Capture
One read of Claude Code CLI
16 pages moved out of 186 read.
commands Changed · +3 / -3 lines
from line 119
| `/resume [session]` | Resume a conversation by ID or name, or open the session picker. [Background sessions](/docs/en/agent-view) appear in the picker marked with `bg`; one that is still running can't be resumed here, so attach to it from `claude agents` or stop it there first. Alias: `/continue` | | `/review [low\|medium\|high\|xhigh\|max\|ultra] [--fix] [--comment] [pr#\|branch\|path]` | Alias of [`/code-review`](/docs/en/code-review#review-a-diff-locally): reviews the current diff, or a PR number, branch, or path you pass, such as `/review 1234`, and takes the same effort levels and flags. With no level given, the review reuses the last `low` through `max` level you typed; see [Review a diff locally](/docs/en/code-review#review-a-diff-locally) for the exact rules. For a deep cloud review, use [`/code-review ultra`](/docs/en/ultrareview). Before v2.1.223, `/review` was a separate command that ran a single-pass, read-only review of a GitHub pull request by number, listing open PRs to pick from when run with no argument; from v2.1.186 through v2.1.201, it ran the same multi-agent engine as `/code-review medium` | | `/rewind` | Rewind the conversation and/or code to a previous point, or summarize from a selected message. See [checkpointing](/docs/en/checkpointing). Aliases: `/checkpoint`, `/undo` | -| `/run` | **[Skill](/docs/en/skills#bundled-skills).** Launch and drive your project's app to see a change working, not only passing tests. See [Run and verify your app](/docs/en/skills#run-and-verify-your-app). Requires Claude Code v2.1.145 or later | -| `/run-skill-generator` | **[Skill](/docs/en/skills#bundled-skills).** Teach `/run` and `/verify` how to build, launch, and drive your project's app from a clean environment by writing a per-project [skill](/docs/en/skills#run-and-verify-your-app). Requires Claude Code v2.1.145 or later | +| `/run` | **[Skill](/docs/en/skills#bundled-skills).** Launch and drive your project's app to see a change working, not only passing tests. See [Run and verify your app](/docs/en/skills#run-and-verify-your-app) | +| `/run-skill-generator` | **[Skill](/docs/en/skills#bundled-skills).** Teach `/run` and `/verify` how to build, launch, and drive your project's app from a clean environment by writing a per-project [skill](/docs/en/skills#run-and-verify-your-app) | | `/sandbox` | Toggle [sandbox mode](/docs/en/sandboxing). Available on supported platforms only | | `/schedule [description]` | Create, update, list, or run [routines](/docs/en/routines), which execute in the cloud. Claude walks you through the setup conversationally. You can also ask about a [routine's recent runs](/docs/en/routines#manage-routines-from-the-cli). Alias: `/routines` | | `/scroll-speed` | Adjust mouse wheel [scroll speed](/docs/en/fullscreen#mouse-wheel-scrolling) interactively, with a ruler you can scroll while the dialog is open to preview the change. Available in [fullscreen rendering](/docs/en/fullscreen) only and not in the JetBrains IDE terminal |
from line 146
| `/upgrade` | Open the upgrade page in your browser to switch to a higher plan tier. When the browser fails to open, the command shows a sign-in prompt without printing the URL | | `/usage` | Show session cost, plan usage limits, and activity stats. On a Pro, Max, Team, or Enterprise plan, includes a breakdown of usage by skill, subagent, plugin, and MCP server. See the [cost tracking guide](/docs/en/costs#using-the-%2Fusage-command) for details. `/cost` and `/stats` are aliases | | `/usage-credits` | Configure usage credits, or request them from your admin, when you hit a limit. Opens your [usage-credits billing settings](/docs/en/costs#add-usage-credits-to-your-subscription) in the browser, except that Team and Enterprise members without billing access instead send a usage-credits request to their admin from the CLI, after confirming in a dialog that the request notifies their admins. When no browser can open the billing page, for example over SSH, the command prints the URL to visit instead; this requires Claude Code v2.1.205 or later, and earlier versions showed nothing in that case. Previously `/extra-usage` | -| `/verify` | **[Skill](/docs/en/skills#bundled-skills).** Confirm a code change does what it should by building your project's app, running it, and observing the result, rather than relying on tests or type checks. See [Run and verify your app](/docs/en/skills#run-and-verify-your-app). Requires Claude Code v2.1.145 or later | +| `/verify` | **[Skill](/docs/en/skills#bundled-skills).** Confirm a code change does what it should by building your project's app, running it, and observing the result, rather than relying on tests or type checks. See [Run and verify your app](/docs/en/skills#run-and-verify-your-app) | | `/vim` | Removed in v2.1.92. To toggle between Vim and Normal editing modes, use `/config` → Editor mode | | `/voice [hold\|tap\|off]` | Toggle [voice dictation](/docs/en/voice-dictation), or enable it in a specific mode. Requires a Claude.ai account | | `/web-setup` | Connect your GitHub account to [Claude Code on the web](/docs/en/web-quickstart#connect-from-your-terminal) using your local `gh` CLI credentials. `/schedule` prompts for this automatically if GitHub isn't connected |
cross-session-messaging Changed · +30 / -1 lines
### Get a notice when another session goes idle #### Ask for a notice #### What each session shows #### Limits
from line 18
* **Hand over a finding**: when one session discovers a breaking change or makes a decision, Claude summarizes it for the session working on the affected area, instead of you re-explaining it there. * **Coordinate parallel worktrees**: when sessions work the same repository in separate [worktrees](/docs/en/worktrees), Claude can tell the other sessions what landed. -* **Get status from long-running work**: have a migration or test run report back to the session you're watching, or ask it yourself from there. +* **Get status from long-running work**: have a migration or test run report back to the session you're watching, or ask it yourself from there. If that session is on this machine, Claude can also [ask it for one notice when it next goes idle or exits](#get-a-notice-when-another-session-goes-idle). * **Message across machines**: reach one of your sessions on another machine or on the web. Use messaging between independent sessions that you start and steer yourself. Claude Code has a dedicated feature for each of the other ways to run or reach multiple sessions, so use the one built for what you're doing instead:
from line 68
Once delivered, the message counts toward [usage](/docs/en/costs) like a prompt you type, and the receiving Claude can reply to the sender the same way, except in the [one-way cross-machine case](#message-sessions-on-other-machines). Permission boundaries stay per-session. Claude is instructed never to ask another session for an action that was denied or blocked in its own session, or that its own permission settings would block, and to route that work back to you instead. On the receiving side, the [receiving session's own permission prompts and rules still apply](#how-a-session-treats-an-incoming-message) to anything the message asks for. + +### Get a notice when another session goes idle + +Claude can ask one of your sessions on this machine to send back one notice when that session next goes idle or exits. Idle here means the session finished a turn with nothing queued. Use it when you're waiting on a long task in another session and want to hear when it's done instead of checking. Requires Claude Code v2.1.236 or later in both sessions. + +#### Ask for a notice + +Tell Claude what you're waiting on. This prompt asks for a notice from the migration session: + +```text wrap theme={null} +Tell me when the migration session finishes what it's working on +``` + +Claude subscribes with the `SendMessage` tool's `notify_when_idle` input, either attached to a message it's sending anyway or on its own. On its own, Claude Code subscribes without starting a turn or spending tokens in the watched session, and sends the notice right away if that session is already idle. Attached to a message, Claude Code delivers the message first and sends the notice later. + +#### What each session shows + +The watched session shows a line saying another process asked to be told when the session is next idle. The asking session shows the notice as a line naming the watched session. The line can include the time that session's turn finished and a one-line status from that turn. If the asking session is idle, Claude Code starts a new turn with the notice. + +#### Limits + +The notice is one-shot: Claude Code sends it once from the watched session, and neither session polls the other. If no notice arrives within 12 hours, Claude Code drops the subscription and tells Claude, so it doesn't keep waiting. + +Each side's [inbound controls](#control-inbound-messages) apply to a notice like a message: + +* **`refuse` on either side**: nothing arrives. The watched session drops the request without recording or answering it, so the subscription expires unanswered after 12 hours, and an asking session with `refuse` never subscribes. +* **`hold` on either side**: the notice arrives with less. The watched session leaves the one-line status out, and the asking session shows the notice in your transcript without delivering it to Claude. + +Only the Claude in your main conversation can subscribe, and only to your sessions on this machine. When a subagent or an agent team teammate sets `notify_when_idle`, Claude Code makes no subscription and tells it so. When Claude asks for a notice from any other agent, such as a teammate, a subagent, or a session beyond this machine, Claude Code refuses the whole call, including any message attached to it, and reports the refusal to Claude so it can resend the message without the request. ### See which sessions Claude can reach
goal Changed · +11 / -6 lines
from line 15
Three approaches keep the current session running between prompts. Pick based on what should start the next turn: -| Approach | Next turn starts when | Stops when | -| :------------------------------------------------------------------ | :------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `/goal` | The previous turn finishes | A model confirms the condition is met or judges it impossible, or a turn fails on [an error you have to fix](#errors-you-have-to-fix-clear-the-goal), or you run [`/goal clear`](#clear-a-goal) | -| [`/loop`](/docs/en/scheduled-tasks#run-a-prompt-repeatedly-with-%2Floop) | A time interval elapses | You stop it, or Claude decides the work is done | -| [Stop hook](/docs/en/hooks-guide#prompt-based-hooks) | The previous turn finishes | Your own script or prompt decides | +| Approach | Next turn starts when | Stops when | +| :------------------------------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `/goal` | The previous turn finishes, or an [idle check-in](#background-work-defers-evaluation) comes due while background work keeps the goal waiting | A model confirms the condition is met or judges it impossible, or a turn fails on [an error you have to fix](#errors-you-have-to-fix-clear-the-goal), or you run [`/goal clear`](#clear-a-goal) | +| [`/loop`](/docs/en/scheduled-tasks#run-a-prompt-repeatedly-with-%2Floop) | A time interval elapses | You stop it, or Claude decides the work is done | +| [Stop hook](/docs/en/hooks-guide#prompt-based-hooks) | The previous turn finishes | Your own script or prompt decides | `/goal` and a Stop hook both fire after every turn. `/goal` is a session-scoped shortcut: you type a condition and it's active for the current session only. A Stop hook lives in your settings file, applies to every session in its scope, and can run a script for deterministic checks or a prompt for model-evaluated ones.
from line 134
If a subagent or a background shell command is still running when a turn ends, Claude Code skips the evaluation for that turn. It evaluates at the end of the next turn that finishes with no background work running. When the background work finishes, Claude Code delivers the result to Claude as a new turn, so you don't have to prompt. -When a turn ends and background work has kept the goal waiting for 30 minutes or more, Claude Code asks Claude to check on that work. Claude Code lists the running tasks and asks Claude to read their output, keep waiting if they're progressing, and fix or stop any that are stuck. After each further 30 minutes of waiting, Claude Code asks again at the next turn end. To change the interval, set [`CLAUDE_CODE_GOAL_CHECKIN_MINUTES`](/docs/en/env-vars); set it to `0` to turn check-ins off. Check-ins require Claude Code v2.1.234 or later. +Once background work has kept the goal waiting for 30 minutes, a check-in is due. In the check-in, Claude Code lists the running tasks and asks Claude to read their output, keep waiting if they're progressing, and fix or stop any that are stuck. After each check-in, the 30 minutes start again. Claude Code delivers a due check-in, the first one included, in one of two ways: + +* **When a turn ends**: Claude Code delivers the check-in at the end of the next turn that finishes with the work still running. In a non-interactive session, such as one started with `-p`, this is the only way Claude Code delivers check-ins. +* **While the session is idle**: in an interactive session, Claude Code also starts a turn on its own to deliver the check-in instead of waiting for your next prompt. After the first check-in, Claude Code waits twice as long before each later idle check-in, up to four times the interval: with the default, 1 hour after the first check-in, then every 2 hours. If the background work has stopped without reporting a result, Claude Code asks Claude to continue toward the goal. Idle check-ins require Claude Code v2.1.236 or later. + +To change the intervals, set [`CLAUDE_CODE_GOAL_CHECKIN_MINUTES`](/docs/en/env-vars). Claude Code uses your value in place of the 30-minute interval and scales the idle intervals with it. Set it to `0` to turn check-ins off. Check-ins require Claude Code v2.1.234 or later. ### Evaluation model and cost
hooks Changed · +10 / -3 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.
from line 578
Use these placeholders to reference hook scripts relative to the project or plugin root, regardless of the working directory when the hook runs: -* `${CLAUDE_PROJECT_DIR}`: the project root. Claude Code also sets this variable in the environment of [stdio MCP servers](/docs/en/mcp#option-3-add-a-local-stdio-server) and plugin LSP servers. +* `${CLAUDE_PROJECT_DIR}`: the project root where the session started. Claude Code also sets this variable in the environment of [stdio MCP servers](/docs/en/mcp#option-3-add-a-local-stdio-server) and plugin LSP servers. * `${CLAUDE_PLUGIN_ROOT}`: the plugin's installation directory, for scripts bundled with a [plugin](/docs/en/plugins). Changes on each plugin update. * `${CLAUDE_PLUGIN_DATA}`: the plugin's [persistent data directory](/docs/en/plugins-reference#persistent-data-directory), for dependencies and state that should survive plugin updates. +<Note> + **Worktrees are different.** If Claude enters a [worktree](/docs/en/worktrees) during the session, Claude Code keeps `${CLAUDE_PROJECT_DIR}` where it was and passes the worktree path to your hooks a different way: + + * **`${CLAUDE_PROJECT_DIR}` stays put**: it still points at the project root where the session started, so a command such as `${CLAUDE_PROJECT_DIR}/.claude/hooks/check-style.sh` still runs the script in the main checkout. + * **`cwd` follows Claude**: the `cwd` field in the hook's [input JSON](#common-input-fields) is the worktree root after Claude enters a worktree, and the new directory after Claude runs `cd`. Read it when a hook needs to know which directory Claude is working in. +</Note> + Prefer [exec form](#exec-form-and-shell-form) for any hook that references a path placeholder. In shell form, wrap each placeholder in double quotes. <Tabs>
from line 2252
In addition to the [common input fields](#common-input-fields), SubagentStop hooks receive `stop_hook_active`, `agent_id`, `agent_type`, `agent_transcript_path`, and `last_assistant_message`. The `agent_type` field is the value used for matcher filtering. The `transcript_path` is the main session's transcript, while `agent_transcript_path` is the subagent's own transcript stored in a nested `subagents/` folder. The `last_assistant_message` field contains the text content of the subagent's final response, so hooks can access it without parsing the transcript file. -SubagentStop hooks also receive the `background_tasks` and `session_crons` arrays described under [Stop input](#stop-input), available in Claude Code v2.1.145 or later. Both arrays are scoped to the parent session, not the subagent. +SubagentStop hooks also receive the `background_tasks` and `session_crons` arrays described under [Stop input](#stop-input). Both arrays are scoped to the parent session, not the subagent. ```json theme={null} {
from line 2400
The `last_assistant_message` field contains the text content of Claude's final response, so hooks can access it without parsing the transcript file. For hooks that act on the just-completed turn, such as read-aloud or notification hooks, use this field rather than reading `transcript_path`: the transcript file isn't guaranteed to include the final message at Stop time on all versions. -The `background_tasks` and `session_crons` arrays, available in Claude Code v2.1.145 or later, let hooks distinguish "session is done" from "session is paused waiting for background work to wake it back up". Both arrays are present when the task registry is reachable and are empty when nothing is in flight or scheduled. +The `background_tasks` and `session_crons` arrays let hooks distinguish "session is done" from "session is paused waiting for background work to wake it back up". Both arrays are present when the task registry is reachable and are empty when nothing is in flight or scheduled. Each entry in `background_tasks` describes one in-flight task and uses these fields:
from line 3216
What happens on `ok: false` depends on the event: * `Stop` and `SubagentStop`: the reason is fed back to Claude as its next instruction and the turn continues, unless the response also sets `impossible: true`, in which case Claude Code allows the stop and the turn ends -* `PreToolUse`: the tool call is denied; by default the turn ends and the deny reason appears in the chat as a warning line. Set `continueOnBlock: true` to instead return the reason to Claude as the tool error so it can adjust and continue, equivalent to a command hook's `permissionDecision: "deny"`. Before v2.1.210, the deny reason was returned to Claude as the tool error and the turn continued -* `PostToolUse`: by default the turn ends and the reason appears in the chat as a warning line. Set `continueOnBlock: true` to feed the reason back to Claude and continue the turn instead -* `PostToolBatch`, `UserPromptSubmit`, and `UserPromptExpansion`: the turn ends and the reason appears as a warning line. These events end the turn on `decision: "block"` regardless of `continue` -* `PostToolUseFailure` and `TaskCreated`: the reason is returned to Claude as a tool error and the tur +* `PreToolUse`: the tool call is denied; by default the turn ends and the deny reason appears in the chat as a warning line. Set `continueOnBlock: true` to instead return the reason to Claude as the tool error so it can adjus
permissions Changed · +12 / -5 lines
from line 539
### When your local settings file needs trust -`.claude/settings.local.json` is normally your own file, so its allow rules and additional directories apply without the trust step. Claude Code treats the file as repository-supplied instead, and holds its rules until you trust the folder, when the file is tracked in git or `.claude` is a symlink. +`.claude/settings.local.json` is normally your own file, so Claude Code applies its allow rules and additional directories without the trust step. When the file is tracked in git, or `.claude` is a symlink, Claude Code treats it as repository-supplied instead and holds its rules until you trust the folder. -Claude Code runs git to tell the two apart, and it runs git in a folder only after you accept a trust dialog for that folder or for a parent directory whose trust extends to it, or in a `-p` or SDK session, which counts as accepted. Until then it holds the file's rules like project settings, with one exception: in your own configuration home, meaning your home directory or any directory whose `.claude` subdirectory you've set as [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars), the file applies right away without running git. Once the check has run, an untracked file, or one in a directory that isn't inside a git repository, applies even though you haven't trusted that exact folder. +Claude Code runs git to tell the two apart, and it runs git only once you've trusted the folder: you accepted the trust dialog for it or for a parent directory whose trust extends to it, or you're in a `-p` or SDK session, which counts as accepted. Until then, where you started Claude Code decides what happens to the file's rules: -Versions 2.1.196 through 2.1.199 held the file's rules in your configuration home and outside git repositories too, and printed the [`this workspace has not been trusted`](/docs/en/errors#workspace-has-not-been-trusted) warning there. Before v2.1.207, an untracked file applied before you accepted the dialog. +* **In your configuration home:** Claude Code applies that folder's `.claude/settings.local.json` right away without running git. Your configuration home is your home directory, or a directory whose `.claude` subdirectory you've set as [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars#variables). If that `CLAUDE_CONFIG_DIR` directory sits inside a git repository and Claude Code [keeps your local settings at the repository root](/docs/en/settings#available-scopes) instead, it holds the rules like anywhere else. +* **Anywhere else:** Claude Code holds the file's rules like project settings. Once the check has run, Claude Code applies the rules of an untracked file, or of a file in a directory outside any git repository, even though you haven't trusted that exact folder. + +<Note> + The configuration-home exception skips only the trust step. `~/.claude/settings.local.json` is still [local scope](/docs/en/settings#available-scopes), so Claude Code reads it only in sessions you start in your home directory itself, not in every project. To apply permission rules across all your projects, add them to your user settings instead: `~/.claude/settings.json`, or `$CLAUDE_CONFIG_DIR/settings.json` when `CLAUDE_CONFIG_DIR` is set. +</Note> + +On versions 2.1.196 through 2.1.199, Claude Code held the file's rules in your configuration home and outside git repositories too, and printed the [`this workspace has not been trusted`](/docs/en/errors#workspace-has-not-been-trusted) warning there. Before v2.1.207, Claude Code applied an untracked file's rules before you accepted the dialog. ### What runs before you trust a folder
plugin-marketplaces Changed · +28 / -6 lines
##### Pick the directory to name ##### Check a plugin whose skill is its root `SKILL.md` ##### Check files behind symlinks ##### Read the validation results
from line 1226
To find skill, agent, and command files whose frontmatter doesn't parse, run `claude plugin validate` and name the directory that holds them. Claude Code doesn't look outside the directory you name. Every run except one against a plugin that has a `plugin.json` requires Claude Code v2.1.233 or later. -Pick the directory by what you want to check: +##### Pick the directory to name +Claude Code checks different files depending on which directory you name. Find what you want to check in the first column, and run that row's command: + | To check | Run | Claude Code checks | | :------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | A plugin that has a `plugin.json` | `claude plugin validate ./plugins/my-plugin` | `plugin.json`, `hooks/hooks.json`, and the `skills`, `agents`, and `commands` directories at the plugin root |
from line 1238
| A project's three directories at once | `claude plugin validate .claude`, or the project root when it has no `.claude-plugin/` manifest | `.claude/skills`, `.claude/agents`, and `.claude/commands` | | Your user-level directories | `claude plugin validate ~/.claude` | `~/.claude/skills`, `~/.claude/agents`, and `~/.claude/commands` | -A plugin run also warns about a `CLAUDE.md` at the plugin root. For paths you set through the [component path fields](/docs/en/plugins-reference#component-path-fields) in `plugin.json`, it checks that each path exists but doesn't read the files there, and it doesn't check a `SKILL.md` at the plugin root. To check a plugin whose skill is its root `SKILL.md`, run the command twice when the plugin sits in a directory named `skills`: name that `skills` directory to check the root `SKILL.md`, and name the plugin directory to check the rest. When the plugin sits under another name, such as `plugins/`, only the second run is available, and no run checks its root `SKILL.md`. +##### Check a plugin whose skill is its root `SKILL.md` -Claude Code doesn't follow symlinks inside the directory you name. What it does depends on where the link is: +When you run `claude plugin validate` against a plugin directory, Claude Code doesn't check a `SKILL.md` at the plugin root. When the plugin sits in a directory named `skills`, run the command twice: +* Name that `skills` directory to check the plugin's root `SKILL.md`. +* Name the plugin directory to check the rest. + +When the plugin sits under another name, such as `plugins/`, the `skills`-directory run isn't available, and no run checks its root `SKILL.md`. + +##### Check files behind symlinks + +When you run `claude plugin validate`, Claude Code doesn't follow symlinks inside the directory you name. What it does depends on where the link is: + * **A linked `skills`, `agents`, or `commands` directory under the plugin or `.claude` root**: Claude Code warns that nothing in it was read. -* **A linked entry inside a `skills`, `agents`, or `commands` directory**: Claude Code skips it and warns, per directory, how many entries it skipped that a session would load. A plugin whose `skills` directory [links to a sibling plugin's skills](/docs/en/plugins-reference#share-files-within-a-marketplace-with-symlinks) passes with warnings; to check the linked skills, name the sibling plugin's directory. The same applies to a [symlinked skill entry](/docs/en/skills#where-skills-live) in `~/.claude/skills` or `.claude/skills`, which a session does follow; to check it, name a directory called `skills` that holds the real folder. +* **A linked entry inside a `skills`, `agents`, or `commands` directory**: Claude Code skips it and warns, per directory, how many entries it skipped that a session would load. * **The `skills`, `agents`, or `commands` directory you name is itself a symlink, or its parent `.claude` directory is**: Claude Code reports an error and checks nothing in it. Name the real directory instead. -A clean run ends with `Validation passed`. `No manifest found in directory` means Claude Code found no `plugin.json` or `marketplace.json` there, and no skill, agent, or command file in the directories it probes under it. Name the `skills`, `agents`, or `commands` directory that holds your files instead. +In two skills cases, the run passes with warnings. To check the linked files, run again and name a directory that holds them directly: +* **A plugin whose `skills` directory [links to a sibling plugin's skills](/docs/en/plugins-reference#share-files-within-a-marketplace-with-symlinks)**: name the sibling plugin's directory. +* **A [symlinked skill entry](/docs/en/skills#where-skills-live) in `~/.claude/skills` or `.claude/skills`**: Claude Code follows the entry in a session. To check it, name a directory called `skills` that holds the real folder. + +##### Read the validation results + +A clean run ends with `Validation passed`. + +`No manifest found in directory` means Claude Code found no `plugin.json` or `marketplace.json` there, and no skill, agent, or command file in the directories it probes under it. Name the `skills`, `agents`, or `commands` directory that holds your files instead. + Two of the errors Claude Code reports from these runs, with the fix for each: * `YAML frontmatter failed to parse: ...`: fix the YAML in the frontmatter block of the skill, agent, or command file. Until you do, a session reads no frontmatter fields from the file * `Invalid JSON syntax: ...` on `hooks/hooks.json`: fix the JSON syntax. Until you do, a session loads the plugin without the hooks in that file. Claude Code reports this error only in a plugin run + +In a plugin run, Claude Code also warns about a `CLAUDE.md` at the plugin root. For paths you set through the [component path fields](/docs/en/plugins-reference#component-path-fields) in `plugin.json`, Claude Code checks that each path exists but doesn't read the files there. ### Plugin installation failures
sandboxing Changed · +5 / -4 lines
from line 179
You can also deny write or read access using `sandbox.filesystem.denyWrite` and `sandbox.filesystem.denyRead`, and re-allow specific paths within a denied region using `sandbox.filesystem.allowRead`. When read rules overlap, the more specific path wins: -| Example rules | Result | -| :------------------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -| `"denyRead": ["~/"]` with `"allowRead": ["~/projects"]` | `~/projects` is readable and the rest of the home directory stays blocked. The narrower allow re-opens that part of the denied region | -| `"allowRead": ["~/"]` with `"denyRead": ["~/.env"]` | `~/.env` stays blocked and the rest of the home directory is readable. An exact deny holds inside a wider allow, so a broad allow can't silently re-expose a secret | +| Example rules | Result | +| :------------------------------------------------------ | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `"denyRead": ["~/"]` with `"allowRead": ["~/projects"]` | `~/projects` is readable and the rest of the home directory stays blocked. The narrower allow re-opens that part of the denied region | +| `"allowRead": ["~/"]` with `"denyRead": ["~/.env"]` | `~/.env` stays blocked and the rest of the home directory is readable. The deny holds inside a wider allow, so a broad allow can't silently re-expose a secret | +| `"allowRead": ["~/"]` with `"denyRead": ["~/**/.env"]` | Every `.env` under the home directory stays blocked and the rest is readable. A [wildcard deny](/docs/en/settings#sandbox-path-prefixes) holds inside a wider allow the same way an exact path does | The example below blocks reading from the entire home directory while still allowing reads from the current project. Place it in your project's `.claude/settings.json`, because the relative path `.` resolves to the project root only when the configuration lives in project settings:
sub-agents Changed · +5 / -1 lines
##### Check an `agents` directory before a session
from line 307
* **A `name` but no `description`**: Claude Code skips the file and writes the reason to the debug log. * **YAML that doesn't parse**: Claude Code reads no fields from the file, skips it, and writes the parse error to the debug log. -To see the debug log, run Claude Code with `--debug`. A [plugin subagent](/docs/en/plugins-reference#agents) whose frontmatter has no `name` or doesn't parse still loads, under its filename. +To see the debug log, run Claude Code with `--debug`. + +A [plugin subagent](/docs/en/plugins-reference#agents) whose frontmatter has no `name` or doesn't parse still loads, under its filename. + +##### Check an `agents` directory before a session To find files in an `agents` directory whose frontmatter doesn't parse, run `claude plugin validate` against the directory, for example `.claude/agents` or `~/.claude/agents`. Claude Code checks only [the directory you name](/docs/en/plugin-marketplaces#validate-a-plugin-or-a-directory-without-a-manifest), and doesn't flag a file whose frontmatter parses but has no `name`. Requires Claude Code v2.1.233 or later.
tools-reference Changed · +46 / -46 lines
from line 12
On Pro, Max, and Team plans, Claude Code starts sessions in [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), where a classifier decides most of these prompts instead of you. The `Permission required` column shows whether the tool prompts in [Manual mode](/docs/en/permission-modes) for paths inside the working directory. File-access tools marked No, including `Read`, `Grep`, and `Glob`, still prompt for paths outside the [working directory and additional directories](/docs/en/permissions#working-directories). `Bash` is marked Yes but runs a built-in set of [read-only commands](/docs/en/permissions#read-only-commands) without prompting. </Info> -| Tool | Description | Permission required | -| :--------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | :------------------ | -| `Agent` | Spawns a [subagent](/docs/en/sub-agents) with its own context window to handle a task. With [agent teams](/docs/en/agent-teams) enabled, a call that carries a `name` can launch a [teammate](/docs/en/agent-teams#how-claude-starts-agent-teams) instead. See [Agent tool behavior](#agent-tool-behavior) | No | -| `Artifact` | Publishes an HTML or Markdown file as an [artifact](/docs/en/artifacts): a private, interactive page on claude.ai. You can share it with a public link, or inside your organization on Team and Enterprise plans, where public sharing requires an Owner to [enable it](/docs/en/artifacts#control-public-sharing). Requires a Pro, Max, Team, or Enterprise plan and `/login` authentication; see [Availability](/docs/en/artifacts#availability) | Yes | -| `AskUserQuestion` | Asks multiple-choice questions to gather requirements or clarify ambiguity. Questions stay open until you answer them by default. See [AskUserQuestion tool behavior](#askuserquestion-tool-behavior) | No | -| `Bash` | Executes shell commands in your environment. See [Bash tool behavior](#bash-tool-behavior) | Yes | -| `CronCreate` | Schedules a recurring or one-shot prompt within the current session. Tasks are session-scoped and restored on `--resume` or `--continue` if unexpired. See [scheduled tasks](/docs/en/scheduled-tasks) | No | -| `CronDelete` | Cancels a scheduled task by ID | No | -| `CronList` | Lists all scheduled tasks in the session | No | -| `Edit` | Makes targeted edits to specific files. See [Edit tool behavior](#edit-tool-behavior) | Yes | -| `EndConversation` | Ends the session, in rare cases of sustained abusive input or when you ask Claude to demonstrate the tool. Requires Claude Code v2.1.213 or later. See [EndConversation tool behavior](#endconversation-tool-behavior) | No | -| `EnterPlanMode` | Switches to plan mode to design an approach before coding | No | -| `EnterWorktree` | Creates an isolated [git worktree](/docs/en/worktrees) and switches into it. Pass a `path` to switch into an existing worktree instead of creating a new one. On first entry the target may be a worktree of the current repository or, in a multi-repo workspace, of a repository nested inside it. Before v2.1.203, a nested repository's worktree was rejected. A `path` outside `.claude/worktrees/` prompts for your approval before entering, since it moves the session's working directory and write access to that location. New-worktree creation and paths under `.claude/worktrees/` don't prompt. Before v2.1.206, Claude entered paths outside `.claude/worktrees/` without a prompt. From within a worktree session, or from a subagent with a pinned working directory such as [`isolation: worktree`](/docs/en/sub-agents#supported-frontmatter-fields), only the `path` form is available and the target must be under `.claude/worktrees/` of the session's repository | Yes | -| `ExitPlanMode` | Presents a plan for approval and exits plan mode | Yes | -| `ExitWorktree` | Exits a worktree session and returns to the original directory. Not available to subagents that already run in their own working directory, such as with [`isolation: worktree`](/docs/en/sub-agents#supported-frontmatter-fields) | No | -| `Glob` | Finds files based on pattern matching. See [Glob tool behavior](#glob-tool-behavior) | No | -| `Grep` | Searches for patterns in file contents. See [Grep tool behavior](#grep-tool-behavior) | No | -| `ListAgents` | Lists the agents Claude can message with `SendMessage`, apart from [agent team](/docs/en/agent-teams) teammates, which Claude reaches through the team's roster: subagents in the session, your other local Claude Code sessions, and, while this session is connected to [Remote Control](/docs/en/remote-control), your [Claude Code on the web](/docs/en/claude-code-on-the-web) sessions and your Remote Control sessions on other machines. Backs the `/list-agents` command. See [cross-session messaging](/docs/en/cross-session-messaging). Requires Claude Code v2.1.224 or later, and appears only in sessions where [cross-session messaging is enabled](/docs/en/cross-session-messaging#availability) | No | -| `ListMcpResourcesTool` | Lists resources exposed by connected [MCP servers](/docs/en/mcp) | No | -| `LSP` | Code intelligence via language servers: jump to definitions, find references, report type errors and warnings. See [LSP tool behavior](#lsp-tool-behavior) | No | -| `Monitor` | Runs a command in the background and feeds each output line back to Claude, so it can react to log entries, file changes, or polled status mid-conversation. Can also open a WebSocket and treat each incoming message as an event. See [Monitor tool](#monitor-tool) | Yes | -| `NotebookEdit` | Modifies Jupyter notebook cells. See [NotebookEdit tool behavior](#notebookedit-tool-behavior) | Yes | -| `PowerShell` | Executes PowerShell commands natively. See [PowerShell tool](#powershell-tool) for availability | Yes | -| `PushNotification` | Sends a desktop notification, and a phone push when [Remote Control](/docs/en/remote-control) is connected, so a long-running task or [scheduled task](/docs/en/scheduled-tasks) can reach you when you step away. Push delivery runs through Anthropic-hosted infrastructure, which is not accessible from Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry | No | -| `Read` | Reads the contents of files. See [Read tool behavior](#read-tool-behavior) | No | -| `ReadMcpResourceTool` | Reads a specific MCP resource by URI | No | -| `RemoteTrigger` | Creates, updates, runs, and lists [Routines](/docs/en/routines) on claude.ai. Backs the `/schedule` command. The [`RemoteTrigger` input reference](/docs/en/agent-sdk/typescript#remotetrigger) documents every action and the organization policies that remove the tool. Routines live on claude.ai and require a Pro, Max, Team, or Enterprise plan, so this tool is not accessible from Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry. Also unavailable when you turn off [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) | No | -| `ReportFindings` | Reports code-review findings as a structured list, with a file, summary, and failure scenario per finding, so Claude Code can render them instead of printing them as text. Claude calls it when active code-review instructions tell it to. Requires Claude Code v2.1.196 or later. As of v2.1.199, a finding can also carry an optional `category` slug, such as `correctness` or `test-coverage`, shown next to the file location in the rendered list | No | -| `ScheduleWakeup` | Reschedules the next iteration of a [self-paced `/loop`](/docs/en/scheduled-tasks#let-claude-choose-the-interval). Claude calls this at the end of each iteration to pick when the next one runs, between one minute and one hour out; you don't call it directly. To end the loop instead, Claude calls it with `stop: true`, which cancels the pending wakeup. The `stop` field requires Claude Code v2.1.202 or later. The pending wakeup appears in `session_crons` in [Stop hook input](/docs/en/hooks#stop-input). Not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry, where a `/loop` prompt with no interval runs on a fixed schedule instead. The same happens when you turn off [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) | No | -| `SendMessage` | Sends a message to another agent: an [agent team](/docs/en/agent-teams) teammate, a [subagent it resumes](/docs/en/sub-agents#resume-subagents) by agent ID or name, or one of your other Claude Code sessions, on this machine or beyond it. Messaging other sessions requires Claude Code v2.1.224 or later; [cross-session messaging](/docs/en/cross-session-messaging) covers which sessions Claude can reach and each case's requirements. A receiver never treats a message from another agent as your consent or approval. Claude can include an optional `summary` input, typically 5-10 words, that Claude Code shows as a one-line preview. When Claude omits it on a [plain-text message](/docs/en/cross-session-messaging#limitations), Claude Code uses the first line of the message as the summary. Claude Code truncates a summary longer than 200 characters with an ellipsis | No | -| `SendUserFile` | Sends files from the session to you with an optional caption, so a generated report, diagram, screenshot, or built artifact reaches your device instead of only being mentioned in the transcript. As of v2.1.196, the optional `display` input controls presentation: `render` opens the file inline in the client, `attach` shows a download card only, and when unset the client decides by file type. Available when a [Remote Control](/docs/en/remote-control) client is connected or the session runs in a managed cloud environment such as [Claude Code on the web](/docs/en/claude-code-on-the-web). Delivery runs through Anthropic-hosted infrastructure, so the tool is not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry | No | -| `ShareOnboardingGuide` | Uploads `ONBOARDING.md` and returns a share link teammates can open in Claude Code. Called from `/team-onboarding` after the guide is written. Available to claude.ai subscribers on Pro, Max, Team, and Enterprise plans | Yes | -| `Skill` | Executes a [skill](/docs/en/skills#control-who-invokes-a-skill) within the main conversation | Yes | -| `TaskCreate` | Creates a new task in the task list. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless you opt in | No | -| `TaskGet` | Retrieves full details for a specific task. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless you opt in | No | -| `TaskList` | Lists all tasks with their current status. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless you opt in | No | -| `TaskOutput` | Retrieves output from a background task. Deprecated in favor of `Read` on the task's output file path. When no task matches the ID, the error lists the running background agents by ID and description. Before v2.1.203, the error named only the missing ID | No | -| `TaskStop` | Stops a running background task by ID. It also accepts an [agent-team teammate](/docs/en/agent-teams) or a named background agent by agent ID or name. Before v2.1.198, it accepted only a background task ID. When no task matches the ID, the error lists the running background agents by ID and description, including agents that another agent spawned. Before v2.1.203, the error listed running teammates and named agents but not background agents another agent spawned, so those couldn't be identified or stopped from the main conversation | No | -| `TaskUpdate` | Updates task status, dependencies, details, or deletes tasks. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless you opt in | No | -| `TodoWrite` | Manages the session task checklist. Disabled by default in favor of `TaskCreate`, `TaskGet`, `TaskList`, and `TaskUpdate`. Set `CLAUDE_CODE_ENABLE_TASKS=0` to re-enable it in [sessions that have the task-tracking tools](#task-tool-availability) | No | -| `ToolSearch` | Searches for and loads deferred tools when [tool search](/docs/en/mcp#scale-with-mcp-tool-search) is enabled | No | -| `WaitForMcpServers` | Waits for one or more [MCP servers](/docs/en/mcp) that are still connecting in the background, so a request can use their tools without restarting the session. Claude calls it when a needed server isn't connected yet. Only appears when [tool search](/docs/en/mcp#scale-with-mcp-tool-search) is disabled, since `ToolSearch` handles the wait when it's enabled | No | -| `WebFetch` | Fetches content from a specified URL. See [WebFetch tool behavior](#webfetch-tool-behavior) | Yes | -| `WebSearch` | Performs web searches. See [WebSearch tool behavior](#websearch-tool-behavior) | Yes | -| `Workflow` | Runs a [dynamic workflow](/docs/en/workflows): a script that orchestrates many subagents in the background and returns one consolidated result | Yes | -| `Write` | Creates or overwrites files. See [Write tool behavior](#write-tool-behavior) | Yes | +| Tool | Description | Permission required | +| :--------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------ | +| `Agent` | Spawns a [subagent](/docs/en/sub-agents) with its own context window to handle a task. With [agent teams](/docs/en/agent-teams) enabled, a call that carries a `name` can launch a [teammate](/docs/en/agent-teams#how-claude-starts-agent-teams) instead. See [Agent tool behavior](#agent-tool-behavior) | No | +| `Artifact` | Publishes an HTML or Markdown file as an [artifact](/docs/en/artifacts): a private, interactive page on claude.ai. You can share it with a public link, or inside your organization on Team and Enterprise plans, where public sharing requires an Owner to [enable it](/docs/en/artifacts#control-public-sharing). Requires a Pro, Max, Team, or Enterprise plan and `/login` authentication; see [Availability](/docs/en/artifacts#availability) | Yes | +| `AskUserQuestion` | Asks multiple-choice questions to gather requirements or clarify ambiguity. Questions stay open until you answer them by default. See [AskUserQuestion tool behavior](#askuserquestion-tool-behavior) | No | +| `Bash` | Executes shell commands in your environment. See [Bash tool behavior](#bash-tool-behavior) | Yes | +| `CronCreate` | Schedules a recurring or one-shot prompt within the current session. Tasks are session-scoped and restored on `--resume` or `--continue` if unexpired. See [scheduled tasks](/docs/en/scheduled-tasks) | No | +| `CronDelete` | Cancels a scheduled task by ID | No | +| `CronList` | Lists all scheduled tasks in the session | No | +| `Edit` | Makes targeted edits to specific files. See [Edit tool behavior](#edit-tool-behavior) | Yes | +| `EndConversation` | Ends the session, in rare cases of sustained abusive input or when you ask Claude to demonstrate the tool. Requires Claude Code v2.1.213 or later. See [EndConversation tool behavior](#endconversation-tool-behavior) | No | +| `EnterPlanMode` | Switches to plan mode to design an approach before coding | No | +| `EnterWorktree` | Creates an isolated [git worktree](/docs/en/worktrees) and switches into it. Pass a `path` to switch into an existing worktree instead of creating a new one. On first entry the target may be a worktree of the current repository or, in a multi-repo workspace, of a repository nested inside it. Before v2.1.203, a nested repository's worktree was rejected. A `path` outside `.claude/worktrees/` prompts for your approval before entering, since it moves the session's working directory and write access to that location. New-worktree creation and paths under `.claude/worktrees/` don't prompt. Before v2.1.206, Claude entered paths outside `.claude/worktrees/` without a prompt. From within a worktree session, or from a subagent with a pinned working directory such as [`isolation: worktree`](/docs/en/sub-agents#supported-frontmatter-fields), only the `path` form is available and the target must be under `.claude/worktrees/` of the session's repository | Yes | +| `ExitPlanMode` | Presents a plan for approval and exits plan mode | Yes | +| `ExitWorktree` | Exits a worktree session and returns to the original directory. Not available to subagents that already run in their own working directory, such as with [`isolation: worktree`](/docs/en/sub-agents#supported-frontmatter-fields) | No | +| `Glob` | Finds files based on pattern matching. See [Glob tool behavior](#glob-tool-behavior) | No | +| `Grep` | Searches for patterns in file contents. See [Grep tool behavior](#grep-tool-behavior) | No | +| `ListAgents` | Lists the agents Claude can message with `SendMessage`, apart from [agent team](/docs/en/agent-teams) teammates, which Claude reaches through the team's roster: subagents in the session, your other local Claude Code sessions, and, while this session is connected to [Remote Control](/docs/en/remote-control), your [Claude Code on the web](/docs/en/claude-code-on-the-web) sessions and your Remote Control sessions on other machines. Backs the `/list-agents` command. See [cross-session messaging](/docs/en/cross-session-messaging). Requires Claude Code v2.1.224 or later, and appears only in sessions where [cross-session messaging is enabled](/docs/en/cross-session-messaging#availability) | No | +| `ListMcpResourcesTool` | Lists resources exposed by connected [MCP servers](/docs/en/mcp) | No | +| `LSP` | Code intelligence via language servers: jump to definitions, find references, report type errors and warnings. See [LSP tool behavior](#lsp-tool-behavior) | No | +| `Monitor` | Runs a command in the background and feeds each output line back to Claude, so it can react to log entries, file changes, or polled status mid-conversation. Can also open a WebSocket and treat each incoming message as an event. See [Monitor tool](#monitor-tool) | Yes | +| `NotebookEdit` | Modifies Jupyter notebook cells. See [NotebookEdit tool behavior](#notebookedit-tool-behavior) | Yes | +| `PowerShell` | Executes PowerShell commands natively. See [PowerShell tool](#powershell-tool) for availability | Yes | +| `PushNotification` | Sends a desktop notification, and a phone push when [Remote Control](/docs/en/remote-control) is connected, so a long-running task or [scheduled task](/docs/en/scheduled-tasks) can reach you when you step away. Push delivery runs through Anthropic-hosted infrastructure, which is not accessible from Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry | No | +| `Read` | Reads the contents of files. See [Read tool behavior](#read-tool-behavior) | No | +| `ReadMcpResourceTool` | Reads a specific MCP resource by URI | No | +| `RemoteTrigger` | Creates, updates, runs, and lists [Routines](/docs/en/routines) on claude.ai. Backs the `/schedule` command. The [`RemoteTrigger` input reference](/docs/en/agent-sdk/typescript#remotetrigger) documents every action and the organization policies that remove the tool. Routines live on claude.ai and require a Pro, Max, Team, or Enterprise plan, so this tool is not accessible from Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry. Also unavailable when you turn off [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) | No | +| `ReportFindings` | Reports code-review findings as a structured list, with a file, summary, and failure scenario per finding, so Claude Code can render them instead of printing them as text. Claude calls it when active code-review instructions tell it to. Requires Claude Code v2.1.196 or later. As of v2.1.199, a finding can also carry an optional `category` slug, such as `correctness` or `test-coverage`, shown next to the file location in the rendered list | No | +| `ScheduleWakeup` | Reschedules the next iteration of a [self-paced `/loop`](/docs/en/scheduled-tasks#let-claude-choose-the-interval). Claude calls this at the end of each iteration to pick when the next one runs, between one minute and one hour out; you don't call it directly. To end the loop instead, Claude calls it with `stop: true`, which cancels the pending wakeup. The `stop` field requires Claude Code v2.1.202 or later. The pending wakeup appears in `session_crons` in [Stop hook input](/docs/en/hooks#stop-input). Not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundry, where a `/loop` prompt with no interval runs on a fixed schedule instead. The same happens when you turn off [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) | No | +| `SendMessage` | Sends a message to another agent: an [agent team](/docs/en/agent-teams) teammate, a [subagent it resumes](/docs/en/sub-agents#resume-subagents) by agent ID or name, or one of your other Claude Code sessions, on this machine or beyond it. Messaging other sessions requires Claude Code v2.1.224 or later; [cross-session messaging](/docs/en/cross-session-messaging) covers which sessions Claude can reach and each case's requirements. A receiver never treats a message from another agent as your consent or approval. Claude can include an optional `summary` input, typically 5-10 words, that Claude Code shows as a one-line preview. When Claude omits it on a [plain-text message](/docs/en/cross-session-messaging#limitations), Claude Code uses the first line of the message as the summary. Claude Code truncates a summary longer than 200 characters with an ellipsis. With the `notify_when_idle` input, Claude can ask one of your other sessions on this machine to [send one notice when it next goes idle or exits](/docs/en/cross-session-messaging#get-a-notice-when-another-session-goes-idle). Requires Claude Code v2.1.236 or later in both sessions | No | +| `SendUserFile` | Sends files from the session to you with an optional caption, so a generated report, diagram, screenshot, or built artifact reaches your device instead of only being mentioned in the transcript. As of v2.1.196, the optional `display` input controls presentation: `render` opens the file inline in the client, `attach` shows a download card only, and when unset the client decides by file type. Available when a [Remote Control](/docs/en/remote-control) client is connected or the session runs in a managed cloud environment such as [Claude Code on the web](/docs/en/claude-code-on-the-web). Delivery runs through Anthropic-hosted infrastructure, so the tool is not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry | No | +| `ShareOnboardingGuide` | Uploads `ONBOARDING.md` and returns a share link teammates can open in Claude Code. Called from `/team-onboarding` after the guide is written. Available to claude.ai subscribers on Pro, Max, Team, and Enterprise plans | Yes | +| `Skill` | Executes a [skill](/docs/en/skills#control-who-invokes-a-skill) within the main conversation | Yes | +| `TaskCreate` | Creates a new task in the task list. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless you opt in | No | +| `TaskGet` | Retrieves full details for a specific task. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless you opt in | No | +| `TaskList` | Lists all tasks with their current status. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless you opt in | No | +| `TaskOutput` | Retrieves output from a background task. Deprecated in favor of `Read` on the task's output file path. When no task matches the ID, the error lists the running background agents by ID and description. Before v2.1.203, the error named only the missing ID | No | +| `TaskStop` | Stops a running background task by ID. It also accepts an [agent-team teammate](/docs/en/agent-teams) or a named background agent by agent ID or name. Before v2.1.198, it accepted only a background task ID. When no task matches the ID, the error lists the running background agents by ID and description, including agents that another agent spawned. Before v2.1.203, the error listed running teammates and named agents but not background agents another agent spawned, so those couldn't be identified or stopped from the main conversation | No | +| `TaskUpdate` | Updates task status, dependencies, details, or deletes tasks. Claude Code leaves it out on the models listed under [Task tool availability](#task-tool-availability) unless you opt in | No | +| `TodoWrite` | Manages the session task checklist. Disabled by default in favor of `TaskCreate`, `TaskGet`, `TaskList`, and `TaskUpdate`. Set `CLAUDE_CODE_ENABLE_TASKS=0` to re-enable it in [sessions that have the task-tracking tools](#task-tool-availability) | No | +| `ToolSearch` | Searches for and loads deferred tools when [tool search](/docs/en/mcp#scale-with-mcp-tool-search) is enabled | No | +| `WaitForMcpServers` | Waits for one or more [MCP servers](/docs/en/mcp) that are still connecting in the background, so a request can use their tools without restarting the session. Claude calls it when a needed server isn't connected yet. Only appears when [tool search](/docs/en/mcp#scale-with-mcp-tool-search) is disabled, since `ToolSearch` handles the wait when it's enabled | No | +| `WebFetch` | Fetches content from a specified URL. See [WebFetch tool behavior](#webfetch-tool-behavior) | Yes | +| `WebSearch` | Performs web searches. See [WebSearch tool behavior](#websearch-tool-behavior) | Yes | +| `Workflow` | Runs a [dynamic workflow](/docs/en/workflows): a script that orchestrates many subagents in the background and returns one consolidated result | Yes | +| `Write` | Creates or overwrites files. See [Write tool behavior](#write-tool-behavior) | Yes | ## Configure tools with permission rules and hooks
vs-code Changed · +17 / -0 lines
## Use a screen reader
from line 355
| `allowDangerouslySkipPermissions` | `false` | Adds Bypass permissions to the mode selector. Use it only in sandboxes with no internet access. | | `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. In a wrapped setup, conversations start in Manual mode unless you set `initialPermissionMode` or picked Manual, Edit automatically, or Auto in an earlier conversation, because the extension skips the settings and built-in-default steps there; see [Switch permission modes](/docs/en/permission-modes#switch-permission-modes). An "Unsupported platform" error at activation means no binary is bundled for your platform; see [which platforms have prebuilt binaries](/docs/en/troubleshoot-install#native-binary-not-found-after-npm-install). | +## Use a screen reader + +The extension's chat panel works with screen readers. You don't need to turn anything on: the extension announces conversation activity for every user, with no visual change. This is separate from the CLI's opt-in [screen reader mode](/docs/en/accessibility), which adapts the terminal interface. + +Screen reader support in the chat panel requires Claude Code v2.1.236 or later. + +During a conversation, the extension announces: + +* **Claude's replies**: the extension announces each reply once, when it's complete, and stays silent while text streams in. Your screen reader reads code blocks as a line-count summary, reads links by their label, and reads tables cell by cell; the full reply stays readable in the transcript. +* **Permission requests and questions**: the extension announces a request when its permission prompt appears, naming the tool Claude wants to use. It announces in the same way when Claude asks you a question and when Claude finishes a plan and waits for your review. +* **Status changes**: the extension announces when Claude starts working, when Claude is ready for your input, and when Claude Code starts compacting the conversation. +* **Errors and model prompts**: the extension announces errors in the conversation, and announces when the [usage-credits consent prompt](/docs/en/model-config#fable-5-and-usage-credits) or the [flagged-request prompt](/docs/en/model-config#ask-before-switching) appears. + +Each turn in the transcript starts with a visually hidden heading labeled with the prompt that started the turn, so you can jump between turns with your screen reader's heading navigation. You can also move focus to the transcript itself with `Tab`, since the extension exposes it as a labeled region, and read it at your own pace. While Claude works, your screen reader reads a text label in place of the progress spinner's animation. + +When you reopen a session or switch to another one, the extension announces nothing: restored history, pending permission prompts, and in-progress status stay silent until something new happens. + ## VS Code extension vs. Claude Code CLI Claude Code is available as both a VS Code extension (graphical panel) and a CLI (command-line interface in the terminal). Some features are only available in the CLI. If you need a CLI-only feature, run `claude` in VS Code's integrated terminal. This requires the [standalone CLI install](/docs/en/setup): the extension does not add `claude` to your PATH. See [Run CLI in VS Code](#run-cli-in-vs-code).
worktrees Changed · +7 / -0 lines
from line 38
When Claude enters a path outside the repository's `.claude/worktrees/` directory, Claude Code asks for your approval first, because the move takes the session's working directory, write access, and project configuration such as `CLAUDE.md` and settings to that location. An `EnterWorktree` [permission rule](/docs/en/permissions) or choosing "don't ask again" doesn't suppress this prompt; only `bypassPermissions` mode skips it. Before v2.1.206, Claude could enter any existing worktree path without asking. +<Note> + **Hook paths don't follow the worktree.** After Claude enters a worktree, Claude Code keeps `${CLAUDE_PROJECT_DIR}` in your [hooks](/docs/en/hooks#reference-scripts-by-path) where it was and passes the worktree path to them a different way: + + * **`${CLAUDE_PROJECT_DIR}` stays put**: it still points at the project root where the session started, so a hook command such as `${CLAUDE_PROJECT_DIR}/.claude/hooks/check-style.sh` still runs the script in the main checkout. + * **`cwd` follows Claude**: the `cwd` field in the hook's [input JSON](/docs/en/hooks#common-input-fields) is the worktree root, and it moves again when Claude runs `cd`. Read it when a hook needs the worktree path. +</Note> + ## Clean up worktrees When you exit an interactive worktree session, Claude checks the worktree for work that removal would delete: changed or untracked files, and new commits.
skills Changed · +0 / -2 lines
from line 38
| `/verify` | Build and run your app to confirm a code change does what it should, without falling back to tests or type checks | | `/run-skill-generator` | Teach `/run` and `/verify` how to build and launch your project | -All three skills require Claude Code v2.1.145 or later. Check your version with `claude --version` or the `/status` command. - `/run` and `/verify` work without setup. They infer the launch from your project type (CLI, server, TUI, browser-driven) and from what's in your README, `package.json`, or `Makefile`. That inference gets unreliable for projects that need anything beyond a standard launch: a database, an env file, a graphical session, a multi-step build. `/run-skill-generator` records the recipe instead. It gets your app running from a clean environment, captures what worked (the install commands, the env vars, the launch script), and commits it as a per-project skill at `.claude/skills/run-<name>/`. After that, `/run`, `/verify`, and any other agent in the repo follow the recorded recipe instead of rediscovering it. Run `/run-skill-generator` once per project, and again if the build or launch process changes.
settings Changed · +3 / -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.
from line 418
| `filesystem.allowWrite` | Additional paths where sandboxed commands can write. Arrays are merged across all settings scopes: user, project, and managed paths are combined, not replaced. Also merged with paths from `Edit(...)` allow permission rules. See [path prefixes](#sandbox-path-prefixes) below. | `["/tmp/build", "~/.kube"]` | | `filesystem.denyWrite` | Paths where sandboxed commands cannot write. Arrays are merged across all settings scopes. Also merged with paths from `Edit(...)` deny permission rules. | `["/etc", "/usr/local/bin"]` | | `filesystem.denyRead` | Paths where sandboxed commands cannot read. Arrays are merged across all settings scopes. Also merged with paths from `Read(...)` deny permission rules. | `["~/.aws/credentials"]` | -| `filesystem.allowRead` | Paths to re-allow reading within `denyRead` regions. An `allowRead` path re-opens reading inside a broader `denyRead` region, and an exact path in `denyRead` stays blocked inside a broader `allowRead`; see the [overlap table](/docs/en/sandboxing#configure-sandboxing) for examples. Arrays are merged across all settings scopes. Use this to create workspace-only read access patterns. | `["."]` | +| `filesystem.allowRead` | Paths to re-allow reading within `denyRead` regions. An `allowRead` path re-opens reading inside a broader `denyRead` region. Claude Code keeps an exact or wildcard `denyRead` entry blocked inside a broader `allowRead`, as the [overlap table](/docs/en/sandboxing#configure-sandboxing) shows. Arrays are merged across all settings scopes. Use this to create workspace-only read access patterns. | `["."]` | | `filesystem.allowManagedReadPathsOnly` | (Managed settings only) Only `filesystem.allowRead` paths from managed settings are respected. `denyRead` still merges from all sources. Default: false | `true` | | `filesystem.disabled` | Skip filesystem isolation while keeping network isolation: sandboxed commands get unrestricted read and write access to the host filesystem, and network egress stays confined to `network.allowedDomains`. Only honored from user, managed, or CLI `--settings` settings. Default: false. Requires Claude Code v2.1.216 or later. See [Disable filesystem isolation](/docs/en/sandboxing#disable-filesystem-isolation) for which sources can set it and what changes when isolation is off | `true` | | `credentials.files` | Credential files or directories to [protect from sandboxed commands](/docs/en/sandboxing#protect-credentials). Each entry has a `path` and a `mode`. `deny` blocks reads inside the sandbox, the same read block as `filesystem.denyRead`, and requires Claude Code v2.1.187 or later. `mask` shows sandboxed commands a sentinel copy of the file on Linux and WSL2, while the sandbox proxy substitutes the real value on outbound requests to that entry's `injectHosts`; on macOS the file is unreadable inside the sandbox instead. It requires `network.tlsTerminate` and Claude Code v2.1.221 or later. [Mask credential files](/docs/en/sandboxing#mask-credential-files) covers which settings sources are honored and when an entry falls back to `deny`. Paths use the same [prefixes](#sandbox-path-prefixes) as `filesystem.*` settings. Arrays are merged across all settings scopes. | `[{ "path": "~/.aws/credentials", "mode": "deny" }]` |
security-guidance Changed · +0 / -1 lines
from line 10
## Prerequisites -* Claude Code CLI version 2.1.144 or later * Python 3.7 or later on your `PATH`. The agentic commit review needs Python 3.10 or later, as do all model-backed reviews when Claude Code uses a third-party provider such as Amazon Bedrock or Google Cloud's Agent Platform. The plugin prefers the versioned interpreters `python3.13` through `python3.10`, then falls back to `python3`, `python`, and `py -3` * A git repository for the directory you work in. The end-of-turn and commit reviews diff against git state and skip silently outside a repository. The per-edit pattern check works anywhere
costs Changed · +1 / -0 lines
from line 291
* **Cache misses**: your first message after a break longer than the [cache lifetime](/docs/en/prompt-caching#cache-lifetime) misses the cache and reprocesses your full context. The lifetime is an hour on a subscription and drops to five minutes once you're drawing on [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans); on an API key or cloud provider, it's five minutes by default. You can keep the one-hour lifetime while drawing on usage credits by setting [`ENABLE_PROMPT_CACHING_1H=1`](/docs/en/env-vars). On Pro and Max plans, when you resume a large session after a long break, Claude Code [offers to resume from a summary](/docs/en/sessions#resume-from-a-summary) so later requests don't carry the full history * **Scheduled tasks**: a [scheduled task](/docs/en/scheduled-tasks) fires on its interval even while the session is idle, sending your full context each time * **Cross-session messages**: Claude Code delivers a [message from another of your sessions](/docs/en/cross-session-messaging) as a new turn when this session sits idle, sending your full context each time. To hold inbound messages instead of delivering them, set [`crossSessionInbound`](/docs/en/settings#available-settings) to `hold` +* **Goal check-ins**: while background work keeps an active [goal](/docs/en/goal) waiting, Claude Code [asks Claude to check on that work](/docs/en/goal#background-work-defers-evaluation) even when the session sits idle, starting a new turn that sends your full context. To turn check-ins off, set [`CLAUDE_CODE_GOAL_CHECKIN_MINUTES`](/docs/en/env-vars) to `0`. Idle check-ins require Claude Code v2.1.236 or later * **Agent teammates**: each active [teammate](#agent-team-token-costs) keeps consuming tokens until it exits * **Compaction**: `/compact` reads the conversation it summarizes, so [compacting a large context](/docs/en/prompt-caching#compacting-the-conversation) is itself a large request. When you want a fresh start instead of continuity, `/clear` costs nothing
accessibility Changed · +1 / -1 lines
from line 4
Claude Code has a screen reader mode that replaces its visual terminal interface with plain, linear text. Instead of boxes, progress animations, and in-place redraws, Claude Code prints labeled lines that a screen reader such as VoiceOver or NVDA reads in order. You can hold a full conversation, approve tool permissions, and review output end to end. -Screen reader mode is opt-in. If you use a screen magnifier, reduced motion, or a colorblind-friendly theme instead of a screen reader, set `CLAUDE_CODE_ACCESSIBILITY`, `prefersReducedMotion`, or `theme` from the [Accessibility settings](#accessibility-settings) table. +Screen reader mode is opt-in. If you use a screen magnifier, reduced motion, or a colorblind-friendly theme instead of a screen reader, set `CLAUDE_CODE_ACCESSIBILITY`, `prefersReducedMotion`, or `theme` from the [Accessibility settings](#accessibility-settings) table. Screen reader mode adapts the terminal interface only, so you don't need it in the VS Code extension's chat panel. On Claude Code v2.1.236 or later, the extension [announces conversation activity to your screen reader](/docs/en/vs-code#use-a-screen-reader) there without any setting. Screen reader mode requires Claude Code v2.1.181 or later. Earlier versions reject the `--ax-screen-reader` flag with `error: unknown option '--ax-screen-reader'`.