Documentation — Spybara

en/agent-view.md +32 −13

Details

87 ✽ clawd walk cycle Write assets/sprites/clawd-walk.png 3m87 ✽ clawd walk cycle Write assets/sprites/clawd-walk.png 3m

88 88

89Ready for review89Ready for review

~~90 ∙ jump physics Opened PR with collision fix ⧉ PR #2048 2h~~90 ∙ jump physics Opened PR with collision fix PR #2048 2h

91 91

92Needs input92Needs input

93 ✻ power-up design needs input: double jump or wall climb? 1m93 ✻ power-up design needs input: double jump or wall climb? 1m

123| `∙` | The process has exited. You can still peek, reply, or attach, and Claude restarts from where it left off |123| `∙` | The process has exited. You can still peek, reply, or attach, and Claude restarts from where it left off |

124| `✢` | A [`/loop`](/en/scheduled-tasks) session sleeping between iterations. The row shows its run count and a countdown |124| `✢` | A [`/loop`](/en/scheduled-tasks) session sleeping between iterations. The row shows its run count and a countdown |

125 125

126The `⧉ PR #N` label that can appear at the right edge of a row is the [pull request the session opened](#pull-request-status), not part of the state icon. When a session has opened more than one pull request, the label adds a `+N` suffix counting the others.126The `PR #N` label that can appear at the right edge of a row is the [pull request the session opened](#pull-request-status), not part of the state icon. When a session has opened more than one pull request, the label shows a count instead, such as `3 PRs`.

127 127

128The terminal tab title shows the awaiting-input count while agent view is open: `2 awaiting input · claude agents` when sessions need input, or `claude agents` when none do.128The terminal tab title shows the awaiting-input count while agent view is open: `2 awaiting input · claude agents` when sessions need input, or `claude agents` when none do.

129 129

139 139

140### Pull request status140### Pull request status

141 141

142When a session opens a pull request, a `⧉ PR #1234` label appears at the right edge of the row, linked to the pull request in terminals that support hyperlinks. The label persists when you send a follow-up to the session, so the pull request remains visible while the row reverts to live progress.142When a session opens a pull request, a `PR #1234` label appears at the right edge of the row, linked to the pull request in terminals that support hyperlinks. The label persists when you send a follow-up to the session, so the pull request remains visible while the row reverts to live progress.

143 143

144When a session has opened more than one pull request, the label shows the open pull request that most needs attention and adds a `+N` suffix counting the others. Open the [peek panel](#peek-and-reply) to see them all.144When a session has opened more than one pull request, the label shows a count instead, such as `3 PRs`, colored by the open pull request that most needs attention. Open the [peek panel](#peek-and-reply) to see them all.

145 145

146The `⧉` icon is colored by the pull request's status:146The pull request number is colored by its status:

147 147

148| Color | Pull request status |148| Color | Pull request status |

149| :----- | :-------------------------------------------- |149| :----- | :-------------------------------------------- |

152| Purple | Merged |152| Purple | Merged |

153| Grey | Draft or closed |153| Grey | Draft or closed |

154 154

155For most tasks this column is where you pick up the result: review and merge the pull request when its `⧉` icon turns green.155For most tasks this column is where you pick up the result: review and merge the pull request when its number turns green.

156 156

157### Peek and reply157### Peek and reply

158 158

174 174

175Detaching never stops a background session: `←`, `Ctrl+Z`, `/exit`, and double `Ctrl+C` or double `Ctrl+D` all leave it running. To end a session from inside it, run `/stop`.175Detaching never stops a background session: `←`, `Ctrl+Z`, `/exit`, and double `Ctrl+C` or double `Ctrl+D` all leave it running. To end a session from inside it, run `/stop`.

176 176

177After you've dispatched or backgrounded a session, pressing `←` on an empty prompt works from any Claude Code session, not only ones you attached to from agent view. It backgrounds the current session and opens agent view with that row selected, so you can switch sessions without leaving the terminal. The row is created even from a fresh session with no conversation history, so `→` returns to it. When that row is the only one, agent view shows an onboarding hint below it. You can turn this shortcut off in `/config` (the `leftArrowOpensAgents` setting).177Pressing `←` on an empty prompt works from any Claude Code session, not only ones you attached to from agent view. It backgrounds the current session and opens agent view with that row selected, so you can switch sessions without leaving the terminal. The row is created even from a fresh session with no conversation history, so `→` returns to it. When that row is the only one, agent view shows an onboarding hint below it. You can turn this shortcut off in `/config` (the `leftArrowOpensAgents` setting).

178 178

179### Organize the list179### Organize the list

180 180

243| `<agent-name> <prompt>` | If the first word matches a custom [subagent](/en/sub-agents) name, that subagent runs as the session's main agent with the configuration from its frontmatter |243| `<agent-name> <prompt>` | If the first word matches a custom [subagent](/en/sub-agents) name, that subagent runs as the session's main agent with the configuration from its frontmatter |

247| `! <command>` | Run a shell command as a background job instead of starting a Claude session. The job appears as a row you can attach to, watch, and detach from |

249 250

263 264

264### From inside a session265### From inside a session

265 266

266Run `/background` or its alias `/bg` to move the current conversation into a background session. Pass a prompt such as `/bg run the test suite and fix any failures` to give one more instruction first.267Run `/background` or its alias `/bg` to move the current conversation into a background session. Pass a prompt such as `/bg run the test suite and fix any failures` to give one more instruction first. If Claude is responding when you run `/bg`, the response continues in the background session.

267 268

268Backgrounding from an interactive session starts a fresh process that resumes from the saved conversation, so running subagents, [monitors](/en/tools-reference#monitor-tool), and background commands do not transfer to it. Claude asks you to confirm before backgrounding when any are running. Once in the background, the session can start new subagents, monitors, and background commands, and those keep running across later detach and reattach.269Backgrounding from an interactive session starts a fresh process that resumes from the saved conversation, so running subagents, [monitors](/en/tools-reference#monitor-tool), and background commands do not transfer to it. Claude asks you to confirm before backgrounding when any are running. Once in the background, the session can start new subagents, monitors, and background commands, and those keep running across later detach and reattach.

269 270

310 claude stop 7c5dcf5d stop this session311 claude stop 7c5dcf5d stop this session

311```312```

312 313

314#### Run a shell command

315

316To run a shell command as a background job instead of a Claude session, type `!` as the first character of the agent view dispatch input. The `!` shows as a prefix and everything you type after it is the command. The following example dispatches `pytest -x` from the agent view input box:

317

318```text theme={null}

319! pytest -x

320```

321

322Press `Enter` to start the job. The same job can also be launched directly from your shell with `--exec`:

323

324```bash theme={null}

325claude --bg --exec 'pytest -x'

326```

327

328The command runs as a PTY-backed job and appears as a row in agent view, with the most recent line of output as its status. A shell job runs the command in place of Claude, so no model is invoked and the output is not sent to any session.

329

330To see the output, attach to the row, press `Space` to peek without attaching, or run `claude logs <id>` from your shell. The captured output stays in memory and is not written to disk. The row and its output clean up automatically about five minutes after the command exits, so read it before then if you need the result.

331

313### How file edits are isolated332### How file edits are isolated

314 333

315Every background session, whether started from agent view, `/bg`, or `claude --bg`, starts in your working directory. Before editing files, Claude moves the session into an isolated [git worktree](/en/worktrees) under `.claude/worktrees/`, so parallel sessions can read the same checkout but each writes to its own.334Every background session, whether started from agent view, `/bg`, or `claude --bg`, starts in your working directory. Before editing files, Claude moves the session into an isolated [git worktree](/en/worktrees) under `.claude/worktrees/`, so parallel sessions can read the same checkout but each writes to its own.

344 363

345### Set the model364### Set the model

346 365

347The model name shown in the agent view header is the dispatch default. New sessions you start from the input use this model, which comes from the [`model` setting](/en/settings#available-settings) in your user settings. Set it by pressing `d` on a model in the [`/model` picker](/en/model-config), or edit the setting directly. To override it for the whole agent view session, pass `--model` when opening agent view. See [Permission mode, model, and effort](#permission-mode-model-and-effort).366The model name shown in the agent view header is the dispatch default. New sessions you start from the input use this model, which comes from the [`model` setting](/en/settings#available-settings) in your user settings. Set it by selecting a model in the [`/model` picker](/en/model-config), or edit the setting directly. To override it for the whole agent view session, pass `--model` when opening agent view. See [Permission mode, model, and effort](#permission-mode-model-and-effort).

348 367

349Each background session can run on a different model. To override it for one session:368Each background session can run on a different model. To override it for one session:

350 369

351* From the shell, pass `--model` with `claude --bg`.370* From the shell, pass `--model` with `claude --bg`.

352* Attach to a running session and run `/model` there. The change persists if the session is respawned.371* Attach to a running session, open `/model`, and press `s` on a model to switch for that session only. The change persists if the session is respawned.

353* Dispatch a [subagent](/en/sub-agents) whose frontmatter sets a `model` field.372* Dispatch a [subagent](/en/sub-agents) whose frontmatter sets a `model` field.

354 373

355### Permission mode, model, and effort374### Permission mode, model, and effort

425 444

426The supervisor and its sessions authenticate with the same credentials as your interactive sessions and make no additional network connections beyond the model API.445The supervisor and its sessions authenticate with the same credentials as your interactive sessions and make no additional network connections beyond the model API.

427 446

428Each background session is its own Claude Code process, managed by the supervisor rather than tied to your terminal. A session that's actively working, waiting for your input, or has a terminal attached keeps its process running. A running background shell command, subagent, workflow, or monitor counts as active work, so a long-running process such as a dev server keeps the session alive.447Each background session is its own Claude Code process, managed by the supervisor rather than tied to your terminal. A session that's actively working, waiting for your input, or has a terminal attached keeps its process running. A running background shell command, subagent, dynamic workflow, or monitor counts as active work, so a long-running process such as a dev server keeps the session alive.

429 448

430Once a session finishes and sits unattached for about an hour, the supervisor stops its process to free resources. A session you have [pinned](#organize-the-list) with `Ctrl+T` is exempt and keeps its process running while idle. The transcript and state stay on disk either way, and the next time you attach, peek, or reply to a stopped session, the supervisor starts a fresh process from where it left off. When every session has finished and no terminal is connected, the supervisor itself exits and starts again the next time you need it.449Once a session finishes and sits unattached for about an hour, the supervisor stops its process to free resources. A session you have [pinned](#organize-the-list) with `Ctrl+T` is exempt and keeps its process running while idle. The transcript and state stay on disk either way, and the next time you attach, peek, or reply to a stopped session, the supervisor starts a fresh process from where it left off. When every session has finished and no terminal is connected, the supervisor itself exits and starts again the next time you need it.

431 450

463 482

464### Cannot open agents because background tasks are running483### Cannot open agents because background tasks are running

465 484

466If pressing `←` to background the current session shows `Cannot open agents — N background task(s) running`, the session has in-flight work such as a subagent, a workflow, or a background shell command, and the shortcut won't silently abandon it. Run `/tasks` to see what's running, then `/bg` to confirm abandoning them. See [From inside a session](#from-inside-a-session) for what does and doesn't transfer when you background.485If pressing `←` to background the current session shows `Cannot open agents — N background task(s) running`, the session has in-flight work such as a subagent, a dynamic workflow, or a background shell command, and the shortcut won't silently abandon it. Run `/tasks` to see what's running, then `/bg` to confirm abandoning them. See [From inside a session](#from-inside-a-session) for what does and doesn't transfer when you background.

467 486

468### Prompt rejected as too short487### Prompt rejected as too short

469 488

en/agents.md +21 −7

Details

4 4

5# Run agents in parallel5# Run agents in parallel

6 6

~~7> Compare the ways Claude Code can take on multiple tasks at once: subagents, agent view, agent teams, and isolated worktree sessions.~~7> Compare the ways Claude Code can take on multiple tasks at once: subagents, agent view, agent teams, and dynamic workflows.

8 8

9[Subagents](/en/sub-agents), [agent view](/en/agent-view), [agent teams](/en/agent-teams), and [worktrees](/en/worktrees) each parallelize work in a different way. The right one depends on whether you want to stay in each conversation yourself, hand tasks off and check back later, or have Claude coordinate a group of workers for you.9[Subagents](/en/sub-agents), [agent view](/en/agent-view), [agent teams](/en/agent-teams), and [dynamic workflows](/en/workflows) each parallelize work in a different way. The right one depends on whether you want to stay in each conversation yourself, hand tasks off and check back later, or have Claude coordinate a group of workers for you.

10 10

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

13| [Subagents](/en/sub-agents) | Delegated workers inside one session that do a side task in their own context and return a summary | A side task would flood your main conversation with search results, logs, or file contents you won't reference again |13| [Subagents](/en/sub-agents) | Delegated workers inside one session that do a side task in their own context and return a summary | A side task would flood your main conversation with search results, logs, or file contents you won't reference again |

14| [Agent view](/en/agent-view) | One screen to dispatch and monitor sessions running in the background, opened with `claude agents`. Research preview | You have several independent tasks and want to hand them off, check status at a glance, and step in only when one needs you |14| [Agent view](/en/agent-view) | One screen to dispatch and monitor sessions running in the background, opened with `claude agents`. Research preview | You have several independent tasks and want to hand them off, check status at a glance, and step in only when one needs you |

15| [Agent teams](/en/agent-teams) | Multiple coordinated sessions with a shared task list and inter-agent messaging, managed by a lead. Experimental and disabled by default | You want Claude to split a project into pieces, assign them, and keep the workers in sync |15| [Agent teams](/en/agent-teams) | Multiple coordinated sessions with a shared task list and inter-agent messaging, managed by a lead. Experimental and disabled by default | You want Claude to split a project into pieces, assign them, and keep the workers in sync |

16| [Worktrees](/en/worktrees) | Separate git checkouts so parallel sessions never touch each other's files | You're running several sessions yourself, or your subagents edit overlapping files |16| [Dynamic workflows](/en/workflows) | A script that runs many subagents and cross-checks their results, for work too big to coordinate one turn at a time or that needs more than a single pass. Research preview | A job outgrows a handful of subagents, or you want findings verified against each other: a codebase-wide audit, a 500-file migration, cross-checked research, or a plan drafted from several angles |

17| [`/batch`](/en/commands) | A planned split of one large change into 5 to 30 worktree-isolated subagents that each open a pull request | A repo-wide migration or mechanical refactor you can describe in one instruction |

18 17

19In every approach the workers are Claude sessions. To involve a different tool, expose it to Claude as an [MCP server](/en/mcp).18In every approach the workers are Claude sessions. To involve a different tool, expose it to Claude as an [MCP server](/en/mcp).

20 19

21You can combine these approaches. Agent view automatically moves each dispatched session into its own worktree when it needs to edit files, and a session you're working in can spawn subagents that each get their own worktree.20Two more tools support this work without being a way to run agents themselves:

22* [Worktrees](/en/worktrees) give each session a separate git checkout, so parallel sessions never edit the same files. Use them for sessions you run yourself. Agent view moves each dispatched session into its own worktree automatically, and subagents you spawn can each get one too.

23* [`/batch`](/en/commands) is a [skill](/en/skills) that has Claude split one large change into 5 to 30 worktree-isolated subagents that each open a pull request. It's a packaged use of subagents and worktrees, not a separate coordination style.

25A few other features run Claude without you driving each step, but they solve a different problem than splitting work across agents:

27* A [background bash command](/en/interactive-mode#background-bash-commands) runs one shell command without blocking the conversation. It doesn't spawn an agent.

28* A [forked subagent](/en/sub-agents#fork-the-current-conversation) is a subagent that inherits your full conversation context instead of starting fresh. It's a way to spawn a subagent, not a separate surface.

29* A [routine](/en/routines) runs a session on a schedule in Anthropic's cloud, not in parallel on your machine.

22 30

23<Note>31<Note>

24 Running several sessions or subagents at once multiplies token usage. See [Costs](/en/costs) for usage and rate-limit details.32 Running several sessions or subagents at once multiplies token usage. See [Costs](/en/costs) for usage and rate-limit details.

28 36

29The right approach depends on who coordinates the work, whether the workers need to communicate, and whether they edit the same files:37The right approach depends on who coordinates the work, whether the workers need to communicate, and whether they edit the same files:

30 38

31* **Who coordinates the work?** If you want Claude to delegate and collect results inside one conversation, use [subagents](/en/sub-agents). If you're handing off independent tasks and checking back on them, use [agent view](/en/agent-view). If you want Claude to plan, assign, and supervise a group of workers, use [agent teams](/en/agent-teams), which are experimental and disabled by default.39* **Who coordinates the work?**

40 * Claude delegates and collects results inside one conversation: [subagents](/en/sub-agents)

41 * You hand off independent tasks and check back later: [agent view](/en/agent-view)

42 * Claude plans, assigns, and supervises a group of workers: [agent teams](/en/agent-teams), experimental and disabled by default

43 * A script holds the plan instead of Claude's turn-by-turn judgment: [dynamic workflows](/en/workflows). See [how workflows compare to subagents and skills](/en/workflows#when-to-use-a-workflow)

32* **Do the workers need to talk to each other?** Subagents report results back to the conversation that spawned them, and agent view sessions report only to you. Teammates in an agent team share a task list and message each other directly.44* **Do the workers need to talk to each other?** Subagents report results back to the conversation that spawned them, and agent view sessions report only to you. Teammates in an agent team share a task list and message each other directly.

33* **Do the tasks touch the same files?** Isolate the work with [worktrees](/en/worktrees). Subagents and sessions you run yourself can each use a separate worktree. Agent teams don't isolate teammates in worktrees, so [partition the work](/en/agent-teams#avoid-file-conflicts) so each teammate owns a different set of files.45* **Do the tasks touch the same files?** Isolate the work with [worktrees](/en/worktrees). Subagents and sessions you run yourself can each use a separate worktree. Agent teams don't isolate teammates in worktrees, so [partition the work](/en/agent-teams#avoid-file-conflicts) so each teammate owns a different set of files.

34 46

39* For background sessions, `claude agents` opens [agent view](/en/agent-view): one screen showing every session, its state, and which ones need your input.51* For background sessions, `claude agents` opens [agent view](/en/agent-view): one screen showing every session, its state, and which ones need your input.

40* For subagents in the current session, `/agents` opens a panel with a **Running** tab listing live subagents and a **Library** tab where you [create and edit custom subagents](/en/sub-agents#use-the-%2Fagents-command). Despite the similar name, this is separate from `claude agents`.52* For subagents in the current session, `/agents` opens a panel with a **Running** tab listing live subagents and a **Library** tab where you [create and edit custom subagents](/en/sub-agents#use-the-%2Fagents-command). Despite the similar name, this is separate from `claude agents`.

41* For anything running in the background of the current session, `/tasks` lists each item and lets you check on, attach to, or stop it.53* For anything running in the background of the current session, `/tasks` lists each item and lets you check on, attach to, or stop it.

54* For dynamic workflows, `/workflows` lists running and completed runs, the phase each is in, and how many agents have finished.

42 55

43For a desktop view of all your sessions, see [parallel sessions in the desktop app](/en/desktop#work-in-parallel-with-sessions).56For a desktop view of all your sessions, see [parallel sessions in the desktop app](/en/desktop#work-in-parallel-with-sessions).

44 57

49* [Create custom subagents](/en/sub-agents): define reusable specialists and control which tools they can use.62* [Create custom subagents](/en/sub-agents): define reusable specialists and control which tools they can use.

50* [Manage agents with agent view](/en/agent-view): dispatch sessions, watch their state, and attach when one needs you.63* [Manage agents with agent view](/en/agent-view): dispatch sessions, watch their state, and attach when one needs you.

51* [Orchestrate agent teams](/en/agent-teams): set up a lead and teammates, assign tasks, and review their work.64* [Orchestrate agent teams](/en/agent-teams): set up a lead and teammates, assign tasks, and review their work.

65* [Orchestrate dynamic workflows](/en/workflows): run a bundled workflow or have Claude write one that runs many subagents and verifies their findings against each other.

52* [Run parallel sessions with worktrees](/en/worktrees): start Claude in an isolated checkout, control what gets copied in, and clean up afterward.66* [Run parallel sessions with worktrees](/en/worktrees): start Claude in an isolated checkout, control what gets copied in, and clean up afterward.

en/amazon-bedrock.md +3 −3

Details

234 234

235Set these environment variables to specific Bedrock model IDs.235Set these environment variables to specific Bedrock model IDs.

236 236

237Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Bedrock resolves to Opus 4.6. Set it to the Opus 4.7 ID to use the latest model:237Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Bedrock resolves to Opus 4.6. Set it to the Opus 4.8 ID to use the latest model:

238 238

239```bash theme={null}239```bash theme={null}

240export ANTHROPIC_DEFAULT_OPUS_MODEL='us.anthropic.claude-opus-4-7'240export ANTHROPIC_DEFAULT_OPUS_MODEL='us.anthropic.claude-opus-4-8'

241export ANTHROPIC_DEFAULT_SONNET_MODEL='us.anthropic.claude-sonnet-4-6'241export ANTHROPIC_DEFAULT_SONNET_MODEL='us.anthropic.claude-sonnet-4-6'

242export ANTHROPIC_DEFAULT_HAIKU_MODEL='us.anthropic.claude-haiku-4-5-20251001-v1:0'242export ANTHROPIC_DEFAULT_HAIKU_MODEL='us.anthropic.claude-haiku-4-5-20251001-v1:0'

243```243```

356 356

357## 1M token context window357## 1M token context window

358 358

359Claude Opus 4.7, Opus 4.6, 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 Amazon Bedrock. Claude Code automatically enables the extended context window when you select a 1M model variant.359Claude Opus 4.6 and later, 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 Amazon Bedrock. Claude Code automatically enables the extended context window when you select a 1M model variant.

360 360

361The [setup wizard](#sign-in-with-bedrock) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. See [Pin models for third-party deployments](/en/model-config#pin-models-for-third-party-deployments) for details.361The [setup wizard](#sign-in-with-bedrock) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. See [Pin models for third-party deployments](/en/model-config#pin-models-for-third-party-deployments) for details.

362 362

en/azure-ai-foundry.md +2 −2

Details

155 155

156Set the model variables to match the deployment names you created in step 1.156Set the model variables to match the deployment names you created in step 1.

157 157

158Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Foundry resolves to Opus 4.6. Set it to the Opus 4.7 ID to use the latest model:158Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Foundry resolves to Opus 4.6. Set it to the Opus 4.8 ID to use the latest model:

159 159

160```bash theme={null}160```bash theme={null}

161export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-7'161export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-8'

162export ANTHROPIC_DEFAULT_SONNET_MODEL='claude-sonnet-4-6'162export ANTHROPIC_DEFAULT_SONNET_MODEL='claude-sonnet-4-6'

163export ANTHROPIC_DEFAULT_HAIKU_MODEL='claude-haiku-4-5'163export ANTHROPIC_DEFAULT_HAIKU_MODEL='claude-haiku-4-5'

164```164```

en/best-practices.md +10 −5

Details

27## Give Claude a way to verify its work27## Give Claude a way to verify its work

28 28

29<Tip>29<Tip>

~~30 Include tests, screenshots, or expected outputs so Claude can check itself. This is the single highest-leverage thing you can do.~~30 Give Claude a check it can run: tests, a build, a screenshot to compare. It's the difference between a session you watch and one you walk away from.

31</Tip>31</Tip>

32 32

~~33Claude performs dramatically better when it can verify its own work, like run tests, compare screenshots, and validate outputs.~~33Claude stops when the work looks done. Without a check it can run, "looks done" is the only signal available, and you become the verification loop: every mistake waits for you to notice it. Give Claude something that produces a pass or fail, and the loop closes on its own. Claude does the work, runs the check, reads the result, and iterates until the check passes.

34 34

~~35Without clear success criteria, it might produce something that looks right but actually doesn't work. You become the only feedback loop, and every mistake requires your attention.~~35The check is anything that returns a signal Claude can read in the conversation: a test suite, a build exit code, a linter, a script that diffs output against a fixture, or a [browser screenshot](/en/chrome) compared against a design.

36 36

38| ------------------------------------- | ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |38| ------------------------------------- | ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

40| **Verify UI changes visually** | *"make the dashboard look better"* | *"\[paste screenshot] implement this design. take a screenshot of the result and compare it to the original. list differences and fix them"* |40| **Verify UI changes visually** | *"make the dashboard look better"* | *"\[paste screenshot] implement this design. take a screenshot of the result and compare it to the original. list differences and fix them"* |

41| **Address root causes, not symptoms** | *"the build is failing"* | *"the build fails with this error: \[paste error]. fix it and verify the build succeeds. address the root cause, don't suppress the error"* |41| **Address root causes, not symptoms** | *"the build is failing"* | *"the build fails with this error: \[paste error]. fix it and verify the build succeeds. address the root cause, don't suppress the error"* |

42 42

~~43UI changes can be verified using the [Claude in Chrome extension](/en/chrome). It opens new tabs in your browser, tests the UI, and iterates until the code works.~~43Once the check exists, decide how hard it gates the stop:

44 44

~~45Your verification can also be a test suite, a linter, or a Bash command that checks output. Invest in making your verification rock-solid.~~45* **In one prompt**: ask Claude to run the check and iterate in the same message, as in the table above.

46* **Across a session**: set the check as a [`/goal` condition](/en/goal). A separate evaluator re-checks it after every turn and Claude keeps working until it holds.

47* **As a deterministic gate**: a [Stop hook](/en/hooks#stop) runs your check as a script and blocks the turn from ending until it passes. Claude Code overrides the hook and ends the turn after 8 consecutive blocks.

48* **By a second opinion**: a [verification subagent](/en/sub-agents) or a [dynamic workflow](/en/workflows) that checks its own findings has a fresh model try to refute the result, so the agent doing the work isn't the one grading it.

50Each step trades setup for attention. The prompt version works on any task today. The `/goal` and Stop hook versions are what let an unattended run finish correctly without you.

46 51

47Have Claude show evidence rather than asserting success: the test output, the command it ran and what it returned, or a screenshot of the result. Reviewing evidence is faster than re-running the verification yourself, and it works for sessions you weren't watching.52Have Claude show evidence rather than asserting success: the test output, the command it ran and what it returned, or a screenshot of the result. Reviewing evidence is faster than re-running the verification yourself, and it works for sessions you weren't watching.

48 53

en/chrome.md +1 −1

Details

62 </Step>62 </Step>

63</Steps>63</Steps>

64 64

~~65Run `/chrome` at any time to check the connection status, manage permissions, or reconnect the extension.~~65Run `/chrome` at any time to check the connection status, manage permissions, reconnect the extension, or choose which connected browser to use. If more than one browser is connected when a browser action starts, Claude prompts you to pick one.

66 66

67For VS Code, see [browser automation in VS Code](/en/vs-code#automate-browser-tasks-with-chrome).67For VS Code, see [browser automation in VS Code](/en/vs-code#automate-browser-tasks-with-chrome).

68 68

en/claude-directory.md +26 −2

Details

4 4

5# Explore the .claude directory5# Explore the .claude directory

6 6

~~7> Where Claude Code reads CLAUDE.md, settings.json, hooks, skills, commands, subagents, rules, and auto memory. Explore the .claude directory in your project and ~/.claude in your home directory.~~7> Where Claude Code reads CLAUDE.md, settings.json, hooks, skills, commands, subagents, workflows, rules, and auto memory. Explore the .claude directory in your project and ~/.claude in your home directory.

8 8

9export const ClaudeExplorer = () => {9export const ClaudeExplorer = () => {

10 const A = useMemo(() => ({href, children}) => <a href={href} style={{10 const A = useMemo(() => ({href, children}) => <a href={href} style={{

361 361

362Every finding must include a concrete fix.`362Every finding must include a concrete fix.`

363 }]363 }]

364 }, {

365 id: 'workflows',

366 label: 'workflows/',

367 type: 'folder',

368 icon: 'folder',

369 color: '#C46686',

370 oneLiner: 'Dynamic workflow scripts that orchestrate many subagents',

371 when: 'Loaded at startup; each file becomes a /<name> command',

372 description: <>Each <C>.js</C> file is a <A href="/en/workflows">dynamic workflow</A>: a script the runtime executes to spawn and coordinate many subagents. Workflows are written by Claude and saved here from <C>/workflows</C> rather than authored from scratch.</>,

373 tips: [<>Save a run from <C>/workflows</C> with <C>s</C> to create one of these</>, <>A project workflow takes precedence over a personal one in <C>~/.claude/workflows/</C> with the same name</>],

374 docsLink: '/en/workflows'

364 }, {375 }, {

365 id: 'agent-memory',376 id: 'agent-memory',

366 label: 'agent-memory/',377 label: 'agent-memory/',

664 description: 'Subagents defined here are available across all your projects. Same format as project agents.',675 description: 'Subagents defined here are available across all your projects. Same format as project agents.',

665 docsLink: '/en/sub-agents',676 docsLink: '/en/sub-agents',

666 children: []677 children: []

678 }, {

679 id: 'global-workflows',

680 label: 'workflows/',

681 type: 'folder',

682 icon: 'folder',

683 color: '#C46686',

684 oneLiner: 'Personal dynamic workflows available in every project',

685 when: 'Loaded at startup; each file becomes a /<name> command',

686 description: <>Workflow scripts saved here are available across all your projects. A project workflow with the same name in <C>.claude/workflows/</C> takes precedence.</>,

687 docsLink: '/en/workflows',

688 children: []

667 }, {689 }, {

668 id: 'global-agent-memory',690 id: 'global-agent-memory',

669 label: 'agent-memory/',691 label: 'agent-memory/',

1447| Define a specialized subagent with its own tools | `agents/*.md` | project or global | [Subagents](/en/sub-agents) |1469| Define a specialized subagent with its own tools | `agents/*.md` | project or global | [Subagents](/en/sub-agents) |

1470| Orchestrate many subagents from a script | `workflows/*.js` | project or global | [Dynamic workflows](/en/workflows) |

1449| Change how Claude formats responses | `output-styles/*.md` | project or global | [Output styles](/en/output-styles) |1472| Change how Claude formats responses | `output-styles/*.md` | project or global | [Output styles](/en/output-styles) |

1450 1473

1465Click a filename to open that node in the explorer above.1488Click a filename to open that node in the explorer above.

1466 1489

1468| --------------------------------------------------- | ------------------ | ------ | ----------------------------------------------------- | --------------------------------------------------------------- |1491| --------------------------------------------------- | ------------------ | ------ | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------- |

1470| [`rules/*.md`](#ce-rules) | Project and global | ✓ | Topic-scoped instructions, optionally path-gated | [Rules](/en/memory#organize-rules-with-claude/rules/) |1493| [`rules/*.md`](#ce-rules) | Project and global | ✓ | Topic-scoped instructions, optionally path-gated | [Rules](/en/memory#organize-rules-with-claude/rules/) |

1476| [`commands/*.md`](#ce-commands) | Project and global | ✓ | Single-file prompts; same mechanism as skills | [Skills](/en/skills) |1499| [`commands/*.md`](#ce-commands) | Project and global | ✓ | Single-file prompts; same mechanism as skills | [Skills](/en/skills) |

1477| [`output-styles/*.md`](#ce-output-styles) | Project and global | ✓ | Custom system-prompt sections | [Output styles](/en/output-styles) |1500| [`output-styles/*.md`](#ce-output-styles) | Project and global | ✓ | Custom system-prompt sections | [Output styles](/en/output-styles) |

1478| [`agents/*.md`](#ce-agents) | Project and global | ✓ | Subagent definitions with their own prompt and tools | [Subagents](/en/sub-agents) |1501| [`agents/*.md`](#ce-agents) | Project and global | ✓ | Subagent definitions with their own prompt and tools | [Subagents](/en/sub-agents) |

1502| [`workflows/*.js`](#ce-workflows) | Project and global | ✓ | Dynamic workflow scripts written by Claude and saved from `/workflows`; each file becomes a `/<name>` command | [Dynamic workflows](/en/workflows) |

en/cli-reference.md +3 −1

Details

56| `--append-system-prompt-file` | Load additional system prompt text from a file and append to the default prompt | `claude --append-system-prompt-file ./extra-rules.txt` |56| `--append-system-prompt-file` | Load additional system prompt text from a file and append to the default prompt | `claude --append-system-prompt-file ./extra-rules.txt` |

57| `--bare` | Minimal mode: skip auto-discovery of hooks, skills, plugins, MCP servers, auto memory, and CLAUDE.md so scripted calls start faster. Claude has access to Bash, file read, and file edit tools. Sets [`CLAUDE_CODE_SIMPLE`](/en/env-vars). See [bare mode](/en/headless#start-faster-with-bare-mode) | `claude --bare -p "query"` |57| `--bare` | Minimal mode: skip auto-discovery of hooks, skills, plugins, MCP servers, auto memory, and CLAUDE.md so scripted calls start faster. Claude has access to Bash, file read, and file edit tools. Sets [`CLAUDE_CODE_SIMPLE`](/en/env-vars). See [bare mode](/en/headless#start-faster-with-bare-mode) | `claude --bare -p "query"` |

59| `--bg` | Start the session as a [background agent](/en/agent-view) and return immediately. Prints the session ID and management commands. Combine with `--agent` to run a specific subagent | `claude --bg "investigate the flaky test"` |59| `--bg` | Start the session as a [background agent](/en/agent-view) and return immediately. Prints the session ID and management commands. Combine with `--exec` to run a shell command as a background job instead of a Claude session, or with `--agent` to run a specific subagent | `claude --bg "investigate the flaky test"` |

60| `--channels` | (Research preview) MCP servers whose [channel](/en/channels) notifications Claude should listen for in this session. Space-separated list of `plugin:<name>@<marketplace>` entries. Requires Claude.ai authentication | `claude --channels plugin:my-notifier@my-marketplace` |60| `--channels` | (Research preview) MCP servers whose [channel](/en/channels) notifications Claude should listen for in this session. Space-separated list of `plugin:<name>@<marketplace>` entries. Requires Claude.ai authentication | `claude --channels plugin:my-notifier@my-marketplace` |

69| `--effort` | Set the [effort level](/en/model-config#adjust-effort-level) for the current session. Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model. Overrides the [`effortLevel`](/en/settings#available-settings) setting for this session and does not persist | `claude --effort high` |69| `--effort` | Set the [effort level](/en/model-config#adjust-effort-level) for the current session. Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model. Overrides the [`effortLevel`](/en/settings#available-settings) setting for this session and does not persist | `claude --effort high` |

70| `--enable-auto-mode` | {/* max-version: 2.1.110 */}Removed in v2.1.111. Auto mode is now in the `Shift+Tab` cycle by default; use `--permission-mode auto` to start in it | `claude --permission-mode auto` |70| `--enable-auto-mode` | {/* max-version: 2.1.110 */}Removed in v2.1.111. Auto mode is now in the `Shift+Tab` cycle by default; use `--permission-mode auto` to start in it | `claude --permission-mode auto` |

71| `--exclude-dynamic-system-prompt-sections` | Move per-machine sections from the system prompt (working directory, environment info, memory paths, git-repo flag) into the first user message. Improves prompt-cache reuse across different users and machines running the same task. Only applies with the default system prompt; ignored when `--system-prompt` or `--system-prompt-file` is set. Use with `-p` for scripted, multi-user workloads | `claude -p --exclude-dynamic-system-prompt-sections "query"` |71| `--exclude-dynamic-system-prompt-sections` | Move per-machine sections from the system prompt (working directory, environment info, memory paths, git-repo flag) into the first user message. Improves prompt-cache reuse across different users and machines running the same task. Only applies with the default system prompt; ignored when `--system-prompt` or `--system-prompt-file` is set. Use with `-p` for scripted, multi-user workloads | `claude -p --exclude-dynamic-system-prompt-sections "query"` |

72| `--exec` | Run a shell command as a PTY-backed background job instead of starting a Claude session. Use with `--bg` to launch from the shell | `claude --bg --exec 'pytest -x'` |

72| `--fallback-model` | Enable automatic fallback to a specified model when the default model is overloaded or not available, for example a retired model. Takes effect in print mode (`-p`) and in [background sessions](/en/agent-view), which run non-interactively; ignored in an interactive session | `claude -p --fallback-model sonnet "query"` |73| `--fallback-model` | Enable automatic fallback to a specified model when the default model is overloaded or not available, for example a retired model. Takes effect in print mode (`-p`) and in [background sessions](/en/agent-view), which run non-interactively; ignored in an interactive session | `claude -p --fallback-model sonnet "query"` |

73| `--fork-session` | When resuming, create a new session ID instead of reusing the original (use with `--resume` or `--continue`) | `claude --resume abc123 --fork-session` |74| `--fork-session` | When resuming, create a new session ID instead of reusing the original (use with `--resume` or `--continue`) | `claude --resume abc123 --fork-session` |

74| `--from-pr` | Resume sessions linked to a specific pull request. Accepts a PR number, a GitHub or GitHub Enterprise PR URL, a GitLab merge request URL, or a Bitbucket pull request URL. Sessions are linked automatically when Claude creates the pull request | `claude --from-pr 123` |75| `--from-pr` | Resume sessions linked to a specific pull request. Accepts a PR number, a GitHub or GitHub Enterprise PR URL, a GitLab merge request URL, or a Bitbucket pull request URL. Sessions are linked automatically when Claude creates the pull request | `claude --from-pr 123` |

93| `--plugin-dir` | Load a plugin from a directory or `.zip` archive for this session only. Each flag takes one path. Repeat the flag for multiple plugins: `--plugin-dir A --plugin-dir B.zip` | `claude --plugin-dir ./my-plugin` |94| `--plugin-dir` | Load a plugin from a directory or `.zip` archive for this session only. Each flag takes one path. Repeat the flag for multiple plugins: `--plugin-dir A --plugin-dir B.zip` | `claude --plugin-dir ./my-plugin` |

94| `--plugin-url` | Fetch a plugin `.zip` archive from a URL for this session only. Repeat the flag for multiple plugins, or pass space-separated URLs in a single quoted value | `claude --plugin-url https://example.com/plugin.zip` |95| `--plugin-url` | Fetch a plugin `.zip` archive from a URL for this session only. Repeat the flag for multiple plugins, or pass space-separated URLs in a single quoted value | `claude --plugin-url https://example.com/plugin.zip` |

97| `--prompt-suggestions` | Emit a `prompt_suggestion` message after each turn with a predicted next user prompt. Requires `--print`, `--output-format stream-json`, and `--verbose`. See [Prompt suggestions](/en/interactive-mode#prompt-suggestions) | `claude -p --prompt-suggestions --output-format stream-json --verbose "query"` |

97| `--remote-control`, `--rc` | Start an interactive session with [Remote Control](/en/remote-control#start-a-remote-control-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"` |99| `--remote-control`, `--rc` | Start an interactive session with [Remote Control](/en/remote-control#start-a-remote-control-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"` |

98| `--remote-control-session-name-prefix <prefix>` | Prefix for auto-generated [Remote Control](/en/remote-control) session names when no explicit name is set. Defaults to your machine's hostname, producing names like `myhost-graceful-unicorn`. Set `CLAUDE_REMOTE_CONTROL_SESSION_NAME_PREFIX` for the same effect | `claude remote-control --remote-control-session-name-prefix dev-box` |100| `--remote-control-session-name-prefix <prefix>` | Prefix for auto-generated [Remote Control](/en/remote-control) session names when no explicit name is set. Defaults to your machine's hostname, producing names like `myhost-graceful-unicorn`. Set `CLAUDE_REMOTE_CONTROL_SESSION_NAME_PREFIX` for the same effect | `claude remote-control --remote-control-session-name-prefix dev-box` |

en/code-review.md +1 −1

Details

283 283

284`/code-review ultra --fix` runs the deeper [ultrareview](/en/ultrareview) in the cloud, then applies its findings to your working tree when they arrive back in your session.284`/code-review ultra --fix` runs the deeper [ultrareview](/en/ultrareview) in the cloud, then applies its findings to your working tree when they arrive back in your session.

285 285

286The command was named `/simplify` before v2.1.147, when it applied fixes by default. `/simplify` still works and is equivalent to `/code-review --fix`.286The command was named `/simplify` before v2.1.147, when it applied fixes by default. {/* min-version: 2.1.154 */}From v2.1.154, `/simplify` runs a separate cleanup-only review that applies fixes without hunting for bugs. If you scripted `/simplify` for bug-finding, switch to `/code-review --fix`, which is unchanged.

287 287

288## Related resources288## Related resources

289 289

en/commands.md +12 −4

Details

30 30

31## All commands31## All commands

32 32

33The table below lists all the commands included in Claude Code. Entries marked **[Skill](/en/skills#bundled-skills)** are bundled skills. They use the same mechanism as skills you write yourself: a prompt handed to Claude, which Claude can also invoke automatically when relevant. Everything else is a built-in command whose behavior is coded into the CLI. To add your own commands, see [skills](/en/skills).33The table below lists all the commands included in Claude Code. Most are built-in commands whose behavior is coded into the CLI. Two kinds of entries are marked:

35* **[Skill](/en/skills#bundled-skills)**: a bundled skill. It works like skills you write yourself: a prompt handed to Claude, which Claude can also invoke automatically when relevant.

36* **[Workflow](/en/workflows#bundled-workflows)**: a bundled [dynamic workflow](/en/workflows) that fans work out across many subagents and runs in the background.

38To add your own commands, see [skills](/en/skills).

34 39

35In the table below, `<arg>` indicates a required argument and `[arg]` indicates an optional one.40In the table below, `<arg>` indicates a required argument and `[arg]` indicates an optional one.

36 41

51| `/claude-api [migrate\|managed-agents-onboard]` | **[Skill](/en/skills#bundled-skills).** Load Claude API reference material for your project's language (Python, TypeScript, Java, Go, Ruby, C#, PHP, or cURL) and Managed Agents reference. Covers tool use, streaming, batches, structured outputs, and common pitfalls. Also activates automatically when your code imports `anthropic` or `@anthropic-ai/sdk`. Run `/claude-api migrate` to upgrade existing Claude API code to a newer model: Claude asks which files to scan and which model to target, then updates model IDs, thinking configuration, and other parameters that changed between versions. Run `/claude-api managed-agents-onboard` for an interactive walkthrough that creates a new Managed Agent from scratch |56| `/claude-api [migrate\|managed-agents-onboard]` | **[Skill](/en/skills#bundled-skills).** Load Claude API reference material for your project's language (Python, TypeScript, Java, Go, Ruby, C#, PHP, or cURL) and Managed Agents reference. Covers tool use, streaming, batches, structured outputs, and common pitfalls. Also activates automatically when your code imports `anthropic` or `@anthropic-ai/sdk`. Run `/claude-api migrate` to upgrade existing Claude API code to a newer model: Claude asks which files to scan and which model to target, then updates model IDs, thinking configuration, and other parameters that changed between versions. Run `/claude-api managed-agents-onboard` for an interactive walkthrough that creates a new Managed Agent from scratch |

52| `/clear [name]` | Start a new conversation with empty context. The previous conversation stays available in `/resume`. Pass a name to label the previous conversation in the `/resume` picker. To free up context while continuing the same conversation, use `/compact` instead. Aliases: `/reset`, `/new` |57| `/clear [name]` | Start a new conversation with empty context. The previous conversation stays available in `/resume`. Pass a name to label the previous conversation in the `/resume` picker. To free up context while continuing the same conversation, use `/compact` instead. Aliases: `/reset`, `/new` |

53| `/code-review [low\|medium\|high\|xhigh\|max\|ultra] [--fix] [--comment] [target]` | **[Skill](/en/skills#bundled-skills).** Review the current diff for correctness bugs and for reuse, simplification, and efficiency cleanups. Pass `--fix` to apply findings to your working tree, `--comment` to post them as inline GitHub PR comments, or `ultra` to run a deep [cloud review](/en/ultrareview). `/simplify` is equivalent to `/code-review --fix`. See [Review a diff locally](/en/code-review#review-a-diff-locally) for effort levels and targeting |58| `/code-review [low\|medium\|high\|xhigh\|max\|ultra] [--fix] [--comment] [target]` | **[Skill](/en/skills#bundled-skills).** Review the current diff for correctness bugs and for reuse, simplification, and efficiency cleanups. Pass `--fix` to apply findings to your working tree, `--comment` to post them as inline GitHub PR comments, or `ultra` to run a deep [cloud review](/en/ultrareview). {/* min-version: 2.1.154 */}From v2.1.154, `/simplify` runs a separate cleanup-only review that applies fixes without hunting for bugs. See [Review a diff locally](/en/code-review#review-a-diff-locally) for effort levels and targeting |

54| `/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, or run with no argument to pick a random color. When [Remote Control](/en/remote-control) is connected, the color syncs to claude.ai/code |59| `/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, or run with no argument to pick a random color. When [Remote Control](/en/remote-control) is connected, the color syncs to claude.ai/code |

55| `/compact [instructions]` | Free up context by summarizing the conversation so far. Optionally pass focus instructions for the summary. See [how compaction handles rules, skills, and memory files](/en/context-window#what-survives-compaction) |60| `/compact [instructions]` | Free up context by summarizing the conversation so far. Optionally pass focus instructions for the summary. See [how compaction handles rules, skills, and memory files](/en/context-window#what-survives-compaction) |

56| `/config` | Open the [Settings](/en/settings) interface to adjust theme, model, [output style](/en/output-styles), and other preferences. Alias: `/settings` |61| `/config` | Open the [Settings](/en/settings) interface to adjust theme, model, [output style](/en/output-styles), and other preferences. Alias: `/settings` |

58| `/copy [N]` | Copy the last assistant response to clipboard. Pass a number `N` to copy the Nth-latest response: `/copy 2` copies the second-to-last. When code blocks are present, shows an interactive picker to select individual blocks or the full response. Press `w` in the picker to write the selection to a file instead of the clipboard, which is useful over SSH |63| `/copy [N]` | Copy the last assistant response to clipboard. Pass a number `N` to copy the Nth-latest response: `/copy 2` copies the second-to-last. When code blocks are present, shows an interactive picker to select individual blocks or the full response. Press `w` in the picker to write the selection to a file instead of the clipboard, which is useful over SSH |

60| `/debug [description]` | **[Skill](/en/skills#bundled-skills).** Enable debug logging for the current session and troubleshoot issues by reading the session debug log. Debug logging is off by default unless you started with `claude --debug`, so running `/debug` mid-session starts capturing logs from that point forward. Optionally describe the issue to focus the analysis |65| `/debug [description]` | **[Skill](/en/skills#bundled-skills).** Enable debug logging for the current session and troubleshoot issues by reading the session debug log. Debug logging is off by default unless you started with `claude --debug`, so running `/debug` mid-session starts capturing logs from that point forward. Optionally describe the issue to focus the analysis |

66| `/deep-research <question>` | **[Workflow](/en/workflows#bundled-workflows).** Fan out web searches on a question, fetch and cross-check sources, and synthesize a cited report |

61| `/desktop` | Continue the current session in the Claude Code Desktop app. Requires macOS or Windows and a Claude subscription. Alias: `/app` |67| `/desktop` | Continue the current session in the Claude Code Desktop app. Requires macOS or Windows and a Claude subscription. Alias: `/app` |

62| `/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 |68| `/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 |

63| `/doctor` | Diagnose and verify your Claude Code installation and settings. Results show with status icons. Press `f` to have Claude fix any reported issues |69| `/doctor` | Diagnose and verify your Claude Code installation and settings. Results show with status icons. Press `f` to have Claude fix any reported issues |

64| `/effort [level\|auto]` | Set the model [effort level](/en/model-config#adjust-effort-level). Accepts `low`, `medium`, `high`, `xhigh`, or `max`; available levels depend on the model and `max` is session-only. `auto` resets to the model default. Without an argument, opens an interactive slider; use left and right arrows to pick a level and `Enter` to apply. Takes effect immediately without waiting for the current response to finish |70| `/effort [level\|auto]` | Set the model [effort level](/en/model-config#adjust-effort-level). Accepts `low`, `medium`, `high`, `xhigh`, `max`, or `ultracode`; available levels depend on the model, and `max` and `ultracode` are session-only. `ultracode` is a Claude Code setting that combines `xhigh` reasoning with automatic [workflow](/en/workflows#let-claude-decide-with-ultracode) orchestration. `auto` resets to the model default. Without an argument, opens an interactive slider; use left and right arrows to pick a level and `Enter` to apply. Takes effect immediately without waiting for the current response to finish |

65| `/exit` | Exit the CLI. In an attached [background session](/en/agent-view#attach-to-a-session), this detaches and the session keeps running. Alias: `/quit` |71| `/exit` | Exit the CLI. In an attached [background session](/en/agent-view#attach-to-a-session), this detaches and the session keeps running. Alias: `/quit` |

66| `/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 |72| `/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 |

67| `/fast [on\|off]` | Toggle [fast mode](/en/fast-mode) on or off |73| `/fast [on\|off]` | Toggle [fast mode](/en/fast-mode) on or off |

84| `/mcp` | Manage MCP server connections and OAuth authentication |90| `/mcp` | Manage MCP server connections and OAuth authentication |

85| `/memory` | Edit `CLAUDE.md` memory files, enable or disable [auto-memory](/en/memory#auto-memory), and view auto-memory entries |91| `/memory` | Edit `CLAUDE.md` memory files, enable or disable [auto-memory](/en/memory#auto-memory), and view auto-memory entries |

87| `/model [model]` | Set the AI model for the current session. For models that support it, use left/right arrows to [adjust effort level](/en/model-config#adjust-effort-level). With no argument, opens a picker; press `d` on a row to also save that model as the default for new sessions. The picker asks for confirmation when the conversation has prior output, since the next response re-reads the full history without cached context. Once confirmed, the change applies without waiting for the current response to finish |93| `/model [model]` | Switch the AI model and save it as your default for new sessions. For models that support it, use left/right arrows to [adjust effort level](/en/model-config#adjust-effort-level). With no argument, opens a picker; press `s` on a row to switch for the current session only. The picker asks for confirmation when the conversation has prior output, since the next response re-reads the full history without cached context. Once confirmed, the change applies without waiting for the current response to finish |

89| `/permissions` | Manage allow, ask, and deny rules for tool permissions. Opens an interactive dialog where you can view rules by scope, add or remove rules, manage working directories, and review [recent auto mode denials](/en/auto-mode-config#review-denials). Alias: `/allowed-tools` |95| `/permissions` | Manage allow, ask, and deny rules for tool permissions. Opens an interactive dialog where you can view rules by scope, add or remove rules, manage working directories, and review [recent auto mode denials](/en/auto-mode-config#review-denials). Alias: `/allowed-tools` |

90| `/plan [description]` | Enter plan mode directly from the prompt. Pass an optional description to enter plan mode and immediately start with that task, for example `/plan fix the auth bug` |96| `/plan [description]` | Enter plan mode directly from the prompt. Pass an optional description to enter plan mode and immediately start with that task, for example `/plan fix the auth bug` |

111| `/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 |117| `/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 |

112| `/setup-bedrock` | Configure [Amazon Bedrock](/en/amazon-bedrock) authentication, region, and model pins through an interactive wizard. Only visible when `CLAUDE_CODE_USE_BEDROCK=1` is set. First-time Bedrock users can also access this wizard from the login screen |118| `/setup-bedrock` | Configure [Amazon Bedrock](/en/amazon-bedrock) authentication, region, and model pins through an interactive wizard. Only visible when `CLAUDE_CODE_USE_BEDROCK=1` is set. First-time Bedrock users can also access this wizard from the login screen |

113| `/setup-vertex` | Configure [Google Vertex AI](/en/google-vertex-ai) authentication, project, region, and model pins through an interactive wizard. Only visible when `CLAUDE_CODE_USE_VERTEX=1` is set. First-time Vertex AI users can also access this wizard from the login screen |119| `/setup-vertex` | Configure [Google Vertex AI](/en/google-vertex-ai) authentication, project, region, and model pins through an interactive wizard. Only visible when `CLAUDE_CODE_USE_VERTEX=1` is set. First-time Vertex AI users can also access this wizard from the login screen |

120| `/simplify [target]` | {/* min-version: 2.1.154 */}**[Skill](/en/skills#bundled-skills).** Review the changed code for cleanup opportunities and apply the fixes. Four review [agents](/en/sub-agents) run in parallel, covering reuse of existing helpers, simplification, efficiency, and whether the change sits at the right level of abstraction. From v2.1.154, the review does not look for correctness bugs. Use `/code-review` to find bugs. On earlier versions `/simplify` is equivalent to `/code-review --fix`. Pass a path or PR reference to review a specific target |

114| `/skills` | List available [skills](/en/skills). Press `t` to sort by token count. Press `Space` to [hide a skill from Claude or the `/` menu](/en/skills#override-skill-visibility-from-settings), then `Enter` to save |121| `/skills` | List available [skills](/en/skills). Press `t` to sort by token count. Press `Space` to [hide a skill from Claude or the `/` menu](/en/skills#override-skill-visibility-from-settings), then `Enter` to save |

116| `/status` | Open the Settings interface (Status tab) showing version, model, account, and connectivity. Works while Claude is responding, without waiting for the current response to finish |123| `/status` | Open the Settings interface (Status tab) showing version, model, account, and connectivity. Works while Claude is responding, without waiting for the current response to finish |

132| `/vim` | {/* max-version: 2.1.91 */}Removed in v2.1.92. To toggle between Vim and Normal editing modes, use `/config` → Editor mode |139| `/vim` | {/* max-version: 2.1.91 */}Removed in v2.1.92. To toggle between Vim and Normal editing modes, use `/config` → Editor mode |

133| `/voice [hold\|tap\|off]` | Toggle [voice dictation](/en/voice-dictation), or enable it in a specific mode. Requires a Claude.ai account |140| `/voice [hold\|tap\|off]` | Toggle [voice dictation](/en/voice-dictation), or enable it in a specific mode. Requires a Claude.ai account |

134| `/web-setup` | Connect your GitHub account to [Claude Code on the web](/en/web-quickstart#connect-from-your-terminal) using your local `gh` CLI credentials. `/schedule` prompts for this automatically if GitHub isn't connected |141| `/web-setup` | Connect your GitHub account to [Claude Code on the web](/en/web-quickstart#connect-from-your-terminal) using your local `gh` CLI credentials. `/schedule` prompts for this automatically if GitHub isn't connected |

142| `/workflows` | Open the [workflow](/en/workflows#watch-the-run) progress view to watch, pause, resume, or save running and completed workflows |

135 143

136## MCP prompts144## MCP prompts

137 145

en/desktop.md +3 −3

Details

78 78

79<span id="auto-mode-availability" />79<span id="auto-mode-availability" />

80 80

~~81Auto mode is a research preview available to all users on the Anthropic API. It is not available on third-party providers. It requires Claude Sonnet 4.6, Opus 4.6, or Opus 4.7.~~81Auto mode is a research preview available to all users on the Anthropic API. It is not available on third-party providers. It requires Claude Opus 4.6 or later, or Sonnet 4.6.

82 82

83<Tip title="Best practice">83<Tip title="Best practice">

84 Start complex tasks in Plan mode so Claude maps out an approach before making changes. Once you approve the plan, switch to Auto accept edits or Ask permissions to execute it. See [explore first, then plan, then code](/en/best-practices#explore-first-then-plan-then-code) for more on this workflow.84 Start complex tasks in Plan mode so Claude maps out an approach before making changes. Once you approve the plan, switch to Auto accept edits or Ask permissions to execute it. See [explore first, then plan, then code](/en/best-practices#explore-first-then-plan-then-code) for more on this workflow.

306 306

307### Watch background tasks307### Watch background tasks

308 308

309The tasks pane shows the background work running inside the current session: subagents, background shell commands, and workflows. Open it from the **Views** menu or drag it into your layout.309The tasks pane shows the background work running inside the current session: subagents, background shell commands, and dynamic workflows. Open it from the **Views** menu or drag it into your layout.

310 310

311Click any entry to see its output in the subagent pane or stop it. To see what other sessions are doing, use the [sidebar](#work-in-parallel-with-sessions).311Click any entry to see its output in the subagent pane or stop it. To see what other sessions are doing, use the [sidebar](#work-in-parallel-with-sessions).

312 312

520 520

521To set environment variables for local sessions and dev servers on any platform, open the environment dropdown in the prompt box, hover over **Local**, and click the gear icon to open the local environment editor. Variables you save here are stored encrypted on your machine and apply to every local session and preview server you start. You can also add variables to the `env` key in your `~/.claude/settings.json` file, though these reach Claude sessions only and not dev servers. See [environment variables](/en/env-vars) for the full list of supported variables.521To set environment variables for local sessions and dev servers on any platform, open the environment dropdown in the prompt box, hover over **Local**, and click the gear icon to open the local environment editor. Variables you save here are stored encrypted on your machine and apply to every local session and preview server you start. You can also add variables to the `env` key in your `~/.claude/settings.json` file, though these reach Claude sessions only and not dev servers. See [environment variables](/en/env-vars) for the full list of supported variables.

522 522

523[Extended thinking](/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. To disable thinking entirely, set `MAX_THINKING_TOKENS` to `0` in the local environment editor. On models with [adaptive reasoning](/en/model-config#adjust-effort-level), any other `MAX_THINKING_TOKENS` value is ignored because adaptive reasoning controls thinking depth instead. On Opus 4.6 and Sonnet 4.6, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` to `1` to use a fixed thinking budget; Opus 4.7 always uses adaptive reasoning and has no fixed-budget mode.523[Extended thinking](/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. To disable thinking entirely, set `MAX_THINKING_TOKENS` to `0` in the local environment editor. On models with [adaptive reasoning](/en/model-config#adjust-effort-level), any other `MAX_THINKING_TOKENS` value is ignored because adaptive reasoning controls thinking depth instead. On Opus 4.6 and Sonnet 4.6, set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` to `1` to use a fixed thinking budget; Opus 4.7 and later always use adaptive reasoning and have no fixed-budget mode.

524 524

525### Remote sessions525### Remote sessions

526 526

en/discover-plugins.md +1 −1

Details

149 * **Marketplaces**: add, remove, or update your added marketplaces149 * **Marketplaces**: add, remove, or update your added marketplaces

150 * **Errors**: view any plugin loading errors150 * **Errors**: view any plugin loading errors

151 151

152 Go to the **Discover** tab to see plugins from the marketplace you just added.152 Go to the **Discover** tab to see plugins from the marketplace you just added. {/* min-version: 2.1.154 */}Plugins marked as relevant to your current working directory are pinned at the top with a **suggested for this directory** label.

153 </Step>153 </Step>

154 154

155 <Step title="Install a plugin">155 <Step title="Install a plugin">

en/env-vars.md +7 −6

Details

129| `BASH_MAX_OUTPUT_LENGTH` | Maximum number of characters in bash outputs before the full output is saved to a file and Claude receives the path plus a short preview. See [Bash tool behavior](/en/tools-reference#bash-tool-behavior) |129| `BASH_MAX_OUTPUT_LENGTH` | Maximum number of characters in bash outputs before the full output is saved to a file and Claude receives the path plus a short preview. See [Bash tool behavior](/en/tools-reference#bash-tool-behavior) |

130| `BASH_MAX_TIMEOUT_MS` | Maximum timeout the model can set for long-running bash commands (default: 600000, or 10 minutes) |130| `BASH_MAX_TIMEOUT_MS` | Maximum timeout the model can set for long-running bash commands (default: 600000, or 10 minutes) |

131| `CCR_FORCE_BUNDLE` | Set to `1` to force [`claude --remote`](/en/claude-code-on-the-web#send-local-repositories-without-github) to bundle and upload your local repository even when GitHub access is available |131| `CCR_FORCE_BUNDLE` | Set to `1` to force [`claude --remote`](/en/claude-code-on-the-web#send-local-repositories-without-github) to bundle and upload your local repository even when GitHub access is available |

132| `CLAUDECODE` | Set to `1` in subprocesses Claude Code spawns (Bash and PowerShell tools, tmux sessions, [hook](/en/hooks) commands, [status line](/en/statusline) commands). Use to detect when a script is running inside a subprocess spawned by Claude Code |132| `CLAUDECODE` | Set to `1` in subprocesses Claude Code spawns (Bash and PowerShell tools, tmux sessions, [hook](/en/hooks) commands, [status line](/en/statusline) commands, stdio [MCP server](/en/mcp) subprocesses). Use to detect when a script is running inside a subprocess spawned by Claude Code |

133| `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` | Set to `1` to disable all built-in [subagent](/en/sub-agents) types such as Explore and Plan. Only applies in non-interactive mode (the `-p` flag). Useful for SDK users who want a blank slate |133| `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` | Set to `1` to disable all built-in [subagent](/en/sub-agents) types such as Explore and Plan. Only applies in non-interactive mode (the `-p` flag). Useful for SDK users who want a blank slate |

134| `CLAUDE_AGENT_SDK_MCP_NO_PREFIX` | Set to `1` to skip the `mcp__<server>__` prefix on tool names from SDK-created MCP servers. Tools use their original names. SDK usage only |134| `CLAUDE_AGENT_SDK_MCP_NO_PREFIX` | Set to `1` to skip the `mcp__<server>__` prefix on tool names from SDK-created MCP servers. Tools use their original names. SDK usage only |

135| `CLAUDE_ASYNC_AGENT_STALL_TIMEOUT_MS` | Stall timeout in milliseconds for background subagents. Default `600000` (10 minutes). The timer resets on each streaming progress event; if no progress arrives within the window, the subagent is aborted and the task is marked failed, surfacing any partial result to the parent |135| `CLAUDE_ASYNC_AGENT_STALL_TIMEOUT_MS` | Stall timeout in milliseconds for background subagents. Default `600000` (10 minutes). The timer resets on each streaming progress event; if no progress arrives within the window, the subagent is aborted and the task is marked failed, surfacing any partial result to the parent |

150| `CLAUDE_CODE_DEBUG_LOGS_DIR` | Override the debug log file path. Despite the name, this is a file path, not a directory. Requires debug mode to be enabled separately via `--debug`, `/debug`, or the `DEBUG` environment variable: setting this variable alone does not enable logging. The [`--debug-file`](/en/cli-reference#cli-flags) flag does both at once. Defaults to `~/.claude/debug/<session-id>.txt` |150| `CLAUDE_CODE_DEBUG_LOGS_DIR` | Override the debug log file path. Despite the name, this is a file path, not a directory. Requires debug mode to be enabled separately via `--debug`, `/debug`, or the `DEBUG` environment variable: setting this variable alone does not enable logging. The [`--debug-file`](/en/cli-reference#cli-flags) flag does both at once. Defaults to `~/.claude/debug/<session-id>.txt` |

151| `CLAUDE_CODE_DEBUG_LOG_LEVEL` | Minimum log level written to the debug log file. Values: `verbose`, `debug` (default), `info`, `warn`, `error`. Set to `verbose` to include high-volume diagnostics like full status line command output, or raise to `error` to reduce noise |151| `CLAUDE_CODE_DEBUG_LOG_LEVEL` | Minimum log level written to the debug log file. Values: `verbose`, `debug` (default), `info`, `warn`, `error`. Set to `verbose` to include high-volume diagnostics like full status line command output, or raise to `error` to reduce noise |

152| `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 |152| `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 |

153| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/en/model-config#adjust-effort-level) on Opus 4.6 and Sonnet 4.6 and fall back to the fixed thinking budget controlled by `MAX_THINKING_TOKENS`. {/* min-version: 2.1.111 */}Has no effect on Opus 4.7, which always uses adaptive reasoning |153| `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | Set to `1` to disable [adaptive reasoning](/en/model-config#adjust-effort-level) on Opus 4.6 and Sonnet 4.6 and fall back to the fixed thinking budget controlled by `MAX_THINKING_TOKENS`. {/* min-version: 2.1.111 */}Has no effect on Opus 4.7 and later, which always use adaptive reasoning |

154| `CLAUDE_CODE_DISABLE_AGENT_VIEW` | Set to `1` to turn off [background agents and agent view](/en/agent-view): `claude agents`, `--bg`, `/background`, and the on-demand supervisor. Equivalent to the [`disableAgentView`](/en/settings#available-settings) setting |154| `CLAUDE_CODE_DISABLE_AGENT_VIEW` | Set to `1` to turn off [background agents and agent view](/en/agent-view): `claude agents`, `--bg`, `/background`, and the on-demand supervisor. Equivalent to the [`disableAgentView`](/en/settings#available-settings) setting |

155| `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN` | Set to `1` to disable [fullscreen rendering](/en/fullscreen) and use the classic main-screen renderer. The conversation stays in your terminal's native scrollback so `Cmd+f` and tmux copy mode work as usual. Takes precedence over `CLAUDE_CODE_NO_FLICKER` and the [`tui`](/en/settings#available-settings) setting. You can also switch with `/tui default` |155| `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN` | Set to `1` to disable [fullscreen rendering](/en/fullscreen) and use the classic main-screen renderer. The conversation stays in your terminal's native scrollback so `Cmd+f` and tmux copy mode work as usual. Takes precedence over `CLAUDE_CODE_NO_FLICKER` and the [`tui`](/en/settings#available-settings) setting. You can also switch with `/tui default` |

156| `CLAUDE_CODE_DISABLE_ATTACHMENTS` | Set to `1` to disable attachment processing. File mentions with `@` syntax are sent as plain text instead of being expanded into file content |156| `CLAUDE_CODE_DISABLE_ATTACHMENTS` | Set to `1` to disable attachment processing. File mentions with `@` syntax are sent as plain text instead of being expanded into file content |

172| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Set to `1` to disable automatic terminal title updates based on conversation context |172| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Set to `1` to disable automatic terminal title updates based on conversation context |

173| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to force-disable [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) regardless of model support or other settings. More direct than `MAX_THINKING_TOKENS=0` |173| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to force-disable [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) regardless of model support or other settings. More direct than `MAX_THINKING_TOKENS=0` |

174| `CLAUDE_CODE_DISABLE_VIRTUAL_SCROLL` | Set to `1` to disable virtual scrolling in [fullscreen rendering](/en/fullscreen) and render every message in the transcript. Use this if scrolling in fullscreen mode shows blank regions where messages should appear |174| `CLAUDE_CODE_DISABLE_VIRTUAL_SCROLL` | Set to `1` to disable virtual scrolling in [fullscreen rendering](/en/fullscreen) and render every message in the transcript. Use this if scrolling in fullscreen mode shows blank regions where messages should appear |

175| `CLAUDE_CODE_DISABLE_WORKFLOWS` | Set to `1` to disable [workflows](/en/workflows#turn-workflows-off). Equivalent to the [`disableWorkflows`](/en/settings#available-settings) setting |

175| `CLAUDE_CODE_EFFORT_LEVEL` | Set the effort level for supported models. Values: `low`, `medium`, `high`, `xhigh`, `max`, or `auto` to use the model default. Available levels depend on the model. Takes precedence over `/effort` and the `effortLevel` setting. See [Adjust effort level](/en/model-config#adjust-effort-level) |176| `CLAUDE_CODE_EFFORT_LEVEL` | Set the effort level for supported models. Values: `low`, `medium`, `high`, `xhigh`, `max`, or `auto` to use the model default. Available levels depend on the model. Takes precedence over `/effort` and the `effortLevel` setting. See [Adjust effort level](/en/model-config#adjust-effort-level) |

176| `CLAUDE_CODE_ENABLE_AWAY_SUMMARY` | Override [session recap](/en/interactive-mode#session-recap) availability. Set to `0` to force recaps off regardless of the `/config` toggle. Set to `1` to force recaps on when [`awaySummaryEnabled`](/en/settings#available-settings) is `false`. Takes precedence over the setting and `/config` toggle |177| `CLAUDE_CODE_ENABLE_AWAY_SUMMARY` | Override [session recap](/en/interactive-mode#session-recap) availability. Set to `0` to force recaps off regardless of the `/config` toggle. Set to `1` to force recaps on when [`awaySummaryEnabled`](/en/settings#available-settings) is `false`. Takes precedence over the setting and `/config` toggle |

177| `CLAUDE_CODE_ENABLE_BACKGROUND_PLUGIN_REFRESH` | Set to `1` to refresh plugin state at turn boundaries in [non-interactive mode](/en/headless) after a background install completes. Off by default because the refresh changes the system prompt mid-session, which invalidates [prompt caching](/en/prompt-caching) for that turn |178| `CLAUDE_CODE_ENABLE_BACKGROUND_PLUGIN_REFRESH` | Set to `1` to refresh plugin state at turn boundaries in [non-interactive mode](/en/headless) after a background install completes. Off by default because the refresh changes the system prompt mid-session, which invalidates [prompt caching](/en/prompt-caching) for that turn |

178| `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL` | Set to `1` to route the "How is Claude doing?" session quality survey to your own [OpenTelemetry collector](/en/monitoring-usage) when Anthropic-bound nonessential traffic is blocked. Survey ratings are emitted only as OTEL events to your configured collector. No survey data is sent to Anthropic in this mode. Applies when `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`, `DISABLE_TELEMETRY`, or `DO_NOT_TRACK` is set, and has no effect otherwise. `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` and the organization product feedback policy take precedence |179| `CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL` | Set to `1` to route the "How is Claude doing?" session quality survey to your own [OpenTelemetry collector](/en/monitoring-usage) when Anthropic-bound nonessential traffic is blocked. Survey ratings are emitted only as OTEL events to your configured collector. No survey data is sent to Anthropic in this mode. Applies when `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC`, `DISABLE_TELEMETRY`, or `DO_NOT_TRACK` is set, and has no effect otherwise. `CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY` and the organization product feedback policy take precedence |

179| `CLAUDE_CODE_ENABLE_FINE_GRAINED_TOOL_STREAMING` | Controls whether tool call inputs stream from the API as Claude generates them. With this off, a large tool input such as a long file write arrives only after Claude finishes generating it, which can look like it's hanging. Enabled by default on the Anthropic API. On Bedrock and Vertex, enabled per model where the deployed container supports it. Set to `0` to opt out. Set to `1` to force on when routing through a proxy via `ANTHROPIC_BASE_URL`, `ANTHROPIC_VERTEX_BASE_URL`, or `ANTHROPIC_BEDROCK_BASE_URL`. Off by default on Foundry and [gateway](/en/llm-gateway) connections |180| `CLAUDE_CODE_ENABLE_FINE_GRAINED_TOOL_STREAMING` | Controls whether tool call inputs stream from the API as Claude generates them. With this off, a large tool input such as a long file write arrives only after Claude finishes generating it, which can look like it's hanging. Enabled by default on the Anthropic API. On Bedrock and Vertex, enabled per model where the deployed container supports it. Set to `0` to opt out. Set to `1` to force on when routing through a proxy via `ANTHROPIC_BASE_URL`, `ANTHROPIC_VERTEX_BASE_URL`, or `ANTHROPIC_BEDROCK_BASE_URL`. Off by default on Foundry and [gateway](/en/llm-gateway) connections |

180| `CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY` | Set to `1` to populate the `/model` picker from your gateway's `/v1/models` endpoint when `ANTHROPIC_BASE_URL` points at an Anthropic-compatible gateway such as LiteLLM, Kong, or an internal proxy. Off by default because gateways backed by a shared API key would otherwise show every user every model the key can access. Discovered models are still filtered by the [`availableModels`](/en/settings#available-settings) allowlist |181| `CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY` | Set to `1` to populate the `/model` picker from your gateway's `/v1/models` endpoint when `ANTHROPIC_BASE_URL` points at an Anthropic-compatible gateway such as LiteLLM, Kong, or an internal proxy. Off by default because gateways backed by a shared API key would otherwise show every user every model the key can access. Discovered models are still filtered by the [`availableModels`](/en/settings#available-settings) allowlist |

181| `CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE` | {/* max-version: 2.1.141 */}Removed in v2.1.142. [Fast mode](/en/fast-mode) defaults to Opus 4.7. Set `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1` to keep Opus 4.6 instead |182| `CLAUDE_CODE_ENABLE_OPUS_4_7_FAST_MODE` | {/* max-version: 2.1.141 */}Removed in v2.1.142, when the [fast mode](/en/fast-mode) default moved from Opus 4.6 to Opus 4.7. Set `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1` to keep Opus 4.6 instead |

182| `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) |183| `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) |

183| `CLAUDE_CODE_ENABLE_TASKS` | Controls whether sessions use the structured Task tools (`TaskCreate`, `TaskUpdate`, `TaskGet`, `TaskList`) or the legacy `TodoWrite` tool. {/* min-version: 2.1.142 */}As of Claude Code v2.1.142, Task tools are the default in all modes. Set to `0` to revert to `TodoWrite`. See [Task list](/en/interactive-mode#task-list) and [Migrate to Task tools](/en/agent-sdk/todo-tracking#migrate-to-task-tools) |184| `CLAUDE_CODE_ENABLE_TASKS` | Controls whether sessions use the structured Task tools (`TaskCreate`, `TaskUpdate`, `TaskGet`, `TaskList`) or the legacy `TodoWrite` tool. {/* min-version: 2.1.142 */}As of Claude Code v2.1.142, Task tools are the default in all modes. Set to `0` to revert to `TodoWrite`. See [Task list](/en/interactive-mode#task-list) and [Migrate to Task tools](/en/agent-sdk/todo-tracking#migrate-to-task-tools) |

184| `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) |185| `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) |

208| `CLAUDE_CODE_OAUTH_REFRESH_TOKEN` | OAuth refresh token for Claude.ai authentication. When set, `claude auth login` exchanges this token directly instead of opening a browser. Requires `CLAUDE_CODE_OAUTH_SCOPES`. Useful for provisioning authentication in automated environments |209| `CLAUDE_CODE_OAUTH_REFRESH_TOKEN` | OAuth refresh token for Claude.ai authentication. When set, `claude auth login` exchanges this token directly instead of opening a browser. Requires `CLAUDE_CODE_OAUTH_SCOPES`. Useful for provisioning authentication in automated environments |

209| `CLAUDE_CODE_OAUTH_SCOPES` | Space-separated OAuth scopes the refresh token was issued with, such as `"user:profile user:inference user:sessions:claude_code"`. Required when `CLAUDE_CODE_OAUTH_REFRESH_TOKEN` is set |210| `CLAUDE_CODE_OAUTH_SCOPES` | Space-separated OAuth scopes the refresh token was issued with, such as `"user:profile user:inference user:sessions:claude_code"`. Required when `CLAUDE_CODE_OAUTH_REFRESH_TOKEN` is set |

210| `CLAUDE_CODE_OAUTH_TOKEN` | OAuth access token for Claude.ai authentication. Alternative to `/login` for SDK and automated environments. Takes precedence over keychain-stored credentials. Generate one with [`claude setup-token`](/en/authentication#generate-a-long-lived-token) |211| `CLAUDE_CODE_OAUTH_TOKEN` | OAuth access token for Claude.ai authentication. Alternative to `/login` for SDK and automated environments. Takes precedence over keychain-stored credentials. Generate one with [`claude setup-token`](/en/authentication#generate-a-long-lived-token) |

211| `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` | Set to `1` to pin [fast mode](/en/fast-mode) to Claude Opus 4.6 instead of the default Opus 4.7. With the variable set, `/fast` runs on Opus 4.6. Without it, `/fast` runs on Opus 4.7 |212| `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE` | Set to `1` to pin fast mode to Claude Opus 4.6 instead of the [current fast mode default](/en/fast-mode#toggle-fast-mode), which depends on your Claude Code version. With the variable set, `/fast` runs on Opus 4.6. Fast mode for Opus 4.6 is deprecated, and this variable will be removed when it is retired |

212| `CLAUDE_CODE_OTEL_FLUSH_TIMEOUT_MS` | Timeout in milliseconds for flushing pending OpenTelemetry spans (default: 5000). See [Monitoring](/en/monitoring-usage) |213| `CLAUDE_CODE_OTEL_FLUSH_TIMEOUT_MS` | Timeout in milliseconds for flushing pending OpenTelemetry spans (default: 5000). See [Monitoring](/en/monitoring-usage) |

213| `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) |214| `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) |

214| `CLAUDE_CODE_OTEL_SHUTDOWN_TIMEOUT_MS` | Timeout in milliseconds for the OpenTelemetry exporter to finish on shutdown (default: 2000). Increase if metrics are dropped at exit. See [Monitoring](/en/monitoring-usage) |215| `CLAUDE_CODE_OTEL_SHUTDOWN_TIMEOUT_MS` | Timeout in milliseconds for the OpenTelemetry exporter to finish on shutdown (default: 2000). Increase if metrics are dropped at exit. See [Monitoring](/en/monitoring-usage) |

230| `CLAUDE_CODE_SCRIPT_CAPS` | JSON object limiting how many times specific scripts may be invoked per session when `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB` is set. Keys are substrings matched against the command text; values are integer call limits. For example, `{"deploy.sh": 2}` allows `deploy.sh` to be called at most twice. Matching is substring-based so shell-expansion tricks like `./scripts/deploy.sh $(evil)` still count against the cap. Runtime fan-out via `xargs` or `find -exec` is not detected; this is a defense-in-depth control |231| `CLAUDE_CODE_SCRIPT_CAPS` | JSON object limiting how many times specific scripts may be invoked per session when `CLAUDE_CODE_SUBPROCESS_ENV_SCRUB` is set. Keys are substrings matched against the command text; values are integer call limits. For example, `{"deploy.sh": 2}` allows `deploy.sh` to be called at most twice. Matching is substring-based so shell-expansion tricks like `./scripts/deploy.sh $(evil)` still count against the cap. Runtime fan-out via `xargs` or `find -exec` is not detected; this is a defense-in-depth control |

231| `CLAUDE_CODE_SCROLL_SPEED` | Set the mouse wheel scroll multiplier in [fullscreen rendering](/en/fullscreen#mouse-wheel-scrolling). Accepts values from 1 to 20. Set to `3` to match `vim` if your terminal sends one wheel event per notch without amplification. Ignored in the JetBrains IDE terminal, where Claude Code uses its own scroll handling |232| `CLAUDE_CODE_SCROLL_SPEED` | Set the mouse wheel scroll multiplier in [fullscreen rendering](/en/fullscreen#mouse-wheel-scrolling). Accepts values from 1 to 20. Set to `3` to match `vim` if your terminal sends one wheel event per notch without amplification. Ignored in the JetBrains IDE terminal, where Claude Code uses its own scroll handling |

232| `CLAUDE_CODE_SESSIONEND_HOOKS_TIMEOUT_MS` | Override the time budget in milliseconds for [SessionEnd](/en/hooks#sessionend) hooks. Applies to session exit, `/clear`, and switching sessions via interactive `/resume`. By default the budget is 1.5 seconds, automatically raised to the highest per-hook `timeout` configured in settings files, up to 60 seconds. Timeouts on plugin-provided hooks do not raise the budget |233| `CLAUDE_CODE_SESSIONEND_HOOKS_TIMEOUT_MS` | Override the time budget in milliseconds for [SessionEnd](/en/hooks#sessionend) hooks. Applies to session exit, `/clear`, and switching sessions via interactive `/resume`. By default the budget is 1.5 seconds, automatically raised to the highest per-hook `timeout` configured in settings files, up to 60 seconds. Timeouts on plugin-provided hooks do not raise the budget |

233| `CLAUDE_CODE_SESSION_ID` | Set automatically in Bash and PowerShell tool subprocesses and in [hook command](/en/hooks) subprocesses to the current session ID. Matches the `session_id` field in the hook JSON input. Updated on `/clear`. Use to correlate scripts and external tools with the Claude Code session that launched them |234| `CLAUDE_CODE_SESSION_ID` | Set automatically to the current session ID in Bash and PowerShell tool subprocesses, [hook command](/en/hooks) subprocesses, and stdio [MCP server](/en/mcp) subprocesses. For Bash, PowerShell, and hooks this matches the `session_id` field in the hook JSON input and is updated on `/clear`. An MCP server subprocess retains the ID it was spawned with, and may receive the initial startup ID rather than the resumed ID when launched via `--resume` or `--continue`. Use to correlate scripts and external tools with the Claude Code session that launched them |

234| `CLAUDE_CODE_SHELL` | Override automatic shell detection. Useful when your login shell differs from your preferred working shell (for example, `bash` vs `zsh`) |235| `CLAUDE_CODE_SHELL` | Override automatic shell detection. Useful when your login shell differs from your preferred working shell (for example, `bash` vs `zsh`) |

235| `CLAUDE_CODE_SHELL_PREFIX` | Command prefix that wraps shell commands Claude Code spawns: Bash tool calls, [hook](/en/hooks) commands, and stdio [MCP server](/en/mcp) startup commands. Useful for logging or auditing. Example: setting `/path/to/logger.sh` runs each command as `/path/to/logger.sh <command>` |236| `CLAUDE_CODE_SHELL_PREFIX` | Command prefix that wraps shell commands Claude Code spawns: Bash tool calls, [hook](/en/hooks) commands, and stdio [MCP server](/en/mcp) startup commands. Useful for logging or auditing. Example: setting `/path/to/logger.sh` runs each command as `/path/to/logger.sh <command>` |

236| `CLAUDE_CODE_SIMPLE` | Set to `1` to run with a minimal system prompt and only the Bash, file read, and file edit tools. MCP tools from `--mcp-config` are still available. Disables auto-discovery of hooks, skills, plugins, MCP servers, auto memory, and CLAUDE.md. OAuth tokens and keychain credentials are not read, so Anthropic authentication must come from `ANTHROPIC_API_KEY` or an `apiKeyHelper` in `--settings`. Equivalent to passing [`--bare`](/en/headless#start-faster-with-bare-mode) |237| `CLAUDE_CODE_SIMPLE` | Set to `1` to run with a minimal system prompt and only the Bash, file read, and file edit tools. MCP tools from `--mcp-config` are still available. Disables auto-discovery of hooks, skills, plugins, MCP servers, auto memory, and CLAUDE.md. OAuth tokens and keychain credentials are not read, so Anthropic authentication must come from `ANTHROPIC_API_KEY` or an `apiKeyHelper` in `--settings`. Equivalent to passing [`--bare`](/en/headless#start-faster-with-bare-mode) |

261| `CLAUDE_CODE_USE_POWERSHELL_TOOL` | Controls the PowerShell tool. On Windows without Git Bash, the tool is enabled automatically; set to `0` to disable it. On Windows with Git Bash installed, the tool is rolling out progressively: set to `1` to opt in or `0` to opt out. On Linux, macOS, and WSL, set to `1` to enable it, which requires `pwsh` on your `PATH`. When enabled on Windows, Claude can run PowerShell commands natively instead of routing through Git Bash. See [PowerShell tool](/en/tools-reference#powershell-tool) |262| `CLAUDE_CODE_USE_POWERSHELL_TOOL` | Controls the PowerShell tool. On Windows without Git Bash, the tool is enabled automatically; set to `0` to disable it. On Windows with Git Bash installed, the tool is rolling out progressively: set to `1` to opt in or `0` to opt out. On Linux, macOS, and WSL, set to `1` to enable it, which requires `pwsh` on your `PATH`. When enabled on Windows, Claude can run PowerShell commands natively instead of routing through Git Bash. See [PowerShell tool](/en/tools-reference#powershell-tool) |

263| `CLAUDE_CONFIG_DIR` | Override the configuration directory (default: `~/.claude`). All settings, credentials, session history, and plugins are stored under this path. Useful for running multiple accounts side by side: for example, `alias claude-work='CLAUDE_CONFIG_DIR=~/.claude-work claude'` |264| `CLAUDE_CONFIG_DIR` | Override the configuration directory (default: `~/.claude`). All settings, credentials, session history, and plugins are stored under this path. Useful for running multiple accounts side by side: for example, `alias claude-work='CLAUDE_CONFIG_DIR=~/.claude-work claude'` |

264| `CLAUDE_EFFORT` | Set automatically in Bash tool subprocesses and hook commands to the active [effort level](/en/model-config#adjust-effort-level) for the turn: `low`, `medium`, `high`, `xhigh`, or `max`. Matches the `effort.level` field passed to [hooks](/en/hooks). Only set when the current model supports the effort parameter |265| `CLAUDE_EFFORT` | Set automatically in Bash tool subprocesses and hook commands to the active [effort level](/en/model-config#adjust-effort-level) for the turn: `low`, `medium`, `high`, `xhigh`, `max`, or `ultra`. The `ultra` value corresponds to ultracode in `/effort`; the variable reports the stored value, not the display label. Matches the `effort.level` field passed to [hooks](/en/hooks). Only set when the current model supports the effort parameter |

265| `CLAUDE_ENABLE_BYTE_WATCHDOG` | Set to `1` to force-enable the byte-level streaming idle watchdog, or set to `0` to force-disable it. When unset, the watchdog is enabled by default for Anthropic API connections. The byte watchdog aborts a connection when no bytes arrive on the wire for the duration set by `CLAUDE_STREAM_IDLE_TIMEOUT_MS`, with a minimum of 5 minutes, independent of the event-level watchdog |266| `CLAUDE_ENABLE_BYTE_WATCHDOG` | Set to `1` to force-enable the byte-level streaming idle watchdog, or set to `0` to force-disable it. When unset, the watchdog is enabled by default for Anthropic API connections. The byte watchdog aborts a connection when no bytes arrive on the wire for the duration set by `CLAUDE_STREAM_IDLE_TIMEOUT_MS`, with a minimum of 5 minutes, independent of the event-level watchdog |

266| `CLAUDE_ENABLE_BYTE_WATCHDOG_BEDROCK` | Set to `1` to enable the byte-level streaming idle watchdog on Amazon Bedrock `vnd.amazon.eventstream` responses. Off by default. Configure the timeout with `CLAUDE_STREAM_IDLE_TIMEOUT_MS` |267| `CLAUDE_ENABLE_BYTE_WATCHDOG_BEDROCK` | Set to `1` to enable the byte-level streaming idle watchdog on Amazon Bedrock `vnd.amazon.eventstream` responses. Off by default. Configure the timeout with `CLAUDE_STREAM_IDLE_TIMEOUT_MS` |

267| `CLAUDE_ENABLE_STREAM_WATCHDOG` | Set to `1` to enable the event-level streaming idle watchdog. Off by default. Applies to all providers, including Bedrock. For Vertex and Foundry, this is the only idle watchdog available. On Bedrock, you can also enable the independent byte-level watchdog with `CLAUDE_ENABLE_BYTE_WATCHDOG_BEDROCK`; the two run together when both are set. Configure the timeout with `CLAUDE_STREAM_IDLE_TIMEOUT_MS` |268| `CLAUDE_ENABLE_STREAM_WATCHDOG` | Set to `1` to enable the event-level streaming idle watchdog. Off by default. Applies to all providers, including Bedrock. For Vertex and Foundry, this is the only idle watchdog available. On Bedrock, you can also enable the independent byte-level watchdog with `CLAUDE_ENABLE_BYTE_WATCHDOG_BEDROCK`; the two run together when both are set. Configure the timeout with `CLAUDE_STREAM_IDLE_TIMEOUT_MS` |

en/errors.md +2 −2

Details

569 569

570### thinking.type.enabled is not supported for this model570### thinking.type.enabled is not supported for this model

571 571

572Your Claude Code version is older than the minimum for Opus 4.7. The CLI sent a thinking configuration the model no longer accepts.572Your Claude Code version is older than the minimum for Opus 4.7 or Opus 4.8. The CLI sent a thinking configuration the model no longer accepts.

573 573

574```text theme={null}574```text theme={null}

575API Error: 400 ... "thinking.type.enabled" is not supported for this model. Use "thinking.type.adaptive" and "output_config.effort" to control thinking behavior.575API Error: 400 ... "thinking.type.enabled" is not supported for this model. Use "thinking.type.adaptive" and "output_config.effort" to control thinking behavior.

577 577

578**What to do:**578**What to do:**

579 579

580* Run `claude update` to upgrade to v2.1.111 or later, then restart Claude Code580* Run `claude update` and restart Claude Code. Opus 4.7 needs v2.1.111 or later. Opus 4.8 needs v2.1.154 or later

581* If you cannot upgrade, run `/model` and select Opus 4.6 or Sonnet instead581* If you cannot upgrade, run `/model` and select Opus 4.6 or Sonnet instead

582* If you hit this in the Agent SDK, see [SDK troubleshooting](/en/agent-sdk/quickstart#troubleshooting)582* If you hit this in the Agent SDK, see [SDK troubleshooting](/en/agent-sdk/quickstart#troubleshooting)

583 583

en/fast-mode.md +17 −12

Details

10 Fast mode is in [research preview](#research-preview). The feature, pricing, and availability may change based on feedback.10 Fast mode is in [research preview](#research-preview). The feature, pricing, and availability may change based on feedback.

11</Note>11</Note>

12 12

13Fast mode is a high-speed configuration for Claude Opus, making the model 2.5x faster at a higher cost per token. Toggle it on with `/fast` when you need speed for interactive work like rapid iteration or live debugging, and toggle it off when cost matters more than latency.13Fast mode is a high-speed configuration for Claude Opus, making the model up to 2.5x faster at a higher cost per token. Toggle it on with `/fast` when you need speed for interactive work like rapid iteration or live debugging, and toggle it off when cost matters more than latency.

14 14

15Fast mode is not a different model. It uses Claude Opus with a different API configuration that prioritizes speed over cost efficiency. You get identical quality and capabilities with faster responses. Fast mode is supported on Opus 4.7 and Opus 4.6. It is not available on Sonnet, Haiku, or other models.15Fast mode is not a different model. It uses Claude Opus with a different API configuration that prioritizes speed over cost efficiency. You get identical quality and capabilities with faster responses. Fast mode is supported on Opus 4.8, Opus 4.7, and Opus 4.6. It is not available on Sonnet, Haiku, or other models.

17<Warning>

18 Fast mode for Opus 4.6 is deprecated and will be removed approximately 30 days after the Opus 4.8 launch. After removal, fast mode on Opus 4.6 falls back to standard speed at standard pricing. Migrate to Opus 4.8 or Opus 4.7 to keep the speedup.

19</Warning>

16 20

17<Note>21<Note>

18 Fast mode requires Claude Code v2.1.36 or later. Check your version with `claude --version`.22 Fast mode requires Claude Code v2.1.36 or later. Check your version with `claude --version`.

20 24

21What to know:25What to know:

22 26

~~23* Use `/fast` to toggle on fast mode in Claude Code CLI. Also available via `/fast` in Claude Code VS Code Extension.~~27* Use `/fast` to toggle on fast mode in the Claude Code CLI. Fast mode is not supported in the VS Code extension.

~~24* Fast mode pricing is \$30/\$150 MTok on both Opus 4.7 and Opus 4.6.~~28* Fast mode pricing is \$10/\$50 MTok on Opus 4.8 and \$30/\$150 MTok on Opus 4.7 and Opus 4.6.

25* Available to all Claude Code users on subscription plans (Pro/Max/Team/Enterprise) and Claude Console.29* Available to all Claude Code users on subscription plans (Pro/Max/Team/Enterprise) and Claude Console.

26* For Claude Code users on subscription plans (Pro/Max/Team/Enterprise), fast mode is available via usage credits only and not included in the subscription rate limits.30* For Claude Code users on subscription plans (Pro/Max/Team/Enterprise), fast mode is available via usage credits only and not included in the subscription rate limits.

27 31

47 51

48When you disable fast mode with `/fast` again, you remain on Opus. The model does not revert to your previous model. To switch to a different model, use `/model`.52When you disable fast mode with `/fast` again, you remain on Opus. The model does not revert to your previous model. To switch to a different model, use `/model`.

49 53

~~50Opus 4.7 is the fast mode default in Claude Code v2.1.142 and later. To pin fast mode to Opus 4.6 instead, set `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1`.~~54Opus 4.8 is the fast mode default in Claude Code v2.1.154 and later. On v2.1.142 through v2.1.153, fast mode defaults to Opus 4.7. To pin fast mode to Opus 4.6 instead, set `CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1`; this override will be removed when fast mode for Opus 4.6 is retired.

51 55

52## Understand the cost tradeoff56## Understand the cost tradeoff

53 57

~~54Fast mode has higher per-token pricing than standard Opus:~~58Fast mode has higher per-token pricing than standard Opus, with the multiplier varying by model:

55 59

~~57| --------- | ------------ | ------------- |~~61| --------------------- | ------------ | ------------- |

~~58| Fast mode | \$30 | \$150 |~~62| Opus 4.8 | \$10 | \$50 |

63| Opus 4.7 and Opus 4.6 | \$30 | \$150 |

59 64

~~60Fast mode pricing is flat across the full 1M token context window.~~65Fast mode pricing is flat across the full 1M token context window. For the standard Opus rate to compare against, see the [Claude pricing reference](https://platform.claude.com/docs/en/about-claude/pricing).

61 66

62When you switch into fast mode mid-conversation, you pay the full fast mode uncached input token price for the entire conversation context. This costs more than if you had enabled fast mode from the start.67When you switch into fast mode mid-conversation, you pay the full fast mode uncached input token price for the entire conversation context. This costs more than if you had enabled fast mode from the start.

63 68

90 95

91Fast mode requires all of the following:96Fast mode requires all of the following:

92 97

93* **Not available on third-party cloud providers**: fast mode is not available on Amazon Bedrock, Google Vertex AI, or Microsoft Azure Foundry. Fast mode is available through the Anthropic Console API and for Claude subscription plans using usage credits.98* **Anthropic API or subscription only**: fast mode is available through the Anthropic Console API and for Claude subscription plans using usage credits. It is not available on Amazon Bedrock, Google Vertex AI, Microsoft Azure Foundry, or Claude Platform on AWS.

94* **Usage credits turned on**: your account must have usage credits turned on, which allows billing beyond your plan's included usage. For individual accounts, turn this on in your [Console billing settings](https://platform.claude.com/settings/organization/billing). For Team and Enterprise, an admin must turn on usage credits for the organization.99* **Usage credits turned on**: your account must have usage credits turned on, which allows billing beyond your plan's included usage. For individual accounts, turn this on in your [Console billing settings](https://platform.claude.com/settings/organization/billing). For Team and Enterprise, an admin must turn on usage credits for the organization.

95 100

96<Note>101<Note>

126 131

127## Handle rate limits132## Handle rate limits

128 133

129Fast mode has separate rate limits from standard Opus. Fast mode for Opus 4.7 and Opus 4.6 share the same rate limit pool: usage on either model draws from the same limits. When you hit the fast mode rate limit or run out of usage credits:134Fast mode has separate rate limits from standard Opus. Fast mode on Opus 4.8, Opus 4.7, and Opus 4.6 shares the same rate limit pool: usage on any of them draws from the same limits. When you hit the fast mode rate limit or run out of usage credits:

130 135

1311. Fast mode automatically falls back to standard speed1361. Fast mode automatically falls back to standard speed

1322. The `↯` icon turns gray to indicate cooldown1372. The `↯` icon turns gray to indicate cooldown

en/github-actions.md +1 −1

Details

13</Note>13</Note>

14 14

15<Info>15<Info>

~~16 **Claude Opus 4.7 is now available.** Claude Code GitHub Actions default to Sonnet. To use Opus 4.7, configure the [model parameter](#breaking-changes-reference) to use `claude-opus-4-7`.~~16 **Claude Opus 4.8 is now available.** Claude Code GitHub Actions default to Sonnet. To use Opus 4.8, configure the [model parameter](#breaking-changes-reference) to use `claude-opus-4-8`.

17</Info>17</Info>

18 18

19## Why use Claude Code GitHub Actions?19## Why use Claude Code GitHub Actions?

en/glossary.md +9 −1

Details

118 118

119### Effort level119### Effort level

120 120

121A setting that controls how much of the adaptive-reasoning thinking budget Claude uses on each turn. Higher effort means more thinking tokens and deeper reasoning; lower effort is faster and cheaper. Effort is supported on Opus 4.7, Opus 4.6, and Sonnet 4.6.121A setting that controls how much of the adaptive-reasoning thinking budget Claude uses on each turn. Higher effort means more thinking tokens and deeper reasoning; lower effort is faster and cheaper. Effort is supported on Opus 4.6 and later, and on Sonnet 4.6.

122 122

123Learn more: [Adjust effort level](/en/model-config#adjust-effort-level)123Learn more: [Adjust effort level](/en/model-config#adjust-effort-level)

124 124

292 292

293Learn more: [How Claude Code works](/en/how-claude-code-works#the-agentic-loop)293Learn more: [How Claude Code works](/en/how-claude-code-works#the-agentic-loop)

294 294

295## V

296

297### Verification loop

298

299How a session knows the work is actually done rather than just plausible. You give Claude a check it can run, such as a test suite, a build, or a screenshot comparison, and Claude iterates until the check passes instead of stopping after one attempt. A verification loop is the prerequisite for [`/goal`](/en/goal), unattended runs, and [dynamic workflows](/en/workflows): without one, the only thing deciding the agent is finished is the agent itself.

300

301Learn more: [Give Claude a way to verify its work](/en/best-practices#give-claude-a-way-to-verify-its-work)

302

295## W303## W

296 304

297### Worktree isolation305### Worktree isolation

en/google-vertex-ai.md +4 −4

Details

212 212

213Set these environment variables to specific Vertex AI model IDs.213Set these environment variables to specific Vertex AI model IDs.

214 214

215Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Vertex resolves to Opus 4.6. Set it to the Opus 4.7 ID to use the latest model:215Without `ANTHROPIC_DEFAULT_OPUS_MODEL`, the `opus` alias on Vertex resolves to Opus 4.6. Set it to the Opus 4.8 ID to use the latest model:

216 216

217```bash theme={null}217```bash theme={null}

218export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-7'218export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-8'

219export ANTHROPIC_DEFAULT_SONNET_MODEL='claude-sonnet-4-6'219export ANTHROPIC_DEFAULT_SONNET_MODEL='claude-sonnet-4-6'

220export ANTHROPIC_DEFAULT_HAIKU_MODEL='claude-haiku-4-5@20251001'220export ANTHROPIC_DEFAULT_HAIKU_MODEL='claude-haiku-4-5@20251001'

221```221```

234To customize models further:234To customize models further:

235 235

236```bash theme={null}236```bash theme={null}

237export ANTHROPIC_MODEL='claude-opus-4-7'237export ANTHROPIC_MODEL='claude-opus-4-8'

238export ANTHROPIC_DEFAULT_HAIKU_MODEL='claude-haiku-4-5@20251001'238export ANTHROPIC_DEFAULT_HAIKU_MODEL='claude-haiku-4-5@20251001'

239```239```

240 240

264 264

265## 1M token context window265## 1M token context window

266 266

267Claude Opus 4.7, Opus 4.6, 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. Claude Code automatically enables the extended context window when you select a 1M model variant.267Claude Opus 4.6 and later, 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. Claude Code automatically enables the extended context window when you select a 1M model variant.

268 268

269The [setup wizard](#sign-in-with-vertex-ai) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. See [Pin models for third-party deployments](/en/model-config#pin-models-for-third-party-deployments) for details.269The [setup wizard](#sign-in-with-vertex-ai) offers a 1M context option when it pins models. To enable it for a manually pinned model instead, append `[1m]` to the model ID. See [Pin models for third-party deployments](/en/model-config#pin-models-for-third-party-deployments) for details.

270 270

en/hooks.md +3 −3

Details

445 445

446Use these placeholders to reference hook scripts relative to the project or plugin root, regardless of the working directory when the hook runs:446Use these placeholders to reference hook scripts relative to the project or plugin root, regardless of the working directory when the hook runs:

447 447

448* `${CLAUDE_PROJECT_DIR}`: the project root.448* `${CLAUDE_PROJECT_DIR}`: the project root. Claude Code also sets this variable in the environment of [stdio MCP servers](/en/mcp#option-3-add-a-local-stdio-server) and plugin LSP servers.

449* `${CLAUDE_PLUGIN_ROOT}`: the plugin's installation directory, for scripts bundled with a [plugin](/en/plugins). Changes on each plugin update.449* `${CLAUDE_PLUGIN_ROOT}`: the plugin's installation directory, for scripts bundled with a [plugin](/en/plugins). Changes on each plugin update.

450* `${CLAUDE_PLUGIN_DATA}`: the plugin's [persistent data directory](/en/plugins-reference#persistent-data-directory), for dependencies and state that should survive plugin updates.450* `${CLAUDE_PLUGIN_DATA}`: the plugin's [persistent data directory](/en/plugins-reference#persistent-data-directory), for dependencies and state that should survive plugin updates.

451 451

566Hook events receive these fields as JSON, in addition to event-specific fields documented in each [hook event](#hook-events) section. For command hooks, this JSON arrives via stdin. For HTTP hooks, it arrives as the POST request body.566Hook events receive these fields as JSON, in addition to event-specific fields documented in each [hook event](#hook-events) section. For command hooks, this JSON arrives via stdin. For HTTP hooks, it arrives as the POST request body.

567 567

569| :---------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |569| :---------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

572| `cwd` | Current working directory when the hook is invoked |572| `cwd` | Current working directory when the hook is invoked |

573| `permission_mode` | Current [permission mode](/en/permissions#permission-modes): `"default"`, `"plan"`, `"acceptEdits"`, `"auto"`, `"dontAsk"`, or `"bypassPermissions"`. Not all events receive this field: see each event's JSON example below to check |573| `permission_mode` | Current [permission mode](/en/permissions#permission-modes): `"default"`, `"plan"`, `"acceptEdits"`, `"auto"`, `"dontAsk"`, or `"bypassPermissions"`. Not all events receive this field: see each event's JSON example below to check |

574| `effort` | Object with a `level` field holding the active [effort level](/en/model-config#adjust-effort-level) for the turn: `"low"`, `"medium"`, `"high"`, `"xhigh"`, or `"max"`. If the requested effort exceeds what the current model supports, this is the downgraded level the model actually used, not the level you requested. The object matches the [status line](/en/statusline#available-data) `effort` field. Present for events that fire within a tool-use context, such as `PreToolUse`, `PostToolUse`, `Stop`, and `SubagentStop`, when the current model supports the effort parameter. The level is also available to hook commands and the Bash tool as the `$CLAUDE_EFFORT` environment variable. |574| `effort` | Object with a `level` field holding the active [effort level](/en/model-config#adjust-effort-level) for the turn: `"low"`, `"medium"`, `"high"`, `"xhigh"`, `"max"`, or `"ultra"`. If the requested model effort exceeds what the current model supports, this is the downgraded level the model actually used. `"ultra"` is the stored value for ultracode and is reported here even though the model receives `xhigh`. The object matches the [status line](/en/statusline#available-data) `effort` field. Present for events that fire within a tool-use context, such as `PreToolUse`, `PostToolUse`, `Stop`, and `SubagentStop`, when the current model supports the effort parameter. The level is also available to hook commands and the Bash tool as the `$CLAUDE_EFFORT` environment variable. |

576 576

577When running with `--agent` or inside a subagent, two additional fields are included:577When running with `--agent` or inside a subagent, two additional fields are included:

en/interactive-mode.md +1 −1

Details

299 299

300The suggestion runs as a background request that reuses the parent conversation's prompt cache, so the additional cost is minimal. Claude Code skips suggestion generation when the cache is cold to avoid unnecessary cost.300The suggestion runs as a background request that reuses the parent conversation's prompt cache, so the additional cost is minimal. Claude Code skips suggestion generation when the cache is cold to avoid unnecessary cost.

301 301

302Suggestions are automatically skipped after the first turn of a conversation, in non-interactive mode, and in plan mode.302Suggestions are automatically skipped after the first turn of a conversation and in plan mode. In print mode they are off by default. Pass [`--prompt-suggestions`](/en/cli-reference#cli-flags) with `--output-format stream-json --verbose` to emit a `prompt_suggestion` message after each turn instead.

303 303

304To disable prompt suggestions entirely, set the environment variable or toggle the setting in `/config`:304To disable prompt suggestions entirely, set the environment variable or toggle the setting in `/config`:

305 305

en/keybindings.md +2 −2

Details

273Actions available in the `ModelPicker` context:273Actions available in the `ModelPicker` context:

274 274

276| :--------------------------- | :------ | :------------------------------------------------ |276| :---------------------------- | :------ | :------------------------------------------- |

279| `modelPicker:setAsDefault` | d | Set highlighted model as default for new sessions |279| `modelPicker:thisSessionOnly` | s | Apply highlighted model to this session only |

280 280

281### Select actions281### Select actions

282 282

en/mcp.md +2 −0

Details

141/mcp141/mcp

142```142```

143 143

144Project-scoped servers from `.mcp.json` that are awaiting your approval appear in `claude mcp list` as `⏸ Pending approval`. Run `claude` interactively to review and approve them. `claude mcp get <name>` shows pending servers as `⏸ Pending approval` and rejected servers as `✗ Rejected`.

145

144The `/mcp` panel shows the tool count next to each connected server and flags servers that advertise the tools capability but expose no tools.146The `/mcp` panel shows the tool count next to each connected server and flags servers that advertise the tools capability but expose no tools.

145 147

146If your request needs tools from a server that is still connecting in the background, Claude waits for that server before continuing. With [tool search](#scale-with-mcp-tool-search) enabled, which is the default, the wait happens inside the `ToolSearch` call. In configurations without tool search, such as Vertex AI, a custom `ANTHROPIC_BASE_URL`, or `ENABLE_TOOL_SEARCH=false`, Claude uses the `WaitForMcpServers` tool instead.148If your request needs tools from a server that is still connecting in the background, Claude waits for that server before continuing. With [tool search](#scale-with-mcp-tool-search) enabled, which is the default, the wait happens inside the `ToolSearch` call. In configurations without tool search, such as Vertex AI, a custom `ANTHROPIC_BASE_URL`, or `ENABLE_TOOL_SEARCH=false`, Claude uses the `WaitForMcpServers` tool instead.

en/microsoft-foundry.md +2 −2

Details

155 155

156Set the model variables to match the deployment names you created in step 1.156Set the model variables to match the deployment names you created in step 1.

157 157

159 159

160```bash theme={null}160```bash theme={null}

161export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-7'161export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-8'

162export ANTHROPIC_DEFAULT_SONNET_MODEL='claude-sonnet-4-6'162export ANTHROPIC_DEFAULT_SONNET_MODEL='claude-sonnet-4-6'

163export ANTHROPIC_DEFAULT_HAIKU_MODEL='claude-haiku-4-5'163export ANTHROPIC_DEFAULT_HAIKU_MODEL='claude-haiku-4-5'

164```164```

en/model-config.md +36 −27

Details

37| **`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 |37| **`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 |

38| **`opusplan`** | Special mode that uses `opus` during plan mode, then switches to `sonnet` for execution |38| **`opusplan`** | Special mode that uses `opus` during plan mode, then switches to `sonnet` for execution |

39 39

40On the Anthropic API and [Claude Platform on AWS](/en/claude-platform-on-aws), `opus` resolves to Opus 4.7 and `sonnet` resolves to Sonnet 4.6. On Bedrock, Vertex, and Foundry, `opus` resolves to Opus 4.6 and `sonnet` resolves to Sonnet 4.5; newer models are available on those providers by selecting the full model name explicitly or setting `ANTHROPIC_DEFAULT_OPUS_MODEL` or `ANTHROPIC_DEFAULT_SONNET_MODEL`.40On the Anthropic API, `opus` resolves to Opus 4.8 and `sonnet` resolves to Sonnet 4.6. On [Claude Platform on AWS](/en/claude-platform-on-aws), `opus` resolves to Opus 4.7 and `sonnet` resolves to Sonnet 4.6. On Bedrock, Vertex, and Foundry, `opus` resolves to Opus 4.6 and `sonnet` resolves to Sonnet 4.5; newer models are available on those providers by selecting the full model name explicitly or setting `ANTHROPIC_DEFAULT_OPUS_MODEL` or `ANTHROPIC_DEFAULT_SONNET_MODEL`.

41 41

42Aliases point to the recommended version for your provider and update over time. To pin to a specific version, use the full model name (for example, `claude-opus-4-7`) or set the corresponding environment variable like `ANTHROPIC_DEFAULT_OPUS_MODEL`.42Aliases point to the recommended version for your provider and update over time. To pin to a specific version, use the full model name (for example, `claude-opus-4-8`) or set the corresponding environment variable like `ANTHROPIC_DEFAULT_OPUS_MODEL`.

43 43

44<Note>44<Note>

~~45 Opus 4.7 requires Claude Code v2.1.111 or later. Run `claude update` to upgrade.~~45 Opus 4.8 requires Claude Code v2.1.154 or later. Run `claude update` to upgrade.

46</Note>46</Note>

47 47

48### Setting your model48### Setting your model

554. **Settings** - Configure permanently in your settings file using the `model`554. **Settings** - Configure permanently in your settings file using the `model`

56 field.56 field.

57 57

58As of v2.1.144, `/model` applies to the current session only and is not written to settings. To save your choice as the default for new sessions, press `d` on the highlighted row in the picker, which writes the `model` field in your user settings. Managed settings take precedence and reapply on the next launch.58As of v2.1.153, `/model` saves your choice as the default for new sessions by writing the `model` field in your user settings. In the picker:

59 59

60The `--model` flag and `ANTHROPIC_MODEL` environment variable also apply only to the session you launch with them. To run different models in different terminals at the same time, launch each one with its own `--model` flag rather than switching with `/model`.60* `Enter`: switch model and save as your default

61* `s`: switch model for this session only

63Typing `/model <name>` directly behaves like `Enter`. Project and managed settings still take precedence and reapply on the next launch.

65In v2.1.144 through v2.1.152, `/model` applied to the current session only and `d` in the picker saved a default.

67The `--model` flag and `ANTHROPIC_MODEL` environment variable apply only to the session you launch with them. To run different models in different terminals at the same time, launch each one with its own `--model` flag rather than switching with `/model`.

61 68

62Resumed sessions started with `claude --resume`, `--continue`, or the `/resume` picker keep the model they were using when the transcript was saved, regardless of the current `model` setting. If that model has been retired, the session falls through to the normal precedence order. This prevents another session's `/model` choice from changing the model on resume.69Resumed sessions started with `claude --resume`, `--continue`, or the `/resume` picker keep the model they were using when the transcript was saved, regardless of the current `model` setting. If that model has been retired, the session falls through to the normal precedence order. This prevents another session's `/model` choice from changing the model on resume.

63 70

64When the active model at startup comes from project or managed settings rather than your own selection, the startup header shows which settings file set it. Run `/model` to override for the current session.71When the active model at startup comes from project or managed settings rather than your own selection, the startup header shows which settings file set it. Run `/model` to override; the project or managed setting reapplies on the next launch.

65 72

66Example usage:73Example usage:

67 74

140 147

141The behavior of `default` depends on your account type:148The behavior of `default` depends on your account type:

142 149

143* **Max and Team Premium**: defaults to Opus 4.7150* **Max, Team Premium, Enterprise pay-as-you-go, and Anthropic API**: defaults to Opus 4.8

144* **Pro, Team Standard, Enterprise, and Anthropic API**: defaults to Sonnet 4.6151* **Claude Platform on AWS**: defaults to Opus 4.7

152* **Pro, Team Standard, and Enterprise subscription seats**: defaults to Sonnet 4.6

145* **Bedrock, Vertex, and Foundry**: defaults to Sonnet 4.5153* **Bedrock, Vertex, and Foundry**: defaults to Sonnet 4.5

146 154

147Claude Code may automatically fall back to Sonnet if you hit a usage threshold with Opus.155Enterprise pay-as-you-go means an Enterprise organization billed by usage rather than by subscription seat.

148 156

149<Note>157Claude Code may automatically fall back to Sonnet if you hit a usage threshold with Opus.

150 On April 23, 2026, the default model for Enterprise pay-as-you-go and Anthropic API users will change to Opus 4.7. To keep a different default, set `ANTHROPIC_MODEL` or the `model` field in [server-managed settings](/en/server-managed-settings).

151</Note>

152 158

153### `opusplan` model setting159### `opusplan` model setting

154 160

168 174

169[Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort) control adaptive reasoning, which lets the model decide whether and how much to think on each step based on task complexity. Lower effort is faster and cheaper for straightforward tasks, while higher effort provides deeper reasoning for complex problems.175[Effort levels](https://platform.claude.com/docs/en/build-with-claude/effort) control adaptive reasoning, which lets the model decide whether and how much to think on each step based on task complexity. Lower effort is faster and cheaper for straightforward tasks, while higher effort provides deeper reasoning for complex problems.

170 176

171Effort is supported on Opus 4.7, Opus 4.6, and Sonnet 4.6. The available levels depend on the model:177The available effort levels depend on the model. Models not listed here do not support effort:

172 178

173| Model | Levels |179| Model | Levels |

174| :---------------------- | :-------------------------------------- |180| :---------------------- | :-------------------------------------- |

177 183

178If you set a level the active model does not support, Claude Code falls back to the highest supported level at or below the one you set. For example, `xhigh` runs as `high` on Opus 4.6.184If you set a level the active model does not support, Claude Code falls back to the highest supported level at or below the one you set. For example, `xhigh` runs as `high` on Opus 4.6.

179 185

180As of v2.1.117, the default effort is `xhigh` on Opus 4.7 and `high` on Opus 4.6 and Sonnet 4.6.186The default effort is `high` on Opus 4.8, Opus 4.6, and Sonnet 4.6, and `xhigh` on Opus 4.7.

181 187

182When you first run Opus 4.7, Claude Code applies `xhigh` even if you previously set a different effort level for Opus 4.6 or Sonnet 4.6. Run `/effort` again to choose a different level after switching.188When you first run Opus 4.8 or Opus 4.7, Claude Code applies that model's default effort even if you previously set a different level for another model: `high` on Opus 4.8 and `xhigh` on Opus 4.7. Run `/effort` again to choose a different level after switching.

183 189

184`low`, `medium`, `high`, and `xhigh` persist across sessions. `max` provides the deepest reasoning with no constraint on token spending and applies to the current session only, except when set through the `CLAUDE_CODE_EFFORT_LEVEL` environment variable.190`low`, `medium`, `high`, and `xhigh` persist across sessions. `max` provides the deepest reasoning with no constraint on token spending and applies to the current session only, except when set through the `CLAUDE_CODE_EFFORT_LEVEL` environment variable.

185 191

192The `/effort` menu also offers `ultracode`. Ultracode is a Claude Code setting rather than a model effort level: it sends `xhigh` to the model and additionally has Claude orchestrate [dynamic workflows](/en/workflows) for substantive tasks. It applies to the current session only. Set it through `/effort`, or pass `"ultracode": true` via `--settings` or an Agent SDK control request. It is not part of the `effortLevel` setting, the `--effort` flag, or `CLAUDE_CODE_EFFORT_LEVEL`.

193

186#### Choose an effort level194#### Choose an effort level

187 195

188Each level trades token spend against capability. The default suits most coding tasks; adjust when you want a different balance.196Each level trades token spend against capability. The default suits most coding tasks; adjust when you want a different balance.

189 197

190| Level | When to use it |198| Level | When to use it |

191| :------- | :------------------------------------------------------------------------------------------------------------------------------------- |199| :---------- | :---------------------------------------------------------------------------------------------------------------------------------------------- |

192| `low` | Reserve for short, scoped, latency-sensitive tasks that are not intelligence-sensitive |200| `low` | Reserve for short, scoped, latency-sensitive tasks that are not intelligence-sensitive |

196| `max` | Can improve performance on demanding tasks but may show diminishing returns and is prone to overthinking. Test before adopting broadly |204| `max` | Can improve performance on demanding tasks but may show diminishing returns and is prone to overthinking. Test before adopting broadly |

205| `ultracode` | A Claude Code setting that plans a [dynamic workflow](/en/workflows) for each substantive task with `xhigh` per-message reasoning. Session-only |

197 206

198The effort scale is calibrated per model, so the same level name does not represent the same underlying value across models.207The effort scale is calibrated per model, so the same level name does not represent the same underlying value across models.

199 208

209* **In `/model`**: use left/right arrow keys to adjust the effort slider when selecting a model218* **In `/model`**: use left/right arrow keys to adjust the effort slider when selecting a model

210* **`--effort` flag**: pass a level name to set it for a single session when launching Claude Code219* **`--effort` flag**: pass a level name to set it for a single session when launching Claude Code

211* **Environment variable**: set `CLAUDE_CODE_EFFORT_LEVEL` to a level name or `auto`220* **Environment variable**: set `CLAUDE_CODE_EFFORT_LEVEL` to a level name or `auto`

212* **Settings**: set `effortLevel` to `low`, `medium`, `high`, or `xhigh` in your settings file. `max` is [session-only](#adjust-effort-level) and is not accepted here221* **Settings**: set `effortLevel` to `low`, `medium`, `high`, or `xhigh` in your settings file. `max` and `ultracode` are [session-only](#adjust-effort-level) and are not accepted here

213* **Skill and subagent frontmatter**: set `effort` in a [skill](/en/skills#frontmatter-reference) or [subagent](/en/sub-agents#supported-frontmatter-fields) markdown file to override the effort level when that skill or subagent runs222* **Skill and subagent frontmatter**: set `effort` in a [skill](/en/skills#frontmatter-reference) or [subagent](/en/sub-agents#supported-frontmatter-fields) markdown file to override the effort level when that skill or subagent runs

214 223

215The environment variable takes precedence over all other methods, then your configured level, then the model default. Frontmatter effort applies when that skill or subagent is active, overriding the session level but not the environment variable.224The environment variable takes precedence over all other methods, then your configured level, then the model default. Frontmatter effort applies when that skill or subagent is active, overriding the session level but not the environment variable.

220 229

221Adaptive reasoning makes thinking optional on each step, so Claude can respond faster to routine prompts and reserve deeper thinking for steps that benefit from it. If you want Claude to think more or less often than the current level produces, you can say so directly in your prompt or in `CLAUDE.md`; the model responds to that guidance within its effort setting.230Adaptive reasoning makes thinking optional on each step, so Claude can respond faster to routine prompts and reserve deeper thinking for steps that benefit from it. If you want Claude to think more or less often than the current level produces, you can say so directly in your prompt or in `CLAUDE.md`; the model responds to that guidance within its effort setting.

222 231

223Opus 4.7 always uses adaptive reasoning. The fixed thinking budget mode and `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` do not apply to it.232Opus 4.7 and later always use adaptive reasoning. The fixed thinking budget mode and `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` do not apply to them.

224 233

225On Opus 4.6 and Sonnet 4.6, you can set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1` to revert to the previous fixed thinking budget controlled by `MAX_THINKING_TOKENS`. See [environment variables](/en/env-vars).234On Opus 4.6 and Sonnet 4.6, you can set `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1` to revert to the previous fixed thinking budget controlled by `MAX_THINKING_TOKENS`. See [environment variables](/en/env-vars).

226 235

238 247

239### Extended context248### Extended context

240 249

241Opus 4.7, Opus 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.250Opus 4.6 and later, 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.

242 251

243Availability 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. Sonnet with 1M context is not part of the automatic upgrade and requires [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) on every subscription plan, including Max.252Availability 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. Sonnet with 1M context is not part of the automatic upgrade and requires [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans) on every subscription plan, including Max.

244 253

262/model sonnet[1m]271/model sonnet[1m]

263 272

264# Or append [1m] to a full model name273# Or append [1m] to a full model name

265/model claude-opus-4-7[1m]274/model claude-opus-4-8[1m]

266```275```

267 276

268## Checking your current model277## Checking your current model

317 326

318| Provider | Example |327| Provider | Example |

319| :-------- | :------------------------------------------------------------------- |328| :-------- | :------------------------------------------------------------------- |

323 332

324Apply 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.333Apply 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.

325 334

326To 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`:335To 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`:

327 336

328```bash theme={null}337```bash theme={null}

329export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-7[1m]'338export ANTHROPIC_DEFAULT_OPUS_MODEL='claude-opus-4-8[1m]'

330```339```

331 340

332The `[1m]` suffix applies the 1M context window to all usage of that alias, including `opusplan`.341The `[1m]` suffix applies the 1M context window to all usage of that alias, including `opusplan`.

en/monitoring-usage.md +1 −0

Details

940* `pre_tokens`: Approximate token count before compaction940* `pre_tokens`: Approximate token count before compaction

941* `post_tokens`: Approximate token count after compaction941* `post_tokens`: Approximate token count after compaction

942* `error`: Error message when compaction failed942* `error`: Error message when compaction failed

943* `precompute_reuse`: Only set when `trigger` is `"manual"`. Auto-compaction can prepare a summary in the background before the context window fills, and this attribute records whether `/compact` reused that prepared summary. `"hit"` means it was reused; `"miss_custom_instructions"`, `"miss_hook"`, and `"miss_not_ready"` give the reason a fresh summary was computed instead. {/* min-version: 2.1.153 */}Requires Claude Code v2.1.153 or later

943 944

944#### Feedback survey event945#### Feedback survey event

945 946

en/permission-modes.md +3 −3

Details

73 | Auto mode | `auto` |73 | Auto mode | `auto` |

74 | Bypass permissions | `bypassPermissions` |74 | Bypass permissions | `bypassPermissions` |

75 75

76 Auto mode appears in the mode indicator after you enable **Allow dangerously skip permissions** in the extension settings, but it stays unavailable until your account meets every requirement listed in the [auto mode section](#eliminate-prompts-with-auto-mode). The `claudeCode.initialPermissionMode` setting does not accept `auto`. To start in auto mode by default, set `defaultMode` in your [user settings](/en/settings#settings-files) instead. Claude Code ignores `defaultMode: "auto"` in project and local settings.76 Auto mode appears in the mode indicator when your account meets every requirement listed in the [auto mode section](#eliminate-prompts-with-auto-mode). The `claudeCode.initialPermissionMode` setting does not accept `auto`. To start in auto mode by default, set `defaultMode` in your [user settings](/en/settings#settings-files) instead. Claude Code ignores `defaultMode: "auto"` in project and local settings.

77 77

~~78 Bypass permissions also requires the **Allow dangerously skip permissions** toggle before it appears in the mode indicator.~~78 Bypass permissions requires the **Allow dangerously skip permissions** toggle in the extension settings before it appears in the mode indicator.

79 79

80 See the [VS Code guide](/en/vs-code) for extension-specific details.80 See the [VS Code guide](/en/vs-code) for extension-specific details.

81 </Tab>81 </Tab>

174 174

175* **Plan**: All plans.175* **Plan**: All plans.

176* **Admin**: on Team and Enterprise, an admin must enable it in [Claude Code admin settings](https://claude.ai/admin-settings/claude-code) before users can turn it on. Admins can also lock it off by setting `permissions.disableAutoMode` to `"disable"` in [managed settings](/en/permissions#managed-settings).176* **Admin**: on Team and Enterprise, an admin must enable it in [Claude Code admin settings](https://claude.ai/admin-settings/claude-code) before users can turn it on. Admins can also lock it off by setting `permissions.disableAutoMode` to `"disable"` in [managed settings](/en/permissions#managed-settings).

177* **Model**: Claude Sonnet 4.6, Opus 4.6, or Opus 4.7. Older models, including Sonnet 4.5, Opus 4.5, Haiku, and claude-3 models, are not supported.177* **Model**: Claude Opus 4.6 or later, or Sonnet 4.6. Older models, including Sonnet 4.5, Opus 4.5, Haiku, and claude-3 models, are not supported.

178* **Provider**: Anthropic API only. Not available on Bedrock, Vertex, or Foundry.178* **Provider**: Anthropic API only. Not available on Bedrock, Vertex, or Foundry.

179 179

180If Claude Code reports auto mode as unavailable, one of these requirements is unmet; this is not a transient outage. A separate message that names a model and says auto mode "cannot determine the safety" of an action is a transient classifier outage; see the [error reference](/en/errors#auto-mode-cannot-determine-the-safety-of-an-action).180If Claude Code reports auto mode as unavailable, one of these requirements is unmet; this is not a transient outage. A separate message that names a model and says auto mode "cannot determine the safety" of an action is a transient classifier outage; see the [error reference](/en/errors#auto-mode-cannot-determine-the-safety-of-an-action).

en/plugin-dependencies.md +2 −0

Details

127| A dependency is set to `false` at a scope with higher precedence than the target scope | Enable fails. Enable the dependency at that scope, or pass `--scope` to write there. |127| A dependency is set to `false` at a scope with higher precedence than the target scope | Enable fails. Enable the dependency at that scope, or pass `--scope` to write there. |

128| All dependencies are installed and allowed | Enable succeeds and writes `true` for the plugin and each dependency that was not already enabled at the target scope. |128| All dependencies are installed and allowed | Enable succeeds and writes `true` for the plugin and each dependency that was not already enabled at the target scope. |

129 129

130This holds even when a dependency sets [`defaultEnabled: false`](/en/plugins-reference#default-enablement) in its manifest, because Claude Code writes an explicit `true` for it. The same applies at install: a dependency pulled in to satisfy an active plugin installs with `true` regardless of its own default.

131

130When you disable a plugin, Claude Code refuses if another enabled plugin still depends on it. The error names the plugins that depend on it and gives you a chained command that disables them in the right order, ending with the one you asked for.132When you disable a plugin, Claude Code refuses if another enabled plugin still depends on it. The error names the plugins that depend on it and gives you a chained command that disables them in the right order, ending with the one you asked for.

131 133

132For example, if `deploy-kit` depends on `secrets-vault`, disabling `secrets-vault` alone fails with output similar to the following:134For example, if `deploy-kit` depends on `secrets-vault`, disabling `secrets-vault` alone fails with output similar to the following:

en/plugin-marketplaces.md +4 −1

Details

199**Standard metadata fields:**199**Standard metadata fields:**

200 200

202| :------------ | :------ | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |202| :--------------- | :------ | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

203| `displayName` | string | {/* min-version: 2.1.143 */}Human-readable name shown in UI surfaces. Falls back to `name` when omitted. May contain spaces and any casing. Not used for namespacing or lookup. Requires Claude Code v2.1.143 or later. |203| `displayName` | string | {/* min-version: 2.1.143 */}Human-readable name shown in UI surfaces. Falls back to `name` when omitted. May contain spaces and any casing. Not used for namespacing or lookup. Requires Claude Code v2.1.143 or later. |

205| `version` | string | Plugin version. If set (here or in `plugin.json`), the plugin is pinned to this string and users only receive updates when it changes. Omit to fall back to the git commit SHA. See [Version resolution](#version-resolution-and-release-channels). |205| `version` | string | Plugin version. If set (here or in `plugin.json`), the plugin is pinned to this string and users only receive updates when it changes. Omit to fall back to the git commit SHA. See [Version resolution](#version-resolution-and-release-channels). |

214| `defaultEnabled` | boolean | {/* min-version: 2.1.154 */}Whether the plugin is enabled after install (default: true). Set to `false` to install the plugin disabled until the user opts in. Takes precedence over the same field in the plugin's `plugin.json`. See [Default enablement](/en/plugins-reference#default-enablement). Requires Claude Code v2.1.154 or later. |

214 215

215**Component configuration fields:**216**Component configuration fields:**

216 217

905| :------- | :------------- |906| :------- | :------------- |

907 908

909With `--json`, each entry includes `name`, `source`, and source-specific fields: `repo` for GitHub sources, `url` for git and URL sources, and `path` for local sources. GitHub and git sources also include a `ref` field when the marketplace was added with a pinned branch or tag.

910

908### Plugin marketplace remove911### Plugin marketplace remove

909 912

910Remove a configured marketplace. The alias `rm` is also accepted.913Remove a configured marketplace. The alias `rm` is also accepted.

en/plugins-reference.md +13 −1

Details

438### Metadata fields438### Metadata fields

439 439

441| :------------ | :----- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------- |441| :--------------- | :------ | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------- |

443| `displayName` | string | {/* min-version: 2.1.143 */}Human-readable name shown in the `/plugin` picker and other UI surfaces. Falls back to `name` when omitted. Unlike `name`, may contain spaces and any casing. Not used for namespacing or lookup. Requires Claude Code v2.1.143 or later. | `"Deployment Tools"` |443| `displayName` | string | {/* min-version: 2.1.143 */}Human-readable name shown in the `/plugin` picker and other UI surfaces. Falls back to `name` when omitted. Unlike `name`, may contain spaces and any casing. Not used for namespacing or lookup. Requires Claude Code v2.1.143 or later. | `"Deployment Tools"` |

444| `version` | string | Optional. Semantic version. Setting this pins the plugin to that version string, so users only receive updates when you bump it. If omitted, Claude Code falls back to the git commit SHA, so every commit is treated as a new version. If also set in the marketplace entry, `plugin.json` wins. See [Version management](#version-management). | `"2.1.0"` |444| `version` | string | Optional. Semantic version. Setting this pins the plugin to that version string, so users only receive updates when you bump it. If omitted, Claude Code falls back to the git commit SHA, so every commit is treated as a new version. If also set in the marketplace entry, `plugin.json` wins. See [Version management](#version-management). | `"2.1.0"` |

451| `defaultEnabled` | boolean | {/* min-version: 2.1.154 */}Whether the plugin starts in an enabled state when the user has not set one. Defaults to `true`. See [Default enablement](#default-enablement). Requires Claude Code v2.1.154 or later. | `false` |

452

453### Default enablement

454

455Set `defaultEnabled: false` in `plugin.json` to ship a plugin that installs disabled. The user turns it on with `claude plugin enable <plugin>` or the `/plugin` interface. Use this for plugins that add cost or scope a user should opt into, such as one that connects to an external service. This requires Claude Code v2.1.154 or later. Earlier versions ignore the field and enable the plugin on install.

456

457`defaultEnabled` is the fallback when nothing else has decided the plugin's state. Two things take precedence over it:

458

459* **The user's setting**: an entry for the plugin in `enabledPlugins` at any settings scope. Once written, it persists across plugin updates and reinstalls, so changing `defaultEnabled` in a later release does not flip an existing user.

460* **A dependency requirement**: when a plugin is required by another one that is active, Claude Code writes `true` for it at install or enable time. That gives it an explicit setting, so its own default no longer applies. See [Enable or disable a plugin with dependencies](/en/plugin-dependencies#enable-or-disable-a-plugin-with-dependencies).

461

462The same field can appear in a plugin's marketplace entry, where it takes precedence over the value in `plugin.json`. See [Optional plugin fields](/en/plugin-marketplaces#optional-plugin-fields).

451 463

452### Component path fields464### Component path fields

453 465

en/settings.md +5 −1

Details

205| `disableRemoteControl` | {/* min-version: 2.1.128 */}Disable [Remote Control](/en/remote-control): blocks `claude remote-control`, the `--remote-control` flag, auto-start, and the in-session toggle. Typically placed in [managed settings](/en/permissions#managed-settings) for per-device MDM enforcement, but works from any scope. Requires Claude Code v2.1.128 or later | `true` |205| `disableRemoteControl` | {/* min-version: 2.1.128 */}Disable [Remote Control](/en/remote-control): blocks `claude remote-control`, the `--remote-control` flag, auto-start, and the in-session toggle. Typically placed in [managed settings](/en/permissions#managed-settings) for per-device MDM enforcement, but works from any scope. Requires Claude Code v2.1.128 or later | `true` |

206| `disableSkillShellExecution` | Disable inline shell execution for `` !`...` `` and ` ```! ` blocks in [skills](/en/skills) and custom commands from user, project, plugin, or additional-directory sources. Commands are replaced with `[shell command execution disabled by policy]` instead of being run. Bundled and managed skills are not affected. Most useful in [managed settings](/en/permissions#managed-settings) where users cannot override it | `true` |206| `disableSkillShellExecution` | Disable inline shell execution for `` !`...` `` and ` ```! ` blocks in [skills](/en/skills) and custom commands from user, project, plugin, or additional-directory sources. Commands are replaced with `[shell command execution disabled by policy]` instead of being run. Bundled and managed skills are not affected. Most useful in [managed settings](/en/permissions#managed-settings) where users cannot override it | `true` |

207| `disableWorkflows` | Disable [dynamic workflows](/en/workflows#turn-workflows-off) and the bundled workflow commands. Default: `false`. Equivalent to setting `CLAUDE_CODE_DISABLE_WORKFLOWS` to `1` | `true` |

207| `editorMode` | Key binding mode for the input prompt: `"normal"` or `"vim"`. Default: `"normal"`. Appears in `/config` as **Editor mode** | `"vim"` |208| `editorMode` | Key binding mode for the input prompt: `"normal"` or `"vim"`. Default: `"normal"`. Appears in `/config` as **Editor mode** | `"vim"` |

208| `effortLevel` | Persist the [effort level](/en/model-config#adjust-effort-level) across sessions. Accepts `"low"`, `"medium"`, `"high"`, or `"xhigh"`. Written automatically when you run `/effort` with one of those values. `--effort` and [`CLAUDE_CODE_EFFORT_LEVEL`](/en/env-vars) override this for one session. See [Adjust effort level](/en/model-config#adjust-effort-level) for supported models | `"xhigh"` |209| `effortLevel` | Persist the [effort level](/en/model-config#adjust-effort-level) across sessions. Accepts `"low"`, `"medium"`, `"high"`, or `"xhigh"`. Written automatically when you run `/effort` with one of those values. `--effort` and [`CLAUDE_CODE_EFFORT_LEVEL`](/en/env-vars) override this for one session. See [Adjust effort level](/en/model-config#adjust-effort-level) for supported models | `"xhigh"` |

254| `teammateMode` | How [agent team](/en/agent-teams) teammates display: `auto` (picks split panes in tmux or iTerm2, in-process otherwise), `in-process`, or `tmux`. `--teammate-mode` overrides this for one session. See [choose a display mode](/en/agent-teams#choose-a-display-mode) | `"in-process"` |255| `teammateMode` | How [agent team](/en/agent-teams) teammates display: `auto` (picks split panes in tmux or iTerm2, in-process otherwise), `in-process`, or `tmux`. `--teammate-mode` overrides this for one session. See [choose a display mode](/en/agent-teams#choose-a-display-mode) | `"in-process"` |

255| `terminalProgressBarEnabled` | Show the terminal progress bar in supported terminals: ConEmu, Ghostty 1.2.0+, and iTerm2 3.6.6+. Default: `true`. Appears in `/config` as **Terminal progress bar** | `false` |256| `terminalProgressBarEnabled` | Show the terminal progress bar in supported terminals: ConEmu, Ghostty 1.2.0+, and iTerm2 3.6.6+. Default: `true`. Appears in `/config` as **Terminal progress bar** | `false` |

256| `tui` | Terminal UI renderer. Use `"fullscreen"` for the flicker-free [alt-screen renderer](/en/fullscreen) with virtualized scrollback. Use `"default"` for the classic main-screen renderer. Set via `/tui`. You can also set the [`CLAUDE_CODE_NO_FLICKER`](/en/env-vars) environment variable | `"fullscreen"` |257| `tui` | Terminal UI renderer. Use `"fullscreen"` for the flicker-free [alt-screen renderer](/en/fullscreen) with virtualized scrollback. Use `"default"` for the classic main-screen renderer. Set via `/tui`. You can also set the [`CLAUDE_CODE_NO_FLICKER`](/en/env-vars) environment variable | `"fullscreen"` |

258| `ultracode` | Turn on [ultracode](/en/workflows#let-claude-decide-with-ultracode) for the session. Session-only and not read from `settings.json`. Set through `/effort ultracode`, `--settings`, or an Agent SDK control request | `true` |

257| `useAutoModeDuringPlan` | Whether plan mode uses auto mode semantics when auto mode is available. Default: `true`. Not read from shared project settings. Appears in `/config` as "Use auto mode during plan" | `false` |259| `useAutoModeDuringPlan` | Whether plan mode uses auto mode semantics when auto mode is available. Default: `true`. Not read from shared project settings. Appears in `/config` as "Use auto mode during plan" | `false` |

258| `viewMode` | Default transcript view mode on startup: `"default"`, `"verbose"`, or `"focus"`. Overrides the sticky `/focus` selection when set. The `--verbose` flag overrides this for one session | `"verbose"` |260| `viewMode` | Default transcript view mode on startup: `"default"`, `"verbose"`, or `"focus"`. Overrides the sticky `/focus` selection when set. The `--verbose` flag overrides this for one session | `"verbose"` |

259| `voice` | [Voice dictation](/en/voice-dictation) settings: `enabled` turns dictation on, `mode` selects `"hold"` or `"tap"`, and `autoSubmit` sends the prompt on key release in hold mode. Written automatically when you run `/voice`. Requires a Claude.ai account | `{ "enabled": true, "mode": "tap" }` |261| `voice` | [Voice dictation](/en/voice-dictation) settings: `enabled` turns dictation on, `mode` selects `"hold"` or `"tap"`, and `autoSubmit` sends the prompt on key release in hold mode. Written automatically when you run `/voice`. Requires a Claude.ai account | `{ "enabled": true, "mode": "tap" }` |

624 626

625#### `enabledPlugins`627#### `enabledPlugins`

626 628

627Controls which plugins are enabled. Format: `"plugin-name@marketplace-name": true/false`629Controls which plugins are enabled. Format: `"plugin-name@marketplace-name": true/false`. A plugin with no entry at any scope falls back to its [`defaultEnabled`](/en/plugins-reference#default-enablement) value.

628 630

629**Scopes**:631**Scopes**:

630 632

691* `hostPattern`: regex pattern to match marketplace hosts (uses `hostPattern`)693* `hostPattern`: regex pattern to match marketplace hosts (uses `hostPattern`)

692* `settings`: inline marketplace declared directly in settings.json without a separate hosted repository (uses `name` and `plugins`)694* `settings`: inline marketplace declared directly in settings.json without a separate hosted repository (uses `name` and `plugins`)

693 695

696For `github` and `git` sources, set `"skipLfs": true` inside the `source` object (alongside `repo` or `url`) to skip Git LFS downloads when Claude Code clones or updates the marketplace repository. LFS pointer files remain as pointers instead of downloading their content. Use this when the repository contains large LFS objects unrelated to plugin content. {/* min-version: 2.1.153 */}Requires Claude Code v2.1.153 or later.

697

694Each marketplace entry also accepts an optional `autoUpdate` Boolean. Set `"autoUpdate": true` alongside `source` to make Claude Code refresh that marketplace and update its installed plugins at startup. When omitted, official Anthropic marketplaces default to `true` and all other marketplaces default to `false`. See [Configure auto-updates](/en/discover-plugins#configure-auto-updates).698Each marketplace entry also accepts an optional `autoUpdate` Boolean. Set `"autoUpdate": true` alongside `source` to make Claude Code refresh that marketplace and update its installed plugins at startup. When omitted, official Anthropic marketplaces default to `true` and all other marketplaces default to `false`. See [Configure auto-updates](/en/discover-plugins#configure-auto-updates).

695 699

696Use `source: 'settings'` to declare a small set of plugins inline without setting up a hosted marketplace repository. Plugins listed here must reference external sources such as GitHub or npm. You still need to enable each plugin separately in `enabledPlugins`.700Use `source: 'settings'` to declare a small set of plugins inline without setting up a hosted marketplace repository. Plugins listed here must reference external sources such as GitHub or npm. You still need to enable each plugin separately in `enabledPlugins`.

en/setup.md +4 −0

Details

184 184

185Claude Code checks for updates on startup and periodically while running. Updates download and install in the background, then take effect the next time you start Claude Code.185Claude Code checks for updates on startup and periodically while running. Updates download and install in the background, then take effect the next time you start Claude Code.

186 186

187Run `claude doctor` to see the result of the most recent update attempt.

188

189If an npm global install can't auto-update because the npm global directory isn't writable, Claude Code shows a one-time notice at startup, and `claude doctor` lists the available fixes. See [permission errors during installation](/en/troubleshoot-install#permission-errors-during-installation) for details.

190

187<Note>191<Note>

188 Homebrew, WinGet, apt, dnf, and apk installations do not auto-update by default; see below to opt in for Homebrew and WinGet. To upgrade Homebrew manually, run `brew upgrade claude-code` or `brew upgrade claude-code@latest`, depending on which cask you installed. For WinGet, run `winget upgrade Anthropic.ClaudeCode`. For Linux package managers, see the upgrade commands in [Install with Linux package managers](#install-with-linux-package-managers).192 Homebrew, WinGet, apt, dnf, and apk installations do not auto-update by default; see below to opt in for Homebrew and WinGet. To upgrade Homebrew manually, run `brew upgrade claude-code` or `brew upgrade claude-code@latest`, depending on which cask you installed. For WinGet, run `winget upgrade Anthropic.ClaudeCode`. For Linux package managers, see the upgrade commands in [Install with Linux package managers](#install-with-linux-package-managers).

189 193

en/skills.md +1 −1

Details

249| `$N` | Shorthand for `$ARGUMENTS[N]`, such as `$0` for the first argument or `$1` for the second. |249| `$N` | Shorthand for `$ARGUMENTS[N]`, such as `$0` for the first argument or `$1` for the second. |

250| `$name` | Named argument declared in the [`arguments`](#frontmatter-reference) frontmatter list. Names map to positions in order, so with `arguments: [issue, branch]` the placeholder `$issue` expands to the first argument and `$branch` to the second. |250| `$name` | Named argument declared in the [`arguments`](#frontmatter-reference) frontmatter list. Names map to positions in order, so with `arguments: [issue, branch]` the placeholder `$issue` expands to the first argument and `$branch` to the second. |

251| `${CLAUDE_SESSION_ID}` | The current session ID. Useful for logging, creating session-specific files, or correlating skill output with sessions. |251| `${CLAUDE_SESSION_ID}` | The current session ID. Useful for logging, creating session-specific files, or correlating skill output with sessions. |

252| `${CLAUDE_EFFORT}` | The current effort level: `low`, `medium`, `high`, `xhigh`, or `max`. Use this to adapt skill instructions to the active effort setting. |252| `${CLAUDE_EFFORT}` | The current effort level: `low`, `medium`, `high`, `xhigh`, `max`, or `ultra`. The `ultra` value is the stored value for ultracode. Use this to adapt skill instructions to the active effort setting. |

253| `${CLAUDE_SKILL_DIR}` | The directory containing the skill's `SKILL.md` file. For plugin skills, this is the skill's subdirectory within the plugin, not the plugin root. Use this in bash injection commands to reference scripts or files bundled with the skill, regardless of the current working directory. |253| `${CLAUDE_SKILL_DIR}` | The directory containing the skill's `SKILL.md` file. For plugin skills, this is the skill's subdirectory within the plugin, not the plugin root. Use this in bash injection commands to reference scripts or files bundled with the skill, regardless of the current working directory. |

254 254

255Indexed arguments use shell-style quoting, so wrap multi-word values in quotes to pass them as a single argument. For example, `/my-skill "hello world" second` makes `$0` expand to `hello world` and `$1` to `second`. The `$ARGUMENTS` placeholder always expands to the full argument string as typed.255Indexed arguments use shell-style quoting, so wrap multi-word values in quotes to pass them as a single argument. For example, `/my-skill "hello world" second` makes `$0` expand to `hello world` and `$1` to `second`. The `$ARGUMENTS` placeholder always expands to the full argument string as typed.

en/slash-commands.md +1 −1

Details

254 254

en/statusline.md +7 −3

Details

144* **Colors**: use [ANSI escape codes](https://en.wikipedia.org/wiki/ANSI_escape_code#Colors) like `\033[32m` for green (terminal must support them). See the [git status example](#git-status-with-colors).144* **Colors**: use [ANSI escape codes](https://en.wikipedia.org/wiki/ANSI_escape_code#Colors) like `\033[32m` for green (terminal must support them). See the [git status example](#git-status-with-colors).

145* **Links**: use [OSC 8 escape sequences](https://en.wikipedia.org/wiki/ANSI_escape_code#OSC) to make text clickable (Cmd+click on macOS, Ctrl+click on Windows/Linux). Requires a terminal that supports hyperlinks like iTerm2, Kitty, or WezTerm. See the [clickable links example](#clickable-links).145* **Links**: use [OSC 8 escape sequences](https://en.wikipedia.org/wiki/ANSI_escape_code#OSC) to make text clickable (Cmd+click on macOS, Ctrl+click on Windows/Linux). Requires a terminal that supports hyperlinks like iTerm2, Kitty, or WezTerm. See the [clickable links example](#clickable-links).

146 146

147**Sizing output to the terminal**

148

149Claude Code captures your script's output instead of connecting it directly to the terminal, so `tput cols` and language-level width detection cannot read the terminal size from inside the script. {/* min-version: 2.1.153 */}Read the `COLUMNS` and `LINES` environment variables instead. Claude Code sets these to the current terminal dimensions before running your script. Requires Claude Code v2.1.153 or later.

150

147<Note>The status line runs locally and does not consume API tokens. It temporarily hides during certain UI interactions, including autocomplete suggestions, the help menu, and permission prompts.</Note>151<Note>The status line runs locally and does not consume API tokens. It temporarily hides during certain UI interactions, including autocomplete suggestions, the help menu, and permission prompts.</Note>

148 152

149## Available data153## Available data

151Claude Code sends the following JSON fields to your script via stdin:155Claude Code sends the following JSON fields to your script via stdin:

152 156

153| Field | Description |157| Field | Description |

154| -------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |158| -------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

156| `cwd`, `workspace.current_dir` | Current working directory. Both fields contain the same value; `workspace.current_dir` is preferred for consistency with `workspace.project_dir`. |160| `cwd`, `workspace.current_dir` | Current working directory. Both fields contain the same value; `workspace.current_dir` is preferred for consistency with `workspace.project_dir`. |

157| `workspace.project_dir` | Directory where Claude Code was launched, which may differ from `cwd` if the working directory changes during a session |161| `workspace.project_dir` | Directory where Claude Code was launched, which may differ from `cwd` if the working directory changes during a session |

169| `context_window.current_usage` | Token counts from the last API call, described in [context window fields](#context-window-fields) |173| `context_window.current_usage` | Token counts from the last API call, described in [context window fields](#context-window-fields) |

170| `exceeds_200k_tokens` | Whether the total token count (input, cache, and output tokens combined) from the most recent API response exceeds 200k. This is a fixed threshold regardless of actual context window size. |174| `exceeds_200k_tokens` | Whether the total token count (input, cache, and output tokens combined) from the most recent API response exceeds 200k. This is a fixed threshold regardless of actual context window size. |

171| `effort.level` | Current reasoning effort (`low`, `medium`, `high`, `xhigh`, or `max`). Reflects the live session value, including mid-session `/effort` changes. Absent when the current model does not support the effort parameter |175| `effort.level` | Current reasoning effort (`low`, `medium`, `high`, `xhigh`, `max`, or `ultra`). The `ultra` value corresponds to ultracode in `/effort`; the field reports the stored value, not the display label. Reflects the live session value, including mid-session `/effort` changes. Absent when the current model does not support the effort parameter |

173| `rate_limits.five_hour.used_percentage`, `rate_limits.seven_day.used_percentage` | Percentage of the 5-hour or 7-day rate limit consumed, from 0 to 100 |177| `rate_limits.five_hour.used_percentage`, `rate_limits.seven_day.used_percentage` | Percentage of the 5-hour or 7-day rate limit consumed, from 0 to 100 |

174| `rate_limits.five_hour.resets_at`, `rate_limits.seven_day.resets_at` | Unix epoch seconds when the 5-hour or 7-day rate limit window resets |178| `rate_limits.five_hour.resets_at`, `rate_limits.seven_day.resets_at` | Unix epoch seconds when the 5-hour or 7-day rate limit window resets |

197 "session_name": "my-session",201 "session_name": "my-session",

198 "transcript_path": "/path/to/transcript.jsonl",202 "transcript_path": "/path/to/transcript.jsonl",

199 "model": {203 "model": {

200 "id": "claude-opus-4-7",204 "id": "claude-opus-4-8",

201 "display_name": "Opus"205 "display_name": "Opus"

202 },206 },

203 "workspace": {207 "workspace": {

en/sub-agents.md +12 −2

Details

268| `description` | Yes | When Claude should delegate to this subagent |268| `description` | Yes | When Claude should delegate to this subagent |

269| `tools` | No | [Tools](#available-tools) the subagent can use. Inherits all tools if omitted. To preload Skills into context, use the `skills` field rather than listing `Skill` here |269| `tools` | No | [Tools](#available-tools) the subagent can use. Inherits all tools if omitted. To preload Skills into context, use the `skills` field rather than listing `Skill` here |

270| `disallowedTools` | No | Tools to deny, removed from inherited or specified list |270| `disallowedTools` | No | Tools to deny, removed from inherited or specified list |

271| `model` | No | [Model](#choose-a-model) to use: `sonnet`, `opus`, `haiku`, a full model ID (for example, `claude-opus-4-7`), or `inherit`. Defaults to `inherit` |271| `model` | No | [Model](#choose-a-model) to use: `sonnet`, `opus`, `haiku`, a full model ID (for example, `claude-opus-4-8`), or `inherit`. Defaults to `inherit` |

272| `permissionMode` | No | [Permission mode](#permission-modes): `default`, `acceptEdits`, `auto`, `dontAsk`, `bypassPermissions`, or `plan`. Ignored for [plugin subagents](#choose-the-subagent-scope) |272| `permissionMode` | No | [Permission mode](#permission-modes): `default`, `acceptEdits`, `auto`, `dontAsk`, `bypassPermissions`, or `plan`. Ignored for [plugin subagents](#choose-the-subagent-scope) |

273| `maxTurns` | No | Maximum number of agentic turns before the subagent stops |273| `maxTurns` | No | Maximum number of agentic turns before the subagent stops |

274| `skills` | No | [Skills](/en/skills) to preload into the subagent's context at startup. The full skill content is injected, not just the description. Subagents can still invoke unlisted project, user, and plugin skills through the Skill tool |274| `skills` | No | [Skills](/en/skills) to preload into the subagent's context at startup. The full skill content is injected, not just the description. Subagents can still invoke unlisted project, user, and plugin skills through the Skill tool |

286The `model` field controls which [AI model](/en/model-config) the subagent uses:286The `model` field controls which [AI model](/en/model-config) the subagent uses:

287 287

288* **Model alias**: Use one of the available aliases: `sonnet`, `opus`, or `haiku`288* **Model alias**: Use one of the available aliases: `sonnet`, `opus`, or `haiku`

289* **Full model ID**: Use a full model ID such as `claude-opus-4-7` or `claude-sonnet-4-6`. Accepts the same values as the `--model` flag289* **Full model ID**: Use a full model ID such as `claude-opus-4-8` or `claude-sonnet-4-6`. Accepts the same values as the `--model` flag

290* **inherit**: Use the same model as the main conversation290* **inherit**: Use the same model as the main conversation

291* **Omitted**: If not specified, defaults to `inherit` (uses the same model as the main conversation)291* **Omitted**: If not specified, defaults to `inherit` (uses the same model as the main conversation)

292 292

394 394

395To 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.395To 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.

396 396

397As of v2.1.153, the MCP restrictions that apply to the main session also cover servers declared in subagent frontmatter:

398

399* [`--strict-mcp-config`](/en/cli-reference) and [`--bare`](/en/cli-reference)

400* [Enterprise managed MCP configuration](/en/managed-mcp)

401* [`allowedMcpServers` and `deniedMcpServers` policies](/en/managed-mcp#policy-based-control-with-allowlists-and-denylists)

402

403When one of these blocks a server, Claude Code skips it and shows a warning naming the blocked servers.

404

405Managed-settings restrictions apply to every subagent regardless of how it is defined. `--strict-mcp-config` does not filter servers you pass inline via `--agents` or the SDK `agents` option, since those are explicit caller input.

406

397#### Permission modes407#### Permission modes

398 408

399The `permissionMode` field controls how the subagent handles permission prompts. Subagents inherit the permission context from the main conversation and can override the mode, except when the parent mode takes precedence as described below.409The `permissionMode` field controls how the subagent handles permission prompts. Subagents inherit the permission context from the main conversation and can override the mode, except when the parent mode takes precedence as described below.

en/voice-dictation.md +1 −1

Details

14 14

15## Requirements15## Requirements

16 16

17Voice dictation streams your recorded audio to Anthropic's servers for transcription. Audio is not processed locally. The speech-to-text service is only available when you authenticate with a Claude.ai account, and is not available when Claude Code is configured to use an Anthropic API key directly, Amazon Bedrock, Google Vertex AI, or Microsoft Foundry. Transcription does not consume Claude messages or tokens and does not count toward the limits shown in `/usage`. See [data usage](/en/data-usage) for how Anthropic handles your data.17Voice dictation streams your recorded audio to Anthropic's servers for transcription. Audio is not processed locally. The speech-to-text service is only available when you authenticate with a Claude.ai account, and is not available when Claude Code is configured to use an Anthropic API key directly, Amazon Bedrock, Google Vertex AI, or Microsoft Foundry. Voice dictation is also not available when your organization has HIPAA compliance enabled. Transcription does not consume Claude messages or tokens and does not count toward the limits shown in `/usage`. See [data usage](/en/data-usage) for how Anthropic handles your data.

18 18

19Voice dictation also needs local microphone access, so it does not work in remote environments such as [Claude Code on the web](/en/claude-code-on-the-web) or SSH sessions. In WSL, voice dictation requires WSLg for audio access. WSLg is included with WSL2 when installed from the Microsoft Store on Windows 10 or 11. If WSLg is not available, for example on WSL1, run Claude Code in native Windows instead.19Voice dictation also needs local microphone access, so it does not work in remote environments such as [Claude Code on the web](/en/claude-code-on-the-web) or SSH sessions. In WSL, voice dictation requires WSLg for audio access. WSLg is included with WSL2 when installed from the Microsoft Store on Windows 10 or 11. If WSLg is not available, for example on WSL1, run Claude Code in native Windows instead.

20 20

en/vs-code.md +2 −2

Details

308### Extension settings308### Extension settings

309 309

311| ----------------------------------- | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |311| ----------------------------------- | --------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

313| `initialPermissionMode` | `default` | Controls approval prompts for new conversations: `default`, `plan`, `acceptEdits`, or `bypassPermissions`. See [permission modes](/en/permission-modes). |313| `initialPermissionMode` | `default` | Controls approval prompts for new conversations: `default`, `plan`, `acceptEdits`, or `bypassPermissions`. See [permission modes](/en/permission-modes). |

322| `environmentVariables` | `[]` | Set environment variables for the Claude process. Use Claude Code settings instead for shared config. |322| `environmentVariables` | `[]` | Set environment variables for the Claude process. Use Claude Code settings instead for shared config. |

324| `allowDangerouslySkipPermissions` | `false` | Adds [Auto mode](/en/permission-modes#eliminate-prompts-with-auto-mode) and Bypass permissions to the mode selector. Auto mode has [plan, admin, model, and provider requirements](/en/permission-modes#eliminate-prompts-with-auto-mode), so it may remain unavailable even with this toggle on. Use Bypass permissions only in sandboxes with no internet access. |324| `allowDangerouslySkipPermissions` | `false` | Adds Bypass permissions to the mode selector. Use it only in sandboxes with no internet access. |

325| `claudeProcessWrapper` | - | Executable used to launch the Claude process. The bundled binary path is passed as an argument when present. Set this to a separately installed `claude` binary if the extension build doesn't include one for your platform. |325| `claudeProcessWrapper` | - | Executable used to launch the Claude process. The bundled binary path is passed as an argument when present. Set this to a separately installed `claude` binary if the extension build doesn't include one for your platform. |

326 326

327## VS Code extension vs. Claude Code CLI327## VS Code extension vs. Claude Code CLI

en/workflows.md +239 −0 created

Details

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.

5# Orchestrate subagents at scale with dynamic workflows

7> Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.

9{/* plan-availability: feature=workflows plans=pro,max,team,enterprise providers=all */}

11<Note>

12 Dynamic workflows are in research preview. They require Claude Code v2.1.154 or later and are available on all paid plans, with Anthropic API access, and on Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry. On Pro, turn them on from the Dynamic workflows row in `/config`.

13</Note>

15A dynamic workflow is a JavaScript script that orchestrates [subagents](/en/sub-agents) at scale. Claude writes the script for the task you describe, and a runtime executes it in the background while your session stays responsive.

17Reach for a workflow when a task needs more agents than one conversation can coordinate, or when you want the orchestration codified as a script you can read and rerun. Examples include a codebase-wide bug sweep, a 500-file migration, a research question that needs sources cross-checked against each other, and a hard plan worth drafting from several independent angles before you commit to one.

19This page covers how to:

21* Decide [when to use a workflow](#when-to-use-a-workflow) instead of subagents or skills

22* [Run a bundled workflow](#run-a-bundled-workflow) with `/deep-research`

23* [Have Claude write a workflow](#have-claude-write-a-workflow) for your task and save it

24* Understand [how a workflow runs](#how-a-workflow-runs) and [manage runs](#manage-runs)

26## When to use a workflow

28[Subagents](/en/sub-agents), [skills](/en/skills), and workflows can all run a multi-step task. The difference is who holds the plan:

31| :------------------------------ | :----------------------------- | :--------------------------- | :----------------------------------- |

39A workflow moves the plan into code. With subagents and skills, Claude is the orchestrator: it decides turn by turn what to spawn next, and every result lands in Claude's context. A workflow script holds the loop, the branching, and the intermediate results itself, so Claude's context holds only the final answer.

41Moving the plan into code also lets a workflow apply a repeatable quality pattern, not just run more agents: it can have independent agents adversarially review each other's findings before they're reported, or draft a plan from several angles and weigh them against each other, so you get a more trustworthy result than a single pass.

43## Run a bundled workflow

45The quickest way to see a workflow in action is to run `/deep-research`, the [built-in workflow](#bundled-workflows) Claude Code includes for investigating a question across many sources. You'll see agents work through a set of phases in the background while your session stays free, and get one report at the end instead of a turn-by-turn transcript.

47<Steps>

48 <Step title="Run the workflow">

49 Run `/deep-research` with a question you want investigated. It fans out web searches across several angles, fetches and cross-checks the sources it finds, and synthesizes a cited report.

51 ```text theme={null}

52 /deep-research What changed in the Node.js permission model between v20 and v22?

53 ```

54 </Step>

56 <Step title="Allow workflows">

57 Claude Code asks whether to allow the workflow. Select **Yes** to continue. The exact prompt depends on your permission mode. See [Approve the plan before it runs](#approve-the-plan-before-it-runs) for the per-mode options.

58 </Step>

60 <Step title="Watch progress">

61 The run starts in the background. Run `/workflows`, use the arrow keys to select the run, and press Enter to open its progress view:

63 ```text theme={null}

64 /workflows

65 ```

67 The view shows each phase with its agent count, token total, and elapsed time. Drill into any phase to see its agents and what each one found. See [Watch the run](#watch-the-run) for the full set of controls.

69 You can also watch from the task panel below the input box: a one-line progress summary appears there while the run is going. Press the down arrow to focus it, then Enter to expand.

70 </Step>

72 <Step title="Read the report">

73 When the run finishes, the report lands in your session. It cites the sources each claim came from, with claims that didn't survive cross-checking already filtered out.

74 </Step>

75</Steps>

77To run a workflow for your own task, [have Claude write one](#have-claude-write-a-workflow), and once a run does what you wanted you can [save it](#save-the-workflow-for-reuse) as a command of your own.

79### Bundled workflows

81Claude Code includes `/deep-research` as a built-in workflow:

83| Command | What it does |

84| :-------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

85| `/deep-research <question>` | Fans out web searches on a question across several angles, fetches and cross-checks the sources it finds, votes on each claim, and returns a cited report with claims that didn't survive cross-checking filtered out. Requires the [WebSearch tool](/en/tools-reference#websearch-tool-behavior) to be available |

87[Workflows you save](#save-the-workflow-for-reuse) yourself become commands the same way and appear in `/` autocomplete alongside the bundled ones.

89### Watch the run

91Workflows run in the background, so the session stays responsive while agents work. Run `/workflows` at any time to list running and completed workflows, then select one to open its progress view.

93```text theme={null}

94/workflows

95```

97The progress view shows each phase with its agent counts, token totals, and elapsed time. The footer lists the key for each action:

99| Key | Action |

100| :------------- | :-------------------------------------------------------------------------------------------------- |

101| `↑` / `↓` | Select a phase or agent |

102| `Enter` or `→` | Drill into the selected phase, then into an agent to read its prompt, recent tool calls, and result |

103| `Esc` | Back out one level |

104| `j` / `k` | Scroll within the agent detail when it overflows |

105| `p` | Pause or resume the run |

106| `x` | Stop the selected agent, or stop the whole workflow when focus is on the run |

107| `r` | Restart the selected running agent |

108| `s` | [Save](#save-the-workflow-for-reuse) the run's script as a command |

109

110## Have Claude write a workflow

111

112You can have Claude write a workflow for your task in two ways:

113

114* [Ask for a workflow](#ask-for-a-workflow-in-your-prompt) in your prompt with the word `workflow`, and Claude writes one for the task.

115* [Let Claude decide with ultracode](#let-claude-decide-with-ultracode): set `/effort ultracode` and Claude plans a workflow for every substantive task in the session.

116

117You can also run a workflow command that already exists: a [bundled workflow](#bundled-workflows) like `/deep-research`, or one you've [saved](#save-the-workflow-for-reuse).

118

119### Ask for a workflow in your prompt

120

121To run a single task as a workflow without changing the session's effort level, include the word `workflow` anywhere in your prompt.

122

123```text theme={null}

124Run a workflow to audit every API endpoint under src/routes/ for missing auth checks

125```

126

127Claude Code highlights the word in your input and Claude writes a workflow script for the task instead of working through it turn by turn.

128

129If the run does what you wanted, you can [save it as a command](#save-the-workflow-for-reuse) afterward.

130

131If Claude Code highlights the word when you didn't mean to trigger one, press `alt+w` to ignore it for this prompt.

132

133### Let Claude decide with ultracode

134

135Ultracode is a Claude Code setting that combines `xhigh` [reasoning effort](/en/model-config#adjust-effort-level) with automatic workflow orchestration. With it on, Claude plans a workflow for each substantive task instead of waiting for you to ask.

136

137```text theme={null}

138/effort ultracode

139```

140

141With ultracode on, Claude decides when a task warrants a workflow. A single request can turn into several workflows in a row: one to understand the code, one to make the change, and one to verify it. This applies to every task in the session, so each request uses more tokens and takes longer than at lower effort levels.

142

143Ultracode lasts for the current session and resets when you start a new one. Drop back with `/effort high` when you return to routine work. It's available on models that support `xhigh` [effort](/en/model-config#adjust-effort-level); on other models the `/effort` menu doesn't offer it.

144

145### Approve the plan before it runs

146

147In the CLI, the per-run prompt shows the planned phases and these options:

148

149* **Yes, run it**: start the run

150* **Yes, and don't ask again for `<name>` in `<path>`**: start, and skip this prompt for this workflow in this project from now on

151* **View raw script**: read the script before deciding

152* **No**: cancel

153

154`Ctrl+G` opens the script in your editor. `Tab` lets you adjust the prompt before the run starts.

155

156Whether you see this prompt depends on your [permission mode](/en/permission-modes):

157

158| Permission mode | When you're prompted |

159| :----------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------ |

160| Default, accept edits | Every run, unless you've selected **Yes, and don't ask again** for that workflow in this project |

161| Auto | First launch only. Any **Yes** records consent in your user settings, and later launches start without prompting. Skipped entirely when ultracode is on |

162| Bypass permissions, `claude -p`, Agent SDK | Never. The run starts immediately |

163

164In the Desktop app, an approval card shows the workflow name, the phase list, and a token-usage caution, with **Once**, **Always**, and **Deny** actions. The progress view appears in the Background tasks side pane.

165

166Your permission mode controls only the launch prompt above. The subagents the workflow spawns always run in `acceptEdits` mode and inherit your [tool allowlist](/en/settings#permission-settings), regardless of your session's mode. File edits are auto-approved.

167

168Shell commands, web fetches, and MCP tools that aren't in your allowlist can still prompt you mid-run. To avoid this on a long run, add the commands the agents need to your allowlist before starting.

169

170In `claude -p` and the Agent SDK there is no one to prompt, so tool calls follow your configured permission rules without interactive confirmation.

171

172### Save the workflow for reuse

173

174When Claude writes a workflow for a task you'll repeat, you can save that run's script as a command. A process like a review you run on every branch then runs the same orchestration each time.

175

176Run `/workflows`, select the run you want to keep, and press `s`. In the save dialog, Tab toggles between the two save locations:

177

178* `.claude/workflows/` in your project: shared with everyone who clones the repo

179* `~/.claude/workflows/` in your home directory: available in every project, visible only to you

180

181Press Enter to save. The workflow runs as `/<name>` in future sessions from either location.

182

183If a project workflow and a personal workflow share a name, the project one runs.

184

185## How a workflow runs

186

187The workflow runtime executes the script in an isolated environment, separate from your conversation. Intermediate results stay in script variables instead of landing in Claude's context.

188

189The runtime tracks each agent's result as the run progresses, which is what makes a run [resumable](#resume-after-a-pause) within the same session.

190

191### Behavior and limits

192

193The runtime applies the following constraints:

194

195| Constraint | Why |

196| :------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------- |

197| No mid-run user input | Only agent permission prompts can pause a run. For sign-off between stages, run each stage as its own workflow |

198| No direct filesystem or shell access from the workflow itself | Agents read, write, and run commands. The script coordinates the agents |

199| Up to 16 concurrent agents, fewer on machines with limited CPU cores | Bounds local resource use |

200| 1,000 agents total per run | Prevents runaway loops |

201

202## Manage runs

203

204Once a run starts, you manage it from the `/workflows` view, or by expanding its progress line in the task panel below the input box.

205

206### Resume after a pause

207

208If you stop a run, you can resume it: agents that already completed return their cached results, and the rest run live. Resume a paused run from `/workflows` by selecting it and pressing `p`, or ask Claude to relaunch the workflow with the same script.

209

210Resume works within the same Claude Code session. If you exit Claude Code while a workflow is running, the next session starts the workflow fresh.

211

212### Cost

213

214A workflow spawns many agents, so a single run can use meaningfully more tokens than working through the same task in conversation. Runs count toward your plan's usage and rate limits like any other session. You can stop a running workflow from `/workflows` at any time without losing completed work.

215

216Every agent in a workflow uses your session's model unless the script routes a stage to a different one. To control the model cost:

217

218* Check `/model` before a large run if you usually switch to a smaller model for routine work

219* Ask Claude to use a smaller model for stages that don't need the strongest one when you describe the task

220

221### Turn workflows off

222

223Workflows are available in the CLI, the Desktop app, the IDE extensions, [non-interactive mode](/en/headless) with `claude -p`, and the [Agent SDK](/en/agent-sdk/overview). The same disable settings apply on every surface.

224

225To turn workflows off for yourself:

226

227* Toggle Dynamic workflows off in `/config`. Persists across sessions.

228* Set `"disableWorkflows": true` in `~/.claude/settings.json`. Persists across sessions.

229* Set `CLAUDE_CODE_DISABLE_WORKFLOWS=1`. Read at startup, so it applies wherever you set it.

230

231To turn workflows off for your whole organization, set `"disableWorkflows": true` in [managed settings](/en/server-managed-settings), or use the toggle on the [Claude Code admin settings](https://claude.ai/admin-settings/claude-code) page.

232

233When workflows are disabled, the bundled workflow commands are unavailable, the `workflow` keyword no longer triggers a run, and `ultracode` is removed from the `/effort` menu.

234

235## Related resources

236

237* [Run agents in parallel](/en/agents): compare subagents, agent view, agent teams, and workflows

238* [Create custom subagents](/en/sub-agents): the worker primitive workflows orchestrate

239* [Manage costs](/en/costs): how multi-agent runs count toward usage limits

Documentation 2026-05-28 06:37 UTC to 2026-05-29 06:38 UTC