What this read moved
1–17 of 17claude-directory Changed · +6 / -6 lines
from line 1442
14421442
14431443The explorer covers files you author and edit. A few related files live elsewhere:
14441444
1445| File | Location | Purpose |
1446| ----------------------- | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
1447| `managed-settings.json` | System-level, varies by OS | Enterprise-enforced settings that you can't override, apart from [narrow exceptions](/docs/en/settings#security-keys-where-the-stricter-value-applies). See [where to save the file](/docs/en/managed-settings#deploy-a-managed-settings-file) and [which managed source Claude Code uses](/docs/en/managed-settings#precedence-within-the-managed-tier). |
1448| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.gitignore`. |
1449| Installed plugins | `~/.claude/plugins` | Cloned marketplaces, installed plugin versions, and per-plugin data, managed by `claude plugin` commands. For a plugin installed from a marketplace [`command` source](/docs/en/plugin-marketplaces#command-sources) in link mode, Claude Code stores links here instead of a copy, and the plugin's files stay in the directory the command prints. See [plugin caching](/docs/en/plugins-reference#plugin-caching-and-file-resolution) for how orphaned versions are cleaned up. |
1445| File | Location | Purpose |
1446| ----------------------- | -------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1447| `managed-settings.json` | System-level, varies by OS | Enterprise-enforced settings that you can't override, apart from [narrow exceptions](/docs/en/settings#security-keys-where-the-stricter-value-applies). See [where to save the file](/docs/en/managed-settings#deploy-a-managed-settings-file) and [which managed source Claude Code uses](/docs/en/managed-settings#precedence-within-the-managed-tier). |
1448| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.gitignore`. |
1449| Installed plugins | `~/.claude/plugins` | Cloned marketplaces, installed plugin versions, and per-plugin data, managed by `claude plugin` commands. For a plugin installed from a marketplace [`command` source](/docs/en/plugin-marketplaces#command-sources) in link mode, Claude Code stores links here instead of a copy, and the plugin's files stay in the directory the command prints. A `command` source requires Claude Code v2.1.229 or later. See [plugin caching](/docs/en/plugins-reference#plugin-caching-and-file-resolution) for how orphaned versions are cleaned up. |
14501450
14511451`~/.claude` also holds data Claude Code writes as you work: transcripts, prompt history, file snapshots, caches, and logs. See [application data](#application-data) below.
14521452
from line 1541
15411541* **Auto memory**: the sweep doesn't delete the memory files in a project's [auto memory](/docs/en/memory#auto-memory) directory, `projects/<project>/memory/`. Claude Code removes that directory only if it has been empty for the whole retention period. Before v2.1.228, the sweep treated folders inside the memory directory as session data and could delete old files beneath it.
15421542* **Claude Desktop and Cowork transcripts**: Claude Code keeps the transcript of a session you started or most recently continued in Claude Desktop or Cowork at any age. To give these transcripts an age limit, set [`desktopSessionCleanupPeriodDays`](/docs/en/settings-reference#desktopsessioncleanupperioddays). When [managed settings](/docs/en/managed-settings) set `cleanupPeriodDays`, Claude Code deletes these transcripts after that period instead. Requires Claude Code v2.1.248 or later; earlier versions delete them after `cleanupPeriodDays`.
15431543
1544Claude Code skips the sweep entirely in these cases:
1544Claude Code skips the age-based sweep in these cases:
15451545
15461546* **Bare mode**: when you run `claude -p` with [`--bare`](/docs/en/headless#start-faster-with-bare-mode), Claude Code doesn't run the sweep in that session.
15471547* **Paused sweep**: if Claude Code can't safely determine the retention period, it pauses the retention cleanup sweep; the [`retention_sweep` event](/docs/en/monitoring-usage#retention-sweep-event) lists each configuration that pauses it. When the cause is a settings file that can't be read or parsed, or settings errors with `cleanupPeriodDays` or `desktopSessionCleanupPeriodDays` explicitly set, Claude Code also shows a warning in `/status` until you fix the settings errors. When [managed settings](/docs/en/server-managed-settings) provide `cleanupPeriodDays`, Claude Code runs the sweep at the managed value in either case.
cloud-environments Changed · +5 / -8 lines
from line 468
468468<AccordionGroup>
469469 <Accordion title="Anthropic services">
470470 * api.anthropic.com
471 * statsig.anthropic.com
472471 * docs.claude.com
473472 * platform.claude.com
474473 * code.claude.com
from line 539
540539 * [www.java.net](http://www.java.net)
541540 * download.oracle.com
542541 * yum.oracle.com
542 * \*.r2.cloudflarestorage.com
543543 </Accordion>
544544
545545 <Accordion title="JavaScript and Node package managers">
from line 550
550550 * npmjs.org
551551 * yarnpkg.com
552552 * registry.yarnpkg.com
553 * jsr.io
554 * npm.jsr.io
553555 </Accordion>
554556
555557 <Accordion title="Python package managers">
from line 606
604606 * central.maven.org
605607 * repo1.maven.org
606608 * repo.maven.apache.org
609 * maven.google.com
607610 * jcenter.bintray.com
608611 * gradle.org
609612 * [www.gradle.org](http://www.gradle.org)
610613 * services.gradle.org
611614 * plugins.gradle.org
615 * plugins-artifacts.gradle.org
612616 * kotlinlang.org
613617 * [www.kotlinlang.org](http://www.kotlinlang.org)
614618 * spring.io
from line 690
686690 </Accordion>
687691
688692 <Accordion title="Cloud services and monitoring">
689 * statsig.com
690 * [www.statsig.com](http://www.statsig.com)
691 * api.statsig.com
692 * sentry.io
693 * \*.sentry.io
694 * downloads.sentry-cdn.com
695693 * http-intake.logs.datadoghq.com
696 * browser-intake-us5-datadoghq.com
697694 * \*.datadoghq.com
698695 * \*.datadoghq.eu
699696 * api.honeycomb.io
errors Changed · +3 / -4 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 1003
10031003
10041004```text theme={null}
10051005OAuth token revoked · Please run /login
1006OAuth token has expired · Please run /login
1007API Error: 401 ... authentication_error
1006Please run /login · API Error: 401 OAuth token has expired ...
10081007```
10091008
10101009**What to do:**
from line 1045
10461045Failed to authenticate: OAuth session expired and could not be refreshed
10471046```
10481047
1049This is not the same state as [OAuth token revoked or expired](#oauth-token-revoked-or-expired). Those messages report a 401 the API returned. Claude Code itself produces `Login expired` for a login it already failed to renew, so it sends no request. When the renewal fails because the account itself is suspended rather than the login being stale, Claude Code shows [Your account is on hold](#your-account-is-on-hold) instead.
1048This is not the same state as [OAuth token revoked or expired](#oauth-token-revoked-or-expired). Those messages report a rejection the API returned. Claude Code itself produces `Login expired` for a login it already failed to renew, so it sends no request. When the renewal fails because the account itself is suspended rather than the login being stale, Claude Code shows [Your account is on hold](#your-account-is-on-hold) instead.
10501049
10511050Sessions authenticated with an API key, [`CLAUDE_CODE_OAUTH_TOKEN`](/docs/en/env-vars), or a third-party provider don't use the saved login and never see this message.
10521051
from line 1641
16421641Context exceeds the 200k-token limit by 94k tokens — run /compact or /clear to continue.
16431642```
16441643
1645When the limit you exceeded is a compaction window smaller than the model's context window, such as the 200K boundary on 1M-context models, the warning reads differently. Requests still succeed past a compaction window; run the named command to bring usage back under it.
1644When the limit you exceeded is a compaction window, such as the 200K boundary on 1M-context models, the warning reads differently. A compaction window can sit below the model's context window, so requests past it can still succeed.
16461645
16471646```text theme={null}
16481647Context is 94k tokens past the 200k-token compaction window — run /compact to reduce usage.
from line 2049
20502049On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), and [Microsoft Foundry](/docs/en/microsoft-foundry), a cybersecurity flag produces the [Usage Policy refusal](#usage-policy-refusal) message instead.
20512050
20522051The safeguard itself is server-side and predates v2.1.203; client releases since then have changed only the message's wording.
2053From v2.1.203 through v2.1.218, the message read `<model> has safety measures that flagged this message for a cybersecurity topic. To learn about the Cyber Verification Program and apply for access,
2052From v2.1.203 through v2.1.218, the message read `<model> has safety measures that flagged this message for a cybersecurity topic. To learn about the Cyber Verification Program and apply for access, visit our help center:` followed by the same help-cent
jetbrains Changed · +4 / -4 lines
from line 82
8282#### General settings
8383
8484* **Claude command**: specify a custom command to run Claude, for example `claude`, `/usr/local/bin/claude`, or `npx @anthropic-ai/claude-code`
85* **Suppress notification for Claude command not found**: skip notifications about not finding the Claude command
85* **Suppress notification for when Claude Command is not found**: skip notifications about not finding the Claude command
8686* **Enable using Option+Enter for multi-line prompts**: on macOS only. When enabled, Option+Enter inserts new lines in Claude Code prompts. Disable if the Option key is being captured unexpectedly. Requires a terminal restart.
8787* **Enable automatic updates**: automatically check for and install plugin updates, applied on restart
8888
from line 207
207207
208208**Tools exposed to the model.** The server hosts several tools, but only one is visible to the model. The rest are internal RPC the CLI uses for its own UI, such as opening diffs and reading selections, and are filtered out before the tool list reaches Claude.
209209
210| Tool name (as seen by hooks) | What it does | Read-only |
211| ---------------------------- | --------------------------------------------------------------------------------------------------------------------- | --------- |
212| `mcp__ide__getDiagnostics` | Returns the IDE's inspection diagnostics, the errors and warnings shown in the editor. Optionally scoped to one file. | Yes |
210| Tool name (as seen by hooks) | What it does | Read-only |
211| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- |
212| `mcp__ide__getDiagnostics` | Returns the IDE's inspection diagnostics, the errors and warnings shown in the editor. Each call covers one file: the file Claude specifies, or the file in your active editor if Claude doesn't specify one. | Yes |
213213
214214The JetBrains plugin does not expose a code-execution tool to the model.
215215
prompt-caching Changed · +5 / -3 lines
from line 153
153153
154154### Denying an entire tool
155155
156Adding a bare tool name like `Bash` or `WebFetch` as a [deny rule](/docs/en/permissions#manage-permissions) removes that tool from Claude's context entirely. Claude Code loads built-in tool definitions into the system prompt layer, so adding or removing one of these rules mid-session invalidates the cache. Claude Code applies the change on the next request, whether you add the rule through `/permissions` or by [editing a settings file directly](/docs/en/settings#when-edits-take-effect). That includes a rule you add through `/permissions` in the middle of a turn.
156If you add a bare tool name like `Bash` or `WebFetch` as a [deny rule](/docs/en/permissions#manage-permissions), Claude can't call that tool from your next request on, whether you add the rule through `/permissions` or by [editing a settings file directly](/docs/en/settings#when-edits-take-effect). That includes a rule you add through `/permissions` in the middle of a turn.
157157
158Only a deny rule that matches in the tool-name position has this effect: a bare tool name, the equivalent `Bash(*)` form, or a [tool-name glob](/docs/en/permissions#tool-name-wildcards) like `"*"`. A glob that matches only MCP tools, such as `"mcp__*"`, removes those tools the same way but leaves the cache intact when the matched tools are [deferred](#connecting-or-disconnecting-an-mcp-server), the default, since deferred definitions were never in the cached prefix. Scoped deny rules like `Bash(rm *)`, and all allow and ask rules, don't change which tools Claude sees. Claude Code checks them when Claude attempts a call, leaving the prefix intact.
158When [tool search](/docs/en/mcp#scale-with-mcp-tool-search) is active, which is the default on supported models, the request's tool definitions don't change and the cached prefix survives. When tool search is unavailable or disabled, Claude Code removes the definition from the next request, which invalidates the cache, and so does removing the rule later.
159
160Only a deny rule that matches in the tool-name position blocks a tool this way: a bare tool name, the equivalent `Bash(*)` form, or a [tool-name glob](/docs/en/permissions#tool-name-wildcards) like `"*"`. A glob that matches only MCP tools, such as `"mcp__*"`, blocks those tools the same way. Scoped deny rules like `Bash(rm *)`, and all allow and ask rules, don't change which tools Claude sees. Claude Code checks them when Claude attempts a call, leaving the prefix intact.
159161
160162### Compacting the conversation
161163
settings-reference Changed · +3 / -5 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 3072
30723072
30733073### `footerLinksRegexes`
30743074
3075Render extra clickable badges in the footer below the input box when a regex matches turn output: tool results, including file contents and fetched pages, and Claude's own responses. Use it to turn IDs printed by project CLIs, such as review tools and issue trackers, into session links. Requires Claude Code v2.1.176 or later.
3075Render extra clickable badges in the footer below the input box when a regex matches turn output: tool results, including file contents and fetched pages, and Claude's own responses. Use it to turn IDs printed by project CLIs, such as review tools and issue trackers, into session links.
30763076
30773077* **Scope**: [`User or managed`](#scopes)
30783078* **Type**: array of objects, each with `type` set to `"regex"`, a `pattern` regex, a `url` template, and an optional `label`; `{name}` placeholders in `url` and `label` are filled from named capture groups in `pattern`
from line 3093
30933093}
30943094```
30953095
3096With this configured, when `PROJ-1234` appears in a tool result or in Claude's reply, a `PROJ-1234` badge appears in the footer linking to `https://issues.example.com/browse/PROJ-1234`. Requires Claude Code v2.1.176 or later.
3096With this configured, when `PROJ-1234` appears in a tool result or in Claude's reply, a `PROJ-1234` badge appears in the footer linking to `https://issues.example.com/browse/PROJ-1234`.
30973097
30983098#### Badge constraints
30993099
from line 3269
32693269Each `tips` entry is a plain string or an object with these fields:
32703270
32713271| Field | Required | Description |
3272| :----------------- | :------- | :------------------------
3272| :----------------- | :------- | :--------------------------------------------------------------------------------------------------------
vs-code Changed · +4 / -4 lines
from line 48
4848
4949 * **Activity Bar**: click the Spark icon in the left sidebar to open the sessions list. Click any session to open it in your [preferred location](#extension-settings), or start a new one. This icon is always visible in the Activity Bar.
5050 * **Command Palette**: `Cmd+Shift+P` (Mac) or `Ctrl+Shift+P` (Windows/Linux), type "Claude Code", and select an option like "Open in New Tab"
51 * **Status Bar**: if you've set [`preferredLocation`](#extension-settings) to `sidebar`, or opened Claude with **Claude Code: Open in Side Bar**, click **✱ Claude Code** in the bottom-right corner of the window. This works even when no file is open.
51 * **Status Bar**: if you've set [`preferredLocation`](#extension-settings) to `sidebar`, or opened Claude with **Claude Code: Open in Side Bar**, click **✻ Claude Code** in the bottom-right corner of the window. This works even when no file is open.
5252
5353 You can drag the Claude panel to reposition it anywhere in VS Code. See [Customize your workflow](#customize-your-workflow) for details.
5454 </Step>
from line 180
180180
181181Run `/usage` to open the Account & usage dialog. The dialog requires a claude.ai sign-in, so it isn't offered on a [third-party provider](#use-third-party-providers). It shows your signed-in account, your plan, and usage bars for your plan's limits, such as the current session and the week. Each bar shows how long until its limit resets.
182182
183The dialog also breaks down what is contributing to your plan limits. It flags behaviors that account for 10% or more of recent usage, such as cache misses, long context, and subagent-heavy or highly parallel sessions, each with a tip to reduce it. Attribution tables show how much usage came from each skill, subagent, plugin, and MCP server. Requires Claude Code v2.1.174 or later.
183The dialog also breaks down what is contributing to your plan limits. It flags behaviors that account for 10% or more of recent usage, such as cache misses, long context, and subagent-heavy or highly parallel sessions, each with a tip to reduce it. Attribution tables show how much usage came from each skill, subagent, plugin, and MCP server.
184184
185185Use the Day and Week toggle to switch between the last 24 hours and the last 7 days. The figures are approximate and computed from local sessions on this machine, so usage from other devices or claude.ai is not included. For more on tracking and reducing usage, see [Track your costs](/docs/en/costs#track-your-costs).
186186
from line 385
385385
386386The extension has two types of settings:
387387
388* **Extension settings** in VS Code: control the extension's behavior within VS Code. Open with `Cmd+,` (Mac) or `Ctrl+,` (Windows/Linux), then go to Extensions → Claude Code. You can also type `/` and select **General Config** to open settings.
388* **Extension settings** in VS Code: control the extension's behavior within VS Code. Open with `Cmd+,` (Mac) or `Ctrl+,` (Windows/Linux), then go to Extensions → Claude Code. You can also type `/` and select **General config…** to open settings.
389389* **Claude Code settings** in `~/.claude/settings.json`: shared between the extension and CLI. Use it for allowed commands, environment variables, hooks, and MCP servers. On Pro, Max, and Team plans, it's also one input to the permission mode conversations start in. [Switch permission modes](/docs/en/permission-modes#switch-permission-modes) lists the order. See [Settings](/docs/en/settings) for details.
390390
391391<Tip>
from line 586
5865864. **Disable conflicting extensions**: Temporarily disable other AI extensions (Cline, Continue, etc.)
5875875. **Check workspace trust**: The extension doesn't work in Restricted Mode
588588
589Alternatively, if you've set [`preferredLocation`](#extension-settings) to `sidebar`, or opened Claude with **Claude Code: Open in Side Bar**, click "✱ Claude Code" in the **Status Bar** (bottom-right corner). This works even without a file open. You can also use the **Command Palette** (`Cmd+Shift+P` / `Ctrl+Shift+P`) and type "Claude Code".
589Alternatively, if you've set [`preferredLocation`](#extension-settings) to `sidebar`, or opened Claude with **Claude Code: Open in Side Bar**, click "✻ Claude Code" in the **Status Bar** (bottom-right corner). This works even without a file open. You can also use the **Command Palette** (`Cmd+Shift+P` / `Ctrl+Shift+P`) and type "Claude Code".
590590
591591### Cmd+Esc does nothing on macOS
592592
amazon-bedrock Changed · +1 / -1 lines
from line 217
217217
218218As of Claude Code v2.1.181, the flat output from `aws configure export-credentials --format process` is also accepted, with the same keys at the top level instead of nested under `Credentials`.
219219
220`Expiration` is optional. As of Claude Code v2.1.176, when the command returns a valid ISO 8601 `Expiration`, Claude Code caches the credentials until five minutes before that time. Without it, or on earlier versions, credentials are cached for one hour.
220`Expiration` is optional. When the command returns a valid ISO 8601 `Expiration`, Claude Code caches the credentials until five minutes before that time. Without it, credentials are cached for one hour.
221221
222222When you configure `awsCredentialExport` without `awsAuthRefresh`, Claude Code uses the exported credentials directly and doesn't re-resolve the AWS default credential provider chain at startup. Requires Claude Code v2.1.206 or later.
223223
best-practices Changed · +0 / -2 lines
from line 512
512512claude -p "<your prompt>" --output-format json | your_command
513513```
514514
515Use `--verbose` for debugging during development, and turn it off in production.
516
517515### Run autonomously with auto mode
518516
519517For uninterrupted execution with background safety checks, use [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode). A classifier model reviews commands before they run, blocking scope escalation, unknown infrastructure, and hostile-content-driven actions while letting routine work proceed without prompts.
common-workflows Changed · +1 / -1 lines
from line 404
404404| [Routines](/docs/en/routines) | Cloud, Anthropic-managed by default | Tasks that should run even when your computer is off. Can also trigger on API calls or GitHub events in addition to a schedule. Configure at [claude.ai/code/routines](https://claude.ai/code/routines). |
405405| [Desktop scheduled tasks](/docs/en/desktop-scheduled-tasks) | Your machine, via the desktop app | Tasks that need direct access to local files, tools, or uncommitted changes. |
406406| [GitHub Actions](/docs/en/github-actions) | Your CI pipeline | Tasks tied to repo events like opened PRs, or cron schedules that should live alongside your workflow config. |
407| [`/loop`](/docs/en/scheduled-tasks) | The current CLI session | Quick polling while a session is open. Tasks stop when you start a new conversation; `--resume` and `--continue` restore unexpired ones. |
407| [`/loop`](/docs/en/scheduled-tasks) | The current CLI session | Quick polling while a session is open. `--resume` and `--continue` restore unexpired fixed-interval loops. |
408408
409409<Tip>
410410 When writing prompts for scheduled tasks, be explicit about what success looks like and what to do with results. The task runs autonomously, so it can't ask clarifying questions. For example: "Review open PRs labeled `needs-review`, leave inline comments on any issues, and post a summary in the `#eng-reviews` Slack channel."
costs Changed · +1 / -1 lines
from line 59
5959
6060Press `d` or `w` to switch between the last 24 hours and the last 7 days. The figures are approximate and computed from local session history on this machine, so usage from other devices or claude.ai is not included.
6161
62In the [VS Code extension](/docs/en/vs-code#check-account-and-usage), the attribution shares and behavior flags appear in the Account & usage dialog with a Day and Week toggle, without the Loops rows. Requires Claude Code v2.1.174 or later.
62In the [VS Code extension](/docs/en/vs-code#check-account-and-usage), the attribution shares and behavior flags appear in the Account & usage dialog with a Day and Week toggle, without the Loops rows.
6363
6464#### Check your usage-credits spend
6565
hooks Changed · +2 / -2 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 1730
17301730| `status` | string | `"completed"` | `"completed"` for foreground subagents, `"async_launched"` for background subagents. As of v2.1.198, subagents run in the background by default, so an omitted `run_in_background` also produces `"async_launched"` |
17311731| `agentId` | string | `"a4d2c8f1e0b3a297"` | Identifier for the subagent run |
17321732| `content` | array | `[{"type": "text", "text": "Found 12 endpoints..."}]` | The subagent's final text blocks |
1733| `resolvedModel` | string | `"claude-sonnet-4-5"` | Model the subagent started on, which may differ from the requested model. Requires Claude Code v2.1.174 or later |
1733| `resolvedModel` | string | `"claude-sonnet-4-5"` | Model the subagent started on, which may differ from the requested model |
17341734| `modelsUsed` | array | `["claude-sonnet-4-5", "claude-haiku-4-5"]` | Models used in order, with consecutive repeats collapsed; set only when the model was swapped mid-run. Requires Claude Code v2.1.212 or later |
17351735| `totalTokens` | number | `12450` | Token count from the subagent's final API request: input, output, and cache tokens combined. This isn't a total across the whole run |
17361736| `totalDurationMs` | number | `48211` | Wall-clock duration of the subagent run |
from line 1739
17391739
17401740For background subagents, the tool returns when the task moves to the background, so `tool_response` carries no usage fields: a background launch returns immediately, and a foreground task that Claude Code backgrounds mid-run returns at that transition. It has `status: "async_launched"`, `agentId`, `description`, `prompt`, `outputFile`, and `resolvedModel`.
17411741
1742On a `completed` response, `resolvedModel` names the model the subagent started on, which can differ from the `model` value in `tool_input`, such as when `availableModels` or another override applies. It requires Claude Code v2.1.174 or later. On an `async_launched` response, `resolvedModel` names the model in use when the agent moved to the background, so a swap that happened before backgrounding is reflected there. `modelsUsed` and the backgrounding-time `resolvedModel` behavior require Claude Code v2.1.212 or later.
1742On a `completed` response, `resolvedModel` names the model the subagent started on, which can differ from the `model` value in `tool_input`, such as when `availableModels` or another override applies. On an `async_launched` response, `resolvedModel` names the model in use when the agent moved to the background, so a swap that happened before backgrounding is reflected there. `modelsUsed` and the backgrounding-time `resolvedModel` behavior require Claude Code v2.1.212 or later.
17431743
17441744<a id="askuserquestion" />
17451745
from line 2769
27692769
27702770| Field | Description |
27712771| :----------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
2772| `watchPaths` | Array of absolute paths. Replaces the current dynamic watch list. Paths from your `matcher` configuration are always watched. Returning an empty array clears the dynamic list, whi
2772| `watchPaths` | Array of absolute paths. Replaces the current dynamic watch list. Paths from your `matcher` configuration are always watched. Returning an empty array clears the dynamic list, which is typical when entering a new directory
how-claude-code-works Changed · +1 / -1 lines
from line 171
171171
172172Built-in commands also guide you through setup:
173173
174* `/init` walks you through creating a CLAUDE.md for your project
174* `/init` generates a starter CLAUDE.md for your project
175175* `/doctor` runs a setup checkup that diagnoses installation and configuration issues and can fix them
176176
177177### It's a conversation
large-codebases Changed · +2 / -2 lines
from line 351
351351
352352### Keep skills discoverable
353353
354With skills spread across many directories, the list Claude chooses from can grow large. Claude picks a skill by reading every discovered skill's name and description, and only the chosen skill's full content loads into context. This section covers how to keep that list small and write descriptions that survive shortening.
354With skills spread across many directories, the list Claude chooses from can grow large. Claude picks a skill by reading every discovered skill's name and description, and only the chosen skill's full content loads into context. This section covers how to keep that list small.
355355
356356Which skills are in scope depends on where you start Claude:
357357
from line 359
359359* **From the repository root**: root skills, plus skills from every subdirectory Claude touches during the session, which can accumulate into the hundreds
360360* **After adding a sibling with [`--add-dir`](#grant-access-across-packages-or-repositories)**: that sibling's skills load too. The `additionalDirectories` setting grants file access only and does not load skills
361361
362Names always load, but [descriptions are shortened when there are many](/docs/en/skills#skill-descriptions-are-cut-short), which can strip the keywords Claude uses to decide whether a skill applies. Keep descriptions short and lead with words a request would contain, like "writing or modifying tests in `packages/api/`".
362Names always load, but [when there are many, some skills lose their descriptions entirely](/docs/en/skills#skill-descriptions-are-cut-short), which can strip the keywords Claude uses to decide whether a skill applies. Keep descriptions short and lead with words a request would contain, like "writing or modifying tests in `packages/api/`".
363363
364364For skills that many directories share, such as PR conventions or a deploy checklist, place them in the repository root's `.claude/skills/` so they load from any starting directory. When shared skills need their own version history or must work across repositories, package them as a [plugin](/docs/en/plugins) instead. Plugin skills use a `plugin-name:skill-name` namespace, so they never collide with per-directory skills. A platform team can version and update them in one place.
365365
permissions Changed · +3 / -1 lines
from line 57
5757
5858A broad deny rule like `Bash(aws *)` blocks every matching call, including calls that also match a narrower allow rule like `Bash(aws s3 ls)`, so a deny rule can't carry allowlist exceptions. The same precedence applies between ask and allow: a matching ask rule prompts even when a more specific allow rule also matches the same call.
5959
60Deny rules behave differently depending on whether they name a tool or scope a pattern within one. A bare tool name like `Bash` removes the tool from Claude's context entirely, so Claude never sees it. Bare-name removal applies to every tool except [`EndConversation`](/docs/en/tools-reference#endconversation-tool-behavior): a deny rule can't remove it while any other tool remains, and an ask rule never prompts for it. A scoped rule like `Bash(rm *)` leaves the tool available and blocks matching calls when Claude attempts them.
60Deny rules behave differently depending on whether they name a tool or scope a pattern within one. A bare tool name like `Bash` removes the tool from Claude's context entirely, so Claude never sees it. If you add such a rule mid-session, Claude can't call the tool from its next tool call on; [Denying an entire tool](/docs/en/prompt-caching#denying-an-entire-tool) covers what happens to a definition Claude has already seen. A scoped rule like `Bash(rm *)` leaves the tool available and blocks matching calls when Claude attempts them.
61
62Bare-name removal applies to every tool except [`EndConversation`](/docs/en/tools-reference#endconversation-tool-behavior): a deny rule can't remove it while any other tool remains, and an ask rule never prompts for it.
6163
6264<Note>
6365 Permission rules are enforced by Claude Code, not by the model. Instructions in your prompt or `CLAUDE.md` shape what Claude tries to do, but they don't change what Claude Code allows. To grant or revoke access, use `/permissions`, the rules described here, a [permission mode](/docs/en/permission-modes), or a [PreToolUse hook](#extend-permissions-with-hooks).
remote-control Changed · +1 / -1 lines
from line 160
1601603. The last meaningful message in existing conversation history
1611614. An auto-generated name like `myhost-graceful-unicorn`, where `myhost` is your machine's hostname or the prefix you set with `--remote-control-session-name-prefix`
162162
163If you didn't set an explicit name, Claude Code updates the title to reflect your prompt once you send one. Claude Code matches auto-generated titles to the language of your conversation, or to the [`language`](/docs/en/settings-reference#language) setting if one is configured; the language matching requires Claude Code v2.1.176 or later.
163If you didn't set an explicit name, Claude Code updates the title to reflect your prompt once you send one. Claude Code matches auto-generated titles to the language of your conversation, or to the [`language`](/docs/en/settings-reference#language) setting if one is configured.
164164
165165When you rename a session from claude.ai or the Claude app, Claude Code also updates the local title shown in `claude --resume`. Claude Code applies the same rename to the session name shown on the prompt bar, and in the `claude agents` listing when the session [runs in the background](/docs/en/agent-view). Before v2.1.221, renaming from the session list at claude.ai or in the Claude app updated only the title, and the CLI kept its previous session name; `/rename`, which runs in the CLI itself, set the name on any version.
166166
skills Changed · +1 / -1 lines
from line 223
223223
224224Claude Code labels synced skills so you can tell where they came from. The `/skills` menu and `/context` group synced skills under `claude.ai sync`, and the `/` command menu marks them as coming from claude.ai.
225225
226When it compares names, Claude Code ignores case, spacing, and invisible characters, and treats compatibility forms such as fullwidth letters and dash variants as their plain equivalents. For example, a local `commit` skill keeps `/commit`, and a synced `Commit` runs only as `/anthropic-skills:Commit`.
226When it compares names, Claude Code ignores case, spacing, and invisible characters, and treats compatibility forms such as fullwidth letters and dash variants as their plain equivalents. For example, a synced skill named `Commit` and a local skill named `commit` count as the same name, so `/commit` keeps running your local skill.
227227
228228A name that differs only by a look-alike letter from another alphabet counts as a different name, and the `claude.ai sync` label is how you tell the two apart. These checks and labels require Claude Code v2.1.228 or later.
229229