`, `ws`), keyed by the server name.

301 

302To keep an MCP server out of the main conversation entirely and avoid its tool descriptions consuming context there, define it inline here rather than in `.mcp.json`. The subagent gets the tools; the parent conversation does not.

303 

276#### Permission modes304#### Permission modes

277 305 

278The `permissionMode` field controls how the subagent handles permission prompts. Subagents inherit the permission context from the main conversation but can override the mode.306The `permissionMode` field controls how the subagent handles permission prompts. Subagents inherit the permission context from the main conversation but can override the mode.

40 40 

41<Steps>41<Steps>

42 <Step title="Open the Claude Code panel">42 <Step title="Open the Claude Code panel">

43 Throughout VS Code, the Spark icon indicates Claude Code: <img src="https://mintcdn.com/claude-code/mfM-EyoZGnQv8JTc/images/vs-code-spark-icon.svg?fit=max&auto=format&n=mfM-EyoZGnQv8JTc&q=85&s=a734d84e785140016672f08e0abb236c" alt="Spark icon" style={{display: "inline", height: "0.85em", verticalAlign: "middle"}} width="16" height="16" data-path="images/vs-code-spark-icon.svg" />43 Throughout VS Code, the Spark icon indicates Claude Code: <img src="https://mintcdn.com/claude-code/c5r9_6tjPMzFdDDT/images/vs-code-spark-icon.svg?fit=max&auto=format&n=c5r9_6tjPMzFdDDT&q=85&s=3ca45e00deadec8c8f4b4f807da94505" alt="Spark icon" style={{display: "inline", height: "0.85em", verticalAlign: "middle"}} width="16" height="16" data-path="images/vs-code-spark-icon.svg" />

44 44 

45 The quickest way to open Claude is to click the Spark icon in the **Editor Toolbar** (top-right corner of the editor). The icon only appears when you have a file open.45 The quickest way to open Claude is to click the Spark icon in the **Editor Toolbar** (top-right corner of the editor). The icon only appears when you have a file open.

46 46