claude-code-20261021T203701Z / documentation capture

agent-sdk/python Changed · +8 / -1 lines

from line 2575

25752575 "subagent_type": str | None, # The type of specialized agent to use

25762576 "model": "sonnet" | "opus" | "haiku" | "fable" | None, # Model override for this agent

2578 "run_in_background": bool | None, # Agents run in the background by default; set to False to run synchronously

2578 "run_in_background": bool | None, # Default when omitted: your main agent's call runs the new agent in the background, and a subagent's call waits for it

25792579 "name": str | None, # Name for the spawned agent

25802580 "team_name": str | None, # Deprecated; ignored

from line 2584

25842584```

25852585

25862586Launches a new agent to handle complex, multi-step tasks autonomously.

2587

2588When Claude leaves `run_in_background` out of an `Agent` call, by default your main agent doesn't wait for the new agent and a subagent waits:

2589

2590* **From your main agent**: the new agent runs in the background, and the result has `status: "async_launched"`. To make your main agent wait for the new agent instead, see [Choose whether Claude waits for subagents](/docs/en/agent-sdk/subagents#choose-whether-claude-waits-for-subagents).

2591* **From one of your subagents**: the calling subagent [waits for the new agent](/docs/en/sub-agents#let-subagents-spawn-their-own-subagents). The new agent runs in the background instead when its definition sets [`background`](#agentdefinition) to `True`, or when you [turn fork mode off](/docs/en/sub-agents#turn-fork-mode-on-or-off) by setting `CLAUDE_CODE_FORK_SUBAGENT` to `0`.

2592

2593Before Python SDK v0.2.169, agents that your subagents started also ran in the background by default. That release is the first to bundle Claude Code v2.1.302 or later.

25872594

25882595**Output (status: `"completed"`):**

25892596

common-workflows Changed · +5 / -0 lines

from line 375

375375

376376To stop `@` references from including file contents and directory listings in your message, set [`CLAUDE_CODE_DISABLE_FILE_MENTIONS=1`](/docs/en/env-vars#variables) in your shell or user settings. Claude then receives the paths you referenced with a note to read them using its file tools. The variable requires Claude Code v2.1.299 or later, and Claude Code ignores it in project and local settings.

377377

378Your [`PreToolUse` hooks](/docs/en/hooks#pretooluse) don't run when Claude Code includes a file you reference with `@`, because it makes no tool call. If you rely on those hooks to control what Claude reads, block specific paths or stop `@` references from including files:

379

380* **Block specific paths**: add a [`Read` deny rule](/docs/en/permissions#read-and-edit) for them. Claude Code doesn't include a file that the rule matches.

381* **Stop `@` references from including files**: set `CLAUDE_CODE_DISABLE_FILE_MENTIONS=1`, which stops `@` file and directory references in your messages from including content, even for paths your hooks don't check. Your matching hooks then run before Claude opens a referenced path with a tool such as `Read`.

382

378383***

379384

380385### Run Claude on a schedule

desktop-scheduled-tasks Changed · +20 / -10 lines

### Find a run's session

from line 24

2424| Access to local files | No (fresh clone) | Yes | Yes |

27| Customizable schedule | Via `/schedule` in the CLI | Yes | Yes |

27| Customizable schedule | Yes | Yes | Yes |

2929

3030> [!TIP]

3131>

from line 57

5757

5858**5. Turn on Only on this computer**

5959

60Skip past the **Trigger** card for now and expand **Advanced settings** below it. On the **General** tab, turn on **Only on this computer**. With it on, the task runs on your machine in a local folder, and the **Trigger** card offers the presets listed in [Schedule options](#schedule-options).

60Skip past the **Trigger** card for now and expand **Advanced settings** below it. On the **General** tab, turn on **Only on this computer**. With it on, the task runs on your machine in a local folder.

6161

6262If the switch is unavailable, clear the repository or the GitHub event or API trigger, because those make the task a [cloud scheduled task](/docs/en/routines).

6363

from line 77

7777

7878Click **Create**. If you haven't trusted the folder yet, Desktop asks you to trust it at this point. The task's detail page opens.

7979

80On the detail page, click the pencil icon to open the [**Edit** form](#manage-scheduled-tasks). There you can change the **Description** that Desktop filled in from your instructions, select **Worktree**, or switch the schedule to **Manual**.

80On the detail page, click the pencil icon to open the [**Edit** form](#manage-scheduled-tasks). There you can change the **Description** that Desktop filled in from your instructions, select **Worktree**, or switch the schedule to **Manual** or **Custom**.

8181

8282You can also create a task by describing what you want in any session. For example, "set up a daily code review that runs every morning at 9am" creates a recurring task. A request like "remind me at 3pm tomorrow to check the deploy" creates a one-time task that disables itself after it fires.

8383

from line 91

9191* **Description**: enter a description. **Create** stays unavailable until you do.

9292* **The instructions box**: enter what Claude should do when the task runs. Select the permission mode and model from the menus in the box.

9393* **Working folder**: select the folder the task runs in. **Create** stays unavailable until you select one.

94* **Trigger**: select a schedule. **Custom** takes a cron expression. For the other presets, see [Schedule options](#schedule-options).

94* **Trigger**: select a schedule. For the presets, see [Schedule options](#schedule-options).

9595

9696Click **Create**. The task's detail page opens.

9797

9898## Schedule options

9999

100When you turn on **Only on this computer** under **Advanced settings**, the **Trigger** card offers Hourly, Daily, Weekdays, and Weekly. The task's [**Edit** form](#manage-scheduled-tasks) also offers **Manual**.

100When you turn on **Only on this computer** under **Advanced settings**, the **Trigger** card offers Hourly, Daily, Weekdays, and Weekly. To get **Manual** or **Custom** for such a task, open its [**Edit** form](#manage-scheduled-tasks) after you create it. That form and the [dialog with **Only on this computer** at the top](#dialog-with-only-on-this-computer-at-the-top) offer these six options:

101101

102102* **Hourly**: runs every hour

103103* **Daily**: runs every day at the local time you pick

from line 104

104104* **Weekdays**: same as Daily but skips Saturday and Sunday

105105* **Weekly**: shows a time picker and a day picker

106106* **Manual**: no schedule, only runs when you click **Run now**. Useful for saving a prompt you trigger on demand

107* **Custom**: runs on a cron expression that you enter and that is evaluated in your local time, such as `0 9 * * *` for 9:00 AM each day. Write days of the week and months as numbers, since their names aren't accepted. Sunday is `0`, not `7`. The form rejects an expression that runs more often than once per hour.

107108

108For intervals the picker doesn't offer, such as every 15 minutes, the first of each month, or a single run at a specific future time, ask Claude in any Desktop session to set the schedule. Use plain language; for example, "schedule a task to run all the tests every 6 hours."

109You can also ask Claude in any Desktop session to set the schedule. Claude isn't held to the once-per-hour limit and can set a single run at a future time. For example, ask "run the test suite every 30 minutes" or "next Monday at 9am, summarize the pull requests merged since Friday."

109110

110111## How scheduled tasks run

111112

from line 118

117118>

118119> For tasks that need to run even when your computer is off, or that should trigger on an API call or GitHub event, create a [cloud scheduled task](/docs/en/routines) instead.

119120

120When a local task fires, a new session appears under a **Scheduled** section in the sidebar. Open it to see what Claude did, review changes, or respond to permission prompts. Claude can edit files, run commands, create commits, and open pull requests, the same as in a session you start yourself.

121### Find a run's session

121122

123To open the session a run started, go to the task's [detail page](#manage-scheduled-tasks) and click that run's row in the **History** list.

124

125The sidebar's session list can show a **Scheduled** group as well, with one row per task. To open the session of a task's latest run, click the task's row in that group. To show the group, [check which layout you have](/docs/en/desktop#check-which-layout-you-have):

126

127* **Current layout**: open the [**Group and sort** menu](/docs/en/desktop#organize-and-find-sessions), select **Show**, then select **Scheduled**. The group starts collapsed, so click its heading to expand it. **Show** lists **Scheduled** when at least one of your tasks is **Active**, the **Status** a task's detail page shows. If it isn't listed, use the **History** list, which works whether or not the group shows.

128* **Earlier layout**: the group is in the session list with nothing to turn on

129

130In a run's session, whichever way you reached it, you can see what Claude did, review changes, and respond to permission prompts. Claude can edit files, run commands, create commits, and open pull requests, the same as in a session you start yourself.

131

122132## Missed runs

123133

124134When the app starts or your computer wakes, Desktop checks whether each task missed any runs in the last seven days. If it did, Desktop starts exactly one catch-up run for the most recently missed time and discards anything older. A daily task that missed six days runs once on wake. Desktop shows a notification when a catch-up run starts.

from line 137

127137

128138## Permissions for scheduled tasks

129139

130Each task has its own permission mode, which you set when creating or editing the task. Allow rules from `~/.claude/settings.json` also apply to scheduled task sessions. If a task runs in [Manual mode](/docs/en/desktop#choose-a-permission-mode) and needs to run a tool it doesn't have permission for, the run stalls until you approve it. The session stays open in the sidebar so you can answer later.

140Each task has its own permission mode, which you set when creating or editing the task. Allow rules from `~/.claude/settings.json` also apply to scheduled task sessions. If a task runs in [Manual mode](/docs/en/desktop#choose-a-permission-mode) and needs to run a tool it doesn't have permission for, the run stalls until you approve it. To approve it, [find the run's session](#find-a-runs-session) and answer the permission prompt there.

131141

132142To avoid stalls, click **Run now** after creating a task, watch for permission prompts, and select "always allow" for each one. Future runs of that task auto-approve the same tools without prompting. You can review and revoke these approvals from the task's detail page.

133143

from line 152

142152* **Edit**: change the instructions, schedule, folder, or other settings

143153* **Review history**: see every past run, including skipped runs. Hover a skipped entry to see why: your computer was asleep, the previous run was still in progress, or other scheduled tasks were already running. Click **Show more** to load older entries.

144154* **Review allowed permissions**: see and revoke saved tool approvals for this task from the **Always allowed** panel

145* **Delete**: remove the task and archive all sessions it created. An **Also delete files on disk** checkbox appears in the confirmation dialog; check it to also remove the task's `SKILL.md` file and associated data from `~/.claude/scheduled-tasks/`.

155* **Delete**: remove the task. The sessions the task created are [archived](/docs/en/desktop#organize-and-find-sessions), not deleted. The folder holding the task's `SKILL.md` file stays on disk at `~/.claude/scheduled-tasks/<task-name>/`, or at `scheduled-tasks/<task-name>/` under [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars) if you set that variable. To remove that folder, delete it yourself.

146156

147157You can also list, create, edit, and pause tasks by asking Claude in any Desktop session. For example, "pause my dependency-audit task" or "show me my scheduled tasks." To delete a task, use the **Delete** button on its detail page.

148158

interactive-mode Changed · +15 / -0 lines

### Cancel a question in vim mode ### Background a session with messages queued

from line 258

258258

259259Block-wise visual mode with `Ctrl+V` is not supported.

260260

261### Cancel a question in vim mode

262

263When you're typing your own answer in the `Other` row of a [question Claude asks](/docs/en/tools-reference#askuserquestion-tool-behavior), press `Esc` twice to cancel the question.

264

265To cancel with a single key press instead, [bind another key to cancel the question](/docs/en/keybindings#cancel-a-question-with-one-key-press).

266

261267## Command history

262268

263269Claude Code keeps a history of the prompts you type, and Up-arrow recall reaches prompts from past sessions of the same project:

from line 394

388394* [`/model`](/docs/en/model-config#setting-your-model): once you confirm the [cache warning](/docs/en/prompt-caching#switching-models), if Claude Code shows one, Claude Code applies your change to the next request it makes in that turn

389395* [`/effort`](/docs/en/model-config#adjust-effort-level): once you confirm the [cache warning](/docs/en/prompt-caching#changing-effort-level), if Claude Code shows one, Claude Code applies your change to the next request it makes in that turn

390396* [`/fast`](/docs/en/fast-mode#toggle-fast-mode): Claude Code keeps the fast mode setting that was active when the turn started, so your speed change applies from your next turn. If your current model doesn't support fast mode, turning it on also [switches your model](/docs/en/prompt-caching#turning-on-fast-mode), and Claude Code uses the new model from its next request in that turn

397

398### Background a session with messages queued

399

400When the session moves to the background after you [press `←`](/docs/en/agent-view#switch-sessions-without-leaving-the-terminal), the messages you had queued move with it. Claude reads them there in the order you sent them.

401

402Commands and `!` shell commands can't move, and neither can some messages, such as one with an [IDE selection](/docs/en/vs-code#the-built-in-ide-mcp-server) attached. If you press `←` while one of them is queued, the session stays in the foreground and a notice that begins `Cannot open agents` appears. To background the session, get the entry out of the queue and then press `←` again:

403

404* **Commands and `!` shell commands**: wait for them to run at the end of the turn, or [take them back](#take-back-what-you-queued) and clear the input box. While anything else is queued, you can't take `!` shell commands back, so wait for them to run.

405* **Messages that can't move**: wait until Claude has read them

391406

392407### Take back what you queued

393408

keybindings Changed · +21 / -0 lines

### Cancel a question with one key press

from line 685

685685

686686In the `Other` row of a question Claude asks, Escape doesn't cancel the question right away in vim mode. Except in [screen reader mode](/docs/en/accessibility), the row starts in INSERT mode each time you focus it. When you press Escape in the `Other` row, the row switches to NORMAL mode or drops a half-typed vim command, and the question stays open. Press Escape again in NORMAL mode to cancel the question.

687687

688### Cancel a question with one key press

689

690To cancel a question with one key press in vim mode, bind another key to `select:cancel` in the `Select` context. You can cancel this way from the `Other` row of a question where you select one option. In [screen reader mode](/docs/en/accessibility) or in a question where you can select several options, the bound key doesn't cancel, so cancel with Escape instead.

691

692Pick a key that you press with Ctrl or Alt. A bare letter or digit [goes to the `Other` row](#text-fields) instead and doesn't reach your bindings. For example, to bind `Ctrl+Q`, add this to `~/.claude/keybindings.json`:

693

694```json theme={null}

695{

696 "bindings": [

697 {

698 "context": "Select",

699 "bindings": {

700 "ctrl+q": "select:cancel"

701 }

702 }

703 ]

704}

705```

706

707After you save the file, press `Ctrl+Q` in the `Other` row of a question where you select one option. The question closes whether the row is in INSERT or NORMAL mode.

708

688709## Validation

689710

690711Claude Code validates your keybindings and writes a warning to the debug log for:

memory Changed · +7 / -0 lines

from line 204

204204

205205Rules without a `paths` field are loaded unconditionally and apply to all files. A path-scoped rule loads when Claude uses the Read, Write, or Edit tool on a matching file. It also loads when Claude views a matching file with a Bash command that [counts as a read](/docs/en/tools-reference#edit-tool-behavior), such as `cat` or `head` on a single file. Matching also works when Claude reaches a file through a symlinked path to the project directory, for example in a symlinked checkout.

206206

207Each pattern is relative to the rule's base directory:

208

209* **Project rules**: the directory that contains the rule's `.claude` folder

210* **[User-level rules](#user-level-rules)**: the session's [primary working directory](/docs/en/permissions#working-directories)

211

212To have path-scoped rules load for files in a sibling git worktree, start Claude Code in that worktree or [move the session there with `/cd`](/docs/en/permissions#move-the-session-to-another-directory).

213

207214Use glob patterns in the `paths` field to match files by extension, directory, or any combination:

208215

209216| Pattern | Matches |

permission-modes Changed · +4 / -0 lines

### `claude agents` shows the bypass permissions warning that interactive sessions skip

from line 699

699699

700700Add `"skipDangerousModePermissionPrompt": true` to `~/.claude/settings.json`, then start a new background session.

701701

702### `claude agents` shows the bypass permissions warning that interactive sessions skip

703

704If [`claude agents`](/docs/en/agent-view#dispatch-defaults) shows the [bypass permissions warning](#bypass-permissions-acceptance) although your interactive sessions skip it, check whether `skipDangerousModePermissionPrompt` is set in `.claude/settings.local.json` or a `--settings` file. Interactive sessions count the key there as your acceptance of the warning, and `claude agents` doesn't. Whether or not you find it there, accept the warning to add the key to `~/.claude/settings.json`, where `claude agents` looks for it.

705

702706## Protected paths

703707

704708Writes to a small set of paths are never auto-approved, except in `bypassPermissions` mode and in interactive terminal sessions in plan mode with [bypass permissions](#skip-all-checks-with-bypasspermissions-mode) available. This prevents accidental corruption of repository state and Claude's own configuration.

routines Changed · +4 / -6 lines

from line 114

114114

115115Click **Create**. The dialog closes and the new task's detail page opens. The task runs the next time one of its triggers matches. To start a run immediately, click **Run now** on the detail page.

116116

117Each run creates a new session alongside your other sessions, where you can see what Claude did, review changes, and create a pull request.

117To see what a run did, click it in the **History** list on the detail page. The run [opens as a full session](#view-and-interact-with-runs), a new one for each run, where you can see what Claude did, review changes, and create a pull request.

118118

119119#### Dialog with Repositories and Environment in the main view

120120

from line 145

145145

146146A schedule trigger runs the task on a recurring cadence, or once at a specific future time. In the task's creation or edit dialog on the web, pick a preset frequency such as hourly, daily, or weekly:

147147

148* **Time zone**: times are entered in your local zone and converted automatically, so the task runs at that wall-clock time regardless of where the cloud infrastructure is located.

149148* **Runs on the hour**: if you schedule a run exactly on the hour, such as 9:00, it can start several minutes late. To start close to the scheduled time, pick a few minutes past the hour, for example 9:07.

150* **Custom intervals**: for a custom interval such as every two hours, pick the closest preset in the dialog, then run `/schedule update` in the CLI to set a specific cron expression. The minimum interval is one hour; expressions that run more frequently are rejected.

149* **Custom intervals**: for a cadence the presets lack, create the task and select **Custom** in its [edit dialog](#edit-and-control-scheduled-tasks). Then enter a cron expression, such as `0 */2 * * *` for every two hours. To set one from the CLI, run [`/schedule update`](#manage-scheduled-tasks-from-the-cli). Expressions that run more often than once per hour are rejected.

150* **Time zone**: when you pick a preset frequency, enter the time in your local time zone.

151151

152152#### Schedule a one-off run

153153

from line 157

157157* Open a cleanup PR after a rollout finishes

158158* Start follow-up work after an upstream change ships

159159

160After the task runs, it turns itself off and the web UI marks it as **Completed**. To run it again, open the task's edit dialog on the web, which offers **One-time** for a one-off task, and set a new time.

160After the task runs, it turns itself off and the web UI marks it as **Completed**. To run it again, open the task's [edit dialog](#edit-and-control-scheduled-tasks) on the web and select **One-time** or **Once**, whichever label your dialog shows. Then set a new date and time in your local time zone and save.

161161

162162Create a one-off run from the CLI by describing the time in natural language. Claude resolves the phrase against the current time and confirms the absolute timestamp before saving.

163163

from line 168

168168```text theme={null}

169169/schedule in 2 weeks, open a cleanup PR that removes the feature flag

170170```

171

172The same local-to-UTC conversion as recurring schedules applies to one-off timestamps.

173171

174172One-off runs count against the same hourly limit as other scheduled runs. See [Usage and limits](#usage-and-limits) for details.

175173

skills Changed · +3 / -2 lines

from line 395

395395| `agent` | No | Which subagent type to use when `context: fork` is set. |

396396| `background` | No | Only applies with `context: fork`. Set to `false` to wait for the forked subagent's result in the turn that invoked the skill, instead of [running it in the background](#run-skills-in-a-subagent). Default: `true`. Requires Claude Code v2.1.218 or later. |

397397| `hooks` | No | Hooks that Claude Code registers when the skill is invoked and keeps running for the rest of the session. See [Hooks in skills and agents](/docs/en/hooks#hooks-in-skills-and-agents) for the configuration format and the `once` option. |

398| `paths` | No | Glob patterns that limit when this skill is activated. Accepts a comma-separated string or a YAML list. When set, Claude loads the skill automatically only when working with files matching the patterns. Uses the same format as [path-specific rules](/docs/en/memory#path-specific-rules). |

398| `paths` | No | Glob patterns that limit when this skill is activated. Accepts a comma-separated string or a YAML list. When set, Claude loads the skill automatically only when working with files matching the patterns. Patterns are relative to Claude's current working directory, and files outside that directory don't match. Uses the same glob format as [path-specific rules](/docs/en/memory#path-specific-rules). |

399399| `shell` | No | Shell to use for `` !`command` `` and ` ```! ` blocks in this skill. Accepts `bash` (default) or `powershell`. Setting `powershell` runs inline shell commands via PowerShell when the [PowerShell tool](/en/tools-reference#powershell-tool) is enabled: it's on by default on Windows without Git Bash, on by default with Git Bash for claude.ai and Console accounts, and needs `CLAUDE_CODE_USE_POWERSHELL_TOOL=1` in Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry sessions and on macOS, Linux, and WSL. Set it to `0` to turn the tool off. |

400400| `metadata` | No | Free-form YAML map for your own key-value data, such as entitlement or catalog fields, read by your own tooling from `SKILL.md`. Claude Code doesn't act on its contents, and drops a value that isn't a map. Don't reuse frontmatter field names such as `paths` as keys. |

401401| `license` | No | License covering the skill. Part of the [Agent Skills](https://agentskills.io) spec; see [Using skill frontmatter outside Claude Code](#using-skill-frontmatter-outside-claude-code). Claude Code accepts the field but doesn't act on it. |

from line 752

752752Which commands get the carveout depends on the shell:

753753

754754* Default `bash` shell: the commands listed under [Output limits](/docs/en/tools-reference#output-limits)

755* `shell: powershell`, when the PowerShell tool is enabled: a [different set](/docs/en/tools-reference#shell-selection-in-settings-hooks-and-skills) that includes `grep` and `git diff` but not `find` or `diff`

755* `shell: powershell`, when the PowerShell tool is enabled: a [different set](/docs/en/tools-reference#exit-code-1-from-searches-and-git-diff-in-powershell) that includes `grep` and `git diff` but not `find` or `diff`

756756

757757With the default `bash` shell, append `|| true` to any other command you expect to exit non-zero. A check script that exits 1 when it finds problems is one example.

758758

from line 1174

117411743. Try rephrasing your request to match the description more closely

117511754. Invoke it directly with `/skill-name` if the skill is user-invocable

117611765. If `/skill-name` isn't recognized either, check whether Claude Code [refused the skill's name](#characters-a-skill-name-cant-hold)

11776. If the skill sets `paths`, check that the files Claude reads, edits, or writes are inside Claude's current working directory. The skill doesn't activate for files outside it, such as those in a sibling git worktree, even one you added with `/add-dir`. To have the skill activate for those files, start Claude Code in that worktree or [move the session there with `/cd`](/docs/en/permissions#move-the-session-to-another-directory).

11771178

11781179If the frontmatter YAML is malformed, Claude Code loads the skill body with empty metadata, so `/skill-name` still works but Claude can't match against your `description`. Run with `--debug` to see the parse error.

11791180

sub-agents Changed · +8 / -1 lines

##### MCP server names that contain a double underscore

from line 485

485485

486486A `disallowedTools` entry with a specifier, such as `Bash(git push *)`, still removes the whole tool from the subagent, not only the matching commands. To keep Bash and block specific commands, add a [Bash deny rule](/docs/en/permissions#bash) such as `Bash(git push *)` to `permissions.deny` in your settings. The rule applies to the main conversation and to subagents.

487487

488##### MCP server names that contain a double underscore

489

490If a subagent gets none of the tools from an MCP server whose name contains `__`, such as `reports__v2`, check the subagent's `mcp__` entries:

491

492* **In `tools`**: write `mcp__` followed by the [server's whole name](/docs/en/permissions#mcp) and `__*`, as in `mcp__reports__v2__*`. Without the trailing `__*`, `mcp__reports__v2` matches none of that server's tools.

493* **In `disallowedTools`**: look for `mcp__reports` or `mcp__reports__*`, the entries that withhold a server named `reports`. With either entry, the subagent loses every `reports__v2` tool as well, because those tool names also begin with `mcp__reports__`. To withhold only the `reports` server's tools, list them one by one instead, such as `mcp__reports__run_query`.

494

488495#### Restrict which subagents can be spawned

489496

490497When an agent runs as the main thread with `claude --agent`, it can spawn subagents using the Agent tool. To restrict which subagent types it can spawn, use `Agent(agent_type)` syntax in the `tools` field.

from line 958

951958

952959### Subagent names

953960

954Claude can give a subagent a name by passing a `name` parameter on the Agent tool call, and may do so on its own, without asking you first. The name makes the subagent addressable: Claude can [message or resume it by name](#resume-subagents) after it finishes.

961If you start a session with [agent teams](/docs/en/agent-teams#enable-agent-teams) enabled, Claude can give a subagent a name by passing a `name` parameter on the Agent tool call. It may do so on its own, without asking you first. The name makes the subagent addressable: Claude can [message or resume it by name](#resume-subagents) after it finishes.

955962

956963In an interactive session with [agent teams](/docs/en/agent-teams) enabled, a subagent that Claude spawns from the main conversation with a `name` launches as a teammate instead, unless the call is a [fork](#fork-the-current-conversation) or passes `isolation` on the call itself. An `isolation` value in the subagent's frontmatter doesn't prevent it, and the teammate then runs in the main session's working directory. See [How Claude starts agent teams](/docs/en/agent-teams#how-claude-starts-agent-teams).

957964

tools-reference Changed · +7 / -2 lines

### Exit code 1 from searches and `git diff` in PowerShell

from line 472

472472

473473PowerShell commands also receive the variables hooks persist through `CLAUDE_ENV_FILE`, under the conditions in [Persisted variables in PowerShell commands](/docs/en/hooks#persisted-variables-in-powershell-commands). Requires Claude Code v2.1.296 or later.

474474

475Exit code 1 from `grep`, `rg`, `egrep`, `fgrep`, `findstr`, and `git grep` means no matches. Exit code 1 from `git diff` means differences exist. Neither result is reported to Claude as a command failure. For `robocopy`, exit codes 0 through 7 are informational results, such as files copied or extra files detected. Exit codes of 8 or higher count as failures.

475### Exit code 1 from searches and `git diff` in PowerShell

476476

477If a `grep` or `rg` search that matches nothing shows `Error: Exit code 1` when Claude runs it in the PowerShell tool, the search didn't fail. You don't need to do anything. The error can appear when the search is part of a longer command. For example, when `rg` exits with code 1, `rg foo | Out-Null` shows the error and `rg foo` doesn't.

478

479The PowerShell tool can count exit code 1 as a normal result from `grep`, `rg`, `egrep`, `fgrep`, `findstr`, `git grep`, and `git diff`. The searches use exit code 1 to report no matches. From `git diff`, exit code 1 means the files differ. A command that shows the error when Claude runs it [counts as failed](/docs/en/skills#when-an-injected-command-fails) in a skill with `shell: powershell`.

480

477481### Windows encoding and exit codes

478482

479483* Redirection with `>` and `>>` writes UTF-8 files on PowerShell 5.1

from line 484

480484* Claude Code encodes text piped to a native command's standard input as UTF-8

481485* Claude Code captures error output without ANSI escape sequences

482486* A command whose child process waits on standard input receives end-of-file instead of hanging

483* Exit code 1 from `where.exe` means no match, and from `fc.exe` and `diff.exe` it means the files differ, so when the command produces output, Claude Code treats that exit code as a valid negative answer rather than a command error. Claude Code still reports a silenced form, such as `where.exe /Q` or a redirect to `$null`, as a failure on exit code 1

487* If `where.exe` finds no match, or `fc.exe` or `diff.exe` finds that the files differ, the result can show `Error: Exit code 1` though the command didn't fail. You don't need to do anything.

488* If a `robocopy` exit code from 1 through 7 shows as an error, the copy didn't fail and you don't need to do anything. `robocopy` exits with code 0 through 7 to report a result, such as files copied, and with 8 or higher when it fails.

484489

485490### Preview limitations

486491

agent-teams Changed · +1 / -1 lines

from line 30

3030| | Subagents | Agent teams |

3131| :- | :- | :- |

3232| **Context** | Own context window; results return to the caller | Own context window; fully independent |

33| **Communication** | Return a result to the caller. Subagents that Claude named when it spawned them can also [message each other](/docs/en/sub-agents#what-loads-at-startup) | Teammates message each other directly |

33| **Communication** | Return a result to the caller. Subagents that Claude [named](/docs/en/sub-agents#subagent-names) when it spawned them can also [message each other](/docs/en/sub-agents#what-loads-at-startup) | Teammates message each other directly |

3434| **Coordination** | Main agent manages all work | Self-coordination through messages, plus a shared task list for [agents that have the Task tools](/docs/en/tools-reference#task-tool-availability) |

3535| **Best for** | Focused tasks where only the result matters | Complex work requiring discussion and collaboration |

3636| **Token cost** | Lower: results summarized back to main context | Higher: each teammate is a separate Claude instance |

claude-tag Changed · +1 / -1 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

Nothing in the body moved in this read. What changed is above.

features-overview Changed · +1 / -1 lines

from line 144

144144* **Subagents** are workers Claude spawns, each returning a summary to the conversation that spawned it

145145* **[Dynamic workflows](/docs/en/workflows)** are scripts Claude writes that run many subagents in the background and return one result

146146

147**Use a subagent** when you need a quick, focused worker: research a question, verify a claim, review a file. The subagent does the work and returns a summary, so your main conversation stays clean. Subagents that Claude named when it spawned them can also [message each other](/docs/en/sub-agents#what-loads-at-startup).

147**Use a subagent** when you need a quick, focused worker: research a question, verify a claim, review a file. The subagent does the work and returns a summary, so your main conversation stays clean. Subagents that Claude [named](/docs/en/sub-agents#subagent-names) when it spawned them can also [message each other](/docs/en/sub-agents#what-loads-at-startup).

148148

149149**Use a dynamic workflow** when a job [outgrows a handful of subagents](/docs/en/workflows#when-to-use-a-workflow), or when you want the findings cross-checked before you see them, such as a codebase-wide audit, a large migration, or a plan drafted from several angles. To start one, [ask for a workflow in your prompt](/docs/en/workflows#ask-for-a-workflow-in-your-prompt).

150150

fullscreen Changed · +1 / -0 lines

from line 28

2828* Your [permission mode](/docs/en/permission-modes) and [effort level](/docs/en/model-config#adjust-effort-level)

2929* The model you last picked with [`/model`](/docs/en/model-config#setting-your-model)

3030* Rules you passed with [`--allowed-tools` or `--disallowed-tools`](/docs/en/cli-reference#cli-flags), and your `--agent`, `--agents`, `--append-system-prompt`, and `--system-prompt-snapshot` flags

31* A `--chrome` or `--no-chrome` flag you launched with, so [Chrome integration](/docs/en/chrome) stays on or off as you chose for this session

3132

3233Claude Code declines to relaunch if the session has a restriction it can't pass to the restarted process. Restrictions it can't pass include:

3334

large-codebases Changed · +1 / -1 lines

from line 345

345345

346346A different subdirectory holds different skills the same way: `packages/web/.claude/skills/component-patterns/` describes the frontend's component conventions instead of testing. When Claude works on a file in `packages/api/`, it loads the api-testing skill. When it works in `packages/web/`, it loads component-patterns instead. Neither directory's skills load during the other's tasks.

347347

348You can also scope a skill by file pattern instead of by placement. The [`paths` frontmatter field](/docs/en/skills#frontmatter-reference) takes glob patterns, and Claude loads the skill automatically only when it works with matching files. Use this for a skill that lives in the repository root's `.claude/skills/` but applies only to certain files wherever they appear, such as a database-migration skill scoped to `**/migrations/**`.

348You can also scope a skill by file pattern instead of by placement. The [`paths` frontmatter field](/docs/en/skills#frontmatter-reference) takes glob patterns, and Claude loads the skill automatically only when it works with matching files. Use this for a skill that lives in the repository root's `.claude/skills/` but applies only to certain files, such as a database-migration skill scoped to `**/migrations/**`.

349349

350350For more on creating and organizing skills, see [Skills](/docs/en/skills).

351351

scheduled-tasks Changed · +2 / -2 lines

from line 26

2626| Access to local files | No (fresh clone) | Yes | Yes |

29| Customizable schedule | Via `/schedule` in the CLI | Yes | Yes |

29| Customizable schedule | Yes | Yes | Yes |

3131

3232> [!TIP]

3333>

One read of Claude Code CLIclaude-code-20261021T203701Z

What this read moved