claude-code-20261022T183701Z / documentation capture

accessibility Changed · +8 / -1 lines

### Project settings can't turn on screen reader mode

from line 20

2020

2121The first line Claude Code prints confirms the mode: `[Screen Reader Mode: on via flag]`, `[Screen Reader Mode: on via env]`, or `[Screen Reader Mode: on via settings]`.

2222

23### Project settings can't turn on screen reader mode

24

25The startup line `Screen reader mode is off: project settings can't turn it on` means the project asked for screen reader mode and nothing else turns it on. Claude Code ignores both the `axScreenReader` key and a `CLAUDE_AX_SCREEN_READER` value under `env` in the project's `.claude/settings.json` and `.claude/settings.local.json`, whatever their value.

26

27* **To turn the mode on**: start Claude Code with `--ax-screen-reader`, set `CLAUDE_AX_SCREEN_READER` to `1` in your shell, or add `"axScreenReader": true` to your user [settings file](/docs/en/settings.md) and restart Claude Code. You don't need to change the project's files. Once you turn the mode on, the [confirmation line](#turn-on-screen-reader-mode) appears at startup instead.

28* **If you don't use a screen reader**: you don't need to do anything. To stop the line from appearing, add `"axScreenReader": false` to your user settings file, or remove the `axScreenReader` key and the `CLAUDE_AX_SCREEN_READER` variable from the project's settings files.

29

2330## Turn off screen reader mode

2431

25Reverse whichever method turned the mode on: start without the flag, unset the environment variable, or set `axScreenReader` to `false`. If you set `CLAUDE_AX_SCREEN_READER` to `0`, Claude Code keeps the mode off even when the setting is `true`.

32Reverse whichever method turned the mode on: start without the flag, unset the environment variable, or set `axScreenReader` to `false` in your user settings file. If you set `CLAUDE_AX_SCREEN_READER` to `0`, Claude Code keeps the mode off even when the setting is `true`.

2633

2734## Accessibility settings

2835

claude-projects Changed · +9 / -7 lines

from line 64

6464You create and use projects at [claude.ai/code](https://claude.ai/code), in the Code tab of the desktop app, or in the Claude mobile app for [iOS](https://apps.apple.com/us/app/claude-by-anthropic/id6473753684) and [Android](https://play.google.com/store/apps/details?id=com.anthropic.claude). In the browser and the desktop app there are two ways to start a project:

6565

6666* **From scratch**, when you know the stream of work you want Claude to run: open the **New project** dialog and name it. [Start a new project from scratch](#start-a-new-project-from-scratch) walks through the dialog.

67* **From a cloud session that's already doing the work**: choose **Continue as project** from that session's menu, and Claude proposes the project's setup from what the session was doing. See [Start from an existing cloud session](#start-from-an-existing-cloud-session).

67* **From a cloud session that's already doing the work**: in that session's sidebar menu, choose **Move to project**, then **Continue as new project**. Claude proposes the project's setup from what the session was doing. See [Start from an existing cloud session](#start-from-an-existing-cloud-session).

6868

6969Either way, [check the prerequisites](#check-the-prerequisites) first.

7070

from line 72

7272

7373Before you create a project, check your plan, your GitHub setup, and what the work needs to reach:

7474

75* **Plan**: you're on Pro or Max and **Projects** shows in your sidebar.

75* **Plan**: you're on Pro or Max, and **Projects** shows in your sidebar, directly or under **More**. Select **Projects** and check that it offers **New project** or **Get started**.

7676* **GitHub, if the project will work on code**: your code is on github.com rather than GitHub Enterprise Server, GitLab, or Bitbucket, your connected GitHub account has push access to it, and the Claude GitHub App is installed on it. If you connected GitHub with [`/web-setup`](/docs/en/web-quickstart#connect-from-your-terminal), that token lets your other cloud sessions reach a repository but isn't enough for a project's cloud threads, which need the Claude GitHub App. [Set up GitHub access](#set-up-github-access) has the steps.

7777* **Network access, secrets, and tools**: for cloud threads, these come from the project's [cloud environment](#choose-an-environment-for-threads). The default environment already reaches [common package registries](/docs/en/cloud-environments.md#default-allowed-domains), so check this only if the work needs other domains, a secret, or a tool that isn't preinstalled. If the work needs an MCP server, check that it shows as connected in your [claude.ai connectors](https://claude.ai/customize/connectors).

7878

from line 107

107107

108108### Start from an existing cloud session

109109

110If you already have a cloud session doing work that belongs in a project, open the session's menu in the sidebar and choose **Continue as project** or **Move to project**:

110If a cloud session you started yourself is doing work that belongs in a project, open its sidebar menu and choose **Move to project**, then pick from the submenu:

111111

112* **Continue as project** creates a new project named after the session and opens it. Claude reads the session and posts **Setup recommendations** in the conversation for you to confirm. The original session stays in your session list, and if it was in the middle of a turn it keeps running, so stop it yourself if you don't want both working at once. If you use the **Set up project** banner that can appear above a cloud session's message box instead, the result is the same, except that the session's running turn stops once the project opens.

113* **Move to project** brings the session's work into an existing project. It posts a message in that project's conversation asking Claude to read the session and pick up where it left off, and new work continues in the project's own threads. The original session stays in your session list, unchanged.

112* Choose **Continue as new project** to create a new project from the session. The project opens, and Claude reads the session and posts **Setup recommendations** in the project conversation for you to confirm. The original session stays in your session list. If it was in the middle of a turn it keeps running, so stop it yourself if you don't want both working at once.

113* Choose one of your existing projects to bring the session's work into that project. That project opens, and a message sent on your behalf asks Claude to read the session and pick up where it left off. The original session stays in your session list, unchanged.

114114

115A **Set up project** banner can also appear above a cloud session's message box. If you use it instead of **Continue as new project**, the result is the same, except that the session's running turn stops once the project opens.

116

115117A local session doesn't have these options. To continue its work in a project, describe the work in the project conversation, or push its branch, add that repository to the project, and name the branch in the task.

116118

117119### Set up GitHub access

from line 416

414416Several Claude Code features let more than one session work at the same time, so running work in parallel is not by itself what a project is for. In a project, Claude starts and tracks the sessions instead of you, and each one starts from the same instructions. This is how each neighboring feature connects to a project:

415417

416418* **Claude Tag**: [Claude Tag](https://claude.com/docs/claude-tag/overview) is Claude in your team's Slack channels, on Team and Enterprise plans. Anyone in a channel can give it work, everyone in the channel sees and steers it, and it uses connections an admin set up for that channel. A project is yours alone: you're the only one who sends it work or sees its threads, it uses your own GitHub access and connectors, and it's on Pro and Max. [How Claude Tag differs from Cowork and Claude Code](https://claude.com/docs/claude-tag/concepts/how-it-works#how-claude-tag-differs-from-cowork-and-claude-code) has the side-by-side.

417* **Cloud sessions**: every thread is a [cloud session](/docs/en/claude-code-on-the-web.md) unless you ask Claude to run it on your machine. Either way, Claude starts and tracks it instead of you. A cloud session you started yourself can become a project or feed one through [**Continue as project** or **Move to project**](#start-from-an-existing-cloud-session).

419* **Cloud sessions**: every thread is a [cloud session](/docs/en/claude-code-on-the-web.md) unless you ask Claude to run it on your machine. Either way, Claude starts and tracks it instead of you. You can also bring the work of a cloud session you started yourself into a project: choose [**Move to project**](#start-from-an-existing-cloud-session) in that session's sidebar menu.

418420* **Scheduled tasks**: when you ask for scheduled work in a project, Claude creates a [cloud scheduled task](/docs/en/routines.md) that runs as threads in that project and appears on its **Scheduled tasks** tab. Scheduled tasks you create outside a project keep working on their own.

419421* **Remote Control**: [Remote Control](/docs/en/remote-control.md) connects claude.ai to a Claude Code session running on your machine. When you ask Claude in a project to run a thread on your computer, the project [uses Remote Control to do it](#run-a-thread-on-your-own-computer).

420422* **Local sessions and agent view**: a session you start yourself in your terminal, IDE, or the desktop app's local environment can't be added to a project. [Agent view](/docs/en/agent-view.md) is a screen for tracking several local sessions side by side, and you still start each one and give it its task yourself.

code-review-pull-requests Changed · +26 / -6 lines

### When a push keeps the earlier result

from line 47

4747

4848A finding that has a line but wasn't posted as an inline comment appears as an annotation in the **Files changed** tab, on the lines concerned. Important findings show in red, nits in yellow, and pre-existing bugs in gray.

4949

50The check run concludes as neutral, or as skipped when an automatic review didn't run because a push changed no files. It never concludes as a failure, so a finished review doesn't fail a required check. If you don't see findings, or a review didn't run, see [Troubleshoot Code Review](/docs/en/code-review-troubleshooting.md).

50The check run concludes as neutral, or as skipped after some pushes that change no files and [keep the earlier result](#when-a-push-keeps-the-earlier-result). It never concludes as a failure, so a finished review doesn't fail a required check. If you don't see findings, or a review didn't run, see [Troubleshoot Code Review](/docs/en/code-review-troubleshooting.md).

5151

52### When a push keeps the earlier result

53

54If the check run has one of these titles after you push, Code Review kept the result of an earlier review instead of starting a new one:

55

56* **Code review skipped — no new changes**: no [Important](#severity-levels) finding from the earlier review is still open, so you don't need a new review

57* **Code review not repeated — earlier findings still open**: to start a new review, push a fix for an open Important finding, or [resolve its thread](#respond-to-findings) and push again

58

59On github.com, Code Review can keep a result when both of these hold:

60

61* The pull request still adds and removes the same lines, as after an empty commit, a clean merge of the base branch, or a clean rebase

62* Nobody has resolved an Important finding's thread since that review

63

64To get a review without a code change, comment [`@claude review`](#comment-commands) or click **Re-run** on the check run.

65

5266### Read the result from a script

5367

5468To gate a merge or post a summary from your own CI, parse the last line of the Details text with `gh` and jq. That line is an HTML comment that holds the severity counts as JSON:

from line 81

6781gh api repos/OWNER/REPO/commits/<commit-sha>/check-runs --jq '.check_runs[] | {id, name}'

6882```

6983

84If the commit has had more than one `Claude Code Review` run, such as after a **Re-run**, GitHub lists only the newest.

85

7086**2. Read the severity counts**

7187

7288Read the counts from the check run's `output.text` field, which holds the Details text. Replace `CHECK_RUN_ID` with the ID:

from line 94

7894 // error("no severity line")'

7995```

8096

81This prints a JSON object with a count per severity and its keys in alphabetical order, for example `{"nit": 1, "normal": 2, "pre_existing": 0}`. The counts include findings from earlier reviews of the pull request whose threads are still open.

97This prints a JSON object with a count per severity and its keys in alphabetical order, for example `{"nit": 1, "normal": 2, "pre_existing": 0}`. Except on a check run that [kept an earlier result](#when-a-push-keeps-the-earlier-result), the counts include findings from earlier reviews of the pull request whose threads are still open.

8298

99Under the title `Code review skipped — no new changes`, the counts leave out nits and pre-existing findings from earlier reviews that are still open. No Important finding from the earlier review is still open then.

100

83101**3. Act on the result**

84102

85Have your script handle these cases:

103Have your script handle these cases in order:

86104

105* **The title starts with `Code review not repeated`**: Code Review [kept an earlier result](#when-a-push-keeps-the-earlier-result) whose Important findings are still open, and the check run has no severity line. Read the title before the counts, with `gh api repos/OWNER/REPO/check-runs/CHECK_RUN_ID --jq .output.title`. Fail the job if you want to gate the merge.

106* **The title ends with `no new changes`**: let the job pass without reading the counts

87107* **`normal` is above zero**: fail the job if you want to gate the merge. The `normal` key holds the count of Important findings, so Claude found at least one bug worth fixing before merge. To print only that count, add `| .normal` before the closing single quote.

88108* **The line is missing**: the command prints an error that contains `no severity line` instead of counts, and exits with a non-zero status. Treat that as no verdict rather than as zero findings. A check run for a review that failed, timed out, was canceled, or was superseded by a newer one has no such line, and some completed reviews have none either.

89109

from line 113

93113

94114* **Open it or mark it ready**: in a repository set to **Once after PR creation** or **After every push**, a review starts when you open or reopen the pull request, or mark a draft ready for review.

95115* **Comment a command**: post [`@claude review`](#comment-commands) on the pull request.

96* **Push a commit**: a push starts a review in a repository set to **After every push**, or on a pull request you subscribed with `@claude review always`.

97* **Click Re-run**: after a review fails or times out on a pull request that isn't from a fork, [run it again](/docs/en/code-review-troubleshooting.md#retrigger-a-failed-or-timed-out-review) from the check run.

116* **Push a commit**: a push starts a review in a repository set to **After every push**, or on a pull request you subscribed with `@claude review always`. If your pull request still adds and removes the same lines after the push, Code Review can [keep the earlier result](#when-a-push-keeps-the-earlier-result) instead.

117* **Click Re-run**: after a review fails or times out on a pull request that isn't from a fork, [run it again](/docs/en/code-review-troubleshooting.md#retrigger-a-failed-or-timed-out-review) from the check run. On a pull request that isn't from a fork, you can also click **Re-run** after a push that [kept the earlier result](#when-a-push-keeps-the-earlier-result).

98118* **Wait for the automatic retry**: a review whose session was interrupted is retried once automatically. The [check run's summary](/docs/en/code-review-troubleshooting.md#retrigger-a-failed-or-timed-out-review) says when that's happening.

99119

100120### Comment commands

from line 124

104124| Command | What it does | When to use it |

105125| :- | :- | :- |

106126| `@claude review` | Starts a single review without subscribing the PR to future pushes | You want one review now, such as on a pull request in a repository set to **Manual**, or another review right away in the other modes |

107| `@claude review always` | Starts a review and subscribes the PR to push-triggered reviews going forward | You want every subsequent push to start a fresh review, such as on a high-priority PR in a repository set to **Manual** |

127| `@claude review always` | Starts a review and subscribes the PR to push-triggered reviews going forward | You want subsequent pushes to start reviews, such as on a high-priority PR in a repository set to **Manual** |

108128| `@claude review once` | Same as `@claude review`: starts a single review without subscribing | The same cases as `@claude review` |

109129| `@claude review stop` | Ends the PR's subscription to push-triggered reviews, without starting a review or canceling one that's already running. Claude replies with a comment instead of a check run. | You subscribed a PR with `@claude review always` in a repository set to **Manual** or **Once after PR creation**, and no longer want each push to start a review |

110130| `@claude review off` or `@claude review pause` | Same as `@claude review stop` | The same cases as `@claude review stop` |

routines Changed · +25 / -4 lines

### Permission prompts during a run #### Artifacts in Accept edits mode

from line 46

4646

4747Create a scheduled task from the web at [claude.ai/code/routines](https://claude.ai/code/routines), from the Desktop app, or from the CLI. All three surfaces write to the same cloud account, so a scheduled task you create in one shows up in the others immediately. In the Desktop app's **Code** tab, click **Scheduled** in the sidebar or in the sidebar's **More** menu, then **New task**, and continue with [Create from the web](#create-from-the-web).

4848

49Scheduled tasks run autonomously as full Claude Code cloud sessions. You don't choose a permission mode. The session runs shell commands, uses [skills](/docs/en/skills.md), and calls any connectors you include, all without stopping for approval apart from some [artifact actions](#when-a-run-publishes-an-artifact-without-asking). Outside a [project](/docs/en/claude-projects.md#what-threads-pick-up-from-your-repositories)'s threads, those skills include the ones committed to the cloned repository.

49Scheduled tasks run autonomously as full Claude Code cloud sessions. The session runs shell commands, uses [skills](/docs/en/skills.md), and calls any connectors you include. Outside a [project](/docs/en/claude-projects.md#what-threads-pick-up-from-your-repositories)'s threads, those skills include the ones committed to the cloned repository. You don't choose a permission mode when you create the task: see [Permission prompts during a run](#permission-prompts-during-a-run) for when a run stops to wait for you.

5050

5151What a scheduled task can reach is determined by:

5252

from line 108

108108

109109**6. Review connectors**

110110

111Switch to the **Connectors** tab of **Advanced settings**. All of your connected [MCP connectors](/docs/en/mcp.md) are included by default. Remove any the task doesn't need: Claude can use every tool from an included connector, including writes, without asking for permission during a run.

111Switch to the **Connectors** tab of **Advanced settings**. All of your connected [MCP connectors](/docs/en/mcp.md) are included by default. Remove any the task doesn't need: Claude can use an included connector during a run, including writes. For when a run stops to ask you first, see [Permission prompts during a run](#permission-prompts-during-a-run).

112112

113113**7. Create the task**

114114

from line 358

358358

359359To manage or add connectors outside of that dialog, visit [claude.ai/customize/connectors](https://claude.ai/customize/connectors) or use `/schedule update` in the CLI.

360360

361### Permission prompts during a run

362

363> [!NOTE]

364>

365> For a task that runs in your organization's self-hosted environment, see [Permissions and tool approval](/docs/en/self-hosted-environments-configuration.md#permissions-and-tool-approval).

366

367When a run starts a new session on Anthropic's cloud, that session begins in [auto mode](/docs/en/permission-modes.md#eliminate-prompts-with-auto-mode) unless auto mode is unavailable. In auto mode, a classifier model allows or blocks actions that would otherwise wait for your approval.

368

369A run still stops and waits for an answer in cases such as these:

370

371* **Actions that prompt even in auto mode**: for example, an action that matches an [ask rule](/docs/en/permissions.md#manage-permissions). See [How auto mode evaluates actions](/docs/en/permission-modes.md#how-auto-mode-evaluates-actions)

372* **Repeated blocks**: one block doesn't end the run. Once blocks reach auto mode's [repeated-block thresholds](/docs/en/permission-modes.md#repeated-block-thresholds), a permission prompt appears in the run's session and waits until someone answers it

373

374If auto mode is unavailable, such as when your organization turned it off or the task's model doesn't support it, the run keeps the permission mode it launched in. To answer a waiting prompt, open the run from the task's [detail page](#view-and-interact-with-runs).

375

376In a [project](/docs/en/claude-projects.md), a run can continue a thread rather than start a new session. That run keeps whatever permission mode the thread is in at the time. When that thread was made, it started in auto mode unless auto mode was unavailable. To answer a prompt waiting in that thread, see [Unblock a thread waiting on approval](/docs/en/claude-projects.md#unblock-a-thread-waiting-on-approval).

377

361378### When a run publishes an artifact without asking

362379

380During a run in [auto mode](#permission-prompts-during-a-run), Claude publishes an [artifact](/docs/en/artifacts.md) without asking you once the classifier allows the publish. You're still asked first when, for example, the publish matches an [ask rule](/docs/en/permissions.md#manage-permissions). A new artifact is visible only to you until you [share it](/docs/en/artifacts.md#share-an-artifact). The [Accept edits rules](#artifacts-in-accept-edits-mode) that follow don't apply in auto mode.

381

382When a scheduled task's job is to keep a page current, give it an artifact you already published.

383

384#### Artifacts in Accept edits mode

385

363386When a scheduled task's schedule or **Run now** starts a run, Claude can publish a new [artifact](/docs/en/artifacts.md) without asking. The new artifact is visible only to you until you [share it](/docs/en/artifacts.md#share-an-artifact). If the publish declares runtime capabilities for the page, such as [connector calls](/docs/en/artifacts.md#pull-live-data-with-mcp-connectors) or [file downloads](/docs/en/artifacts.md#offer-a-file-download), Claude asks first.

364387

365388In those runs, Claude republishes an existing artifact without asking only when all of these hold:

from line 396

373396* The existing page holds no grant that reaches beyond the page, such as [connector calls](/docs/en/artifacts.md#pull-live-data-with-mcp-connectors)

374397

375398In every other case, including a run that an API or GitHub trigger starts, Claude asks first.

376

377When a scheduled task's job is to keep a page current, give it an artifact you already published.

378399

379400### Environments and network access

380401

settings-reference Changed · +14 / -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 48

4949| [`awsAuthRefresh`](#awsauthrefresh) | Refresh expired [Bedrock credentials](/docs/en/amazon-bedrock.md#advanced-credential-configuration) in `.aws` with your own command | Authentication and providers | Any file |

5050| [`awsCredentialExport`](#awscredentialexport) | Supply [Bedrock credentials](/docs/en/amazon-bedrock.md#advanced-credential-configuration) as JSON from your own command | Authentication and providers | Any file |

from line 816

816816* Your `~/.claude/skills/` and `~/.claude/commands/` directories, including [skills synced from claude.ai](/docs/en/skills.md#where-synced-skills-load)

817817* An `--add-dir` directory

818818* [Plugins declared with a `.claude-plugin` manifest](/docs/en/plugins/loading#plugins-shared-through-a-repository) inside `~/.claude/skills/` or the project's `.claude/skills/`

819* Plugins loaded for one session only, whose ids end in [`@inline`](/docs/en/plugins/loading#find-where-a-plugin-came-from), when all of these hold:

820 * The session is a [Code session](/docs/en/desktop.md#environment-configuration) or [Cowork session](/docs/en/managed-settings.md#where-and-when-a-policy-applies), other than a cloud session, for which the Claude Desktop app itself starts Claude Code

821 * Your managed settings set the key, not only an embedding host's [parent settings](/docs/en/managed-settings.md#let-an-embedding-host-add-policy)

822 * The session runs Claude Code v2.1.305 or later

819823

820Skills from managed settings and bundled skills keep their `allowed-tools`. A skill's `disallowed-tools` still applies. For what a developer sees when Claude Code ignores the field, see [When only managed permission rules apply](/docs/en/skills.md#when-only-managed-permission-rules-apply).

824Skills from managed settings and bundled skills keep their `allowed-tools`. `@inline` plugins outside those Desktop sessions keep theirs too, except one named [`anthropic-skills`](/docs/en/skills#names-reserved-for-synced-skills). A skill's `disallowed-tools` still applies. For what a developer sees when Claude Code ignores the field, see [When only managed permission rules apply](/docs/en/skills.md#when-only-managed-permission-rules-apply).

821825

822826* **Scope**: [`Managed`](#scopes)

823827* **Type**: Boolean

from line 1960

19561960

19571961* **Scope**: [`Any file`](#scopes), with [limits on project and local settings](/docs/en/sandboxing.md#repository-settings-under-an-admin-required-sandbox)

19581962* **Type**: Boolean

1959 * `true`: sandboxed commands can connect to every Unix socket

1963 * `true`: sandboxed commands can connect to every Unix socket. On Linux and WSL2 they can also connect to VM sockets, the `AF_VSOCK` address family

19601964 * `false`: the sandbox blocks Unix-socket connections: on macOS except the paths in `allowUnixSockets`, and on Linux and WSL2 through the seccomp filter when it's present

19611965* **Default**: `false`

19621966

from line 2347

23432347

23442348 Ignoring this group in project and local settings requires Claude Code v2.1.282 or later.

23452349 * Variables that change how Claude Code starts or syncs, such as `CLAUDE_CODE_PROCESS_WRAPPER`, `CLAUDE_CODE_SYNC_SKILLS`, `CLAUDE_CODE_SYNC_PLUGINS`, `CLAUDE_CODE_PLUGIN_CACHE_DIR`, and `CLAUDE_CODE_PLUGIN_SEED_DIR`.

2350 * The [screen reader mode](/docs/en/accessibility.md) variable `CLAUDE_AX_SCREEN_READER` and the other variables whose names start with `CLAUDE_AX_`, such as [`CLAUDE_AX_STARTUP_QUIET_MS`](/docs/en/env-vars#variables).

23462351 * [`CLAUDE_CODE_USER_DIALOG_TIMEOUT_MS`](/docs/en/env-vars#variables), which sets the timer on an unanswered dialog.

23472352 * [`CLAUDE_CODE_DISABLE_ATTACHMENTS`](/docs/en/env-vars#variables), which turns off attachment processing.

23482353 * [`CLAUDE_CODE_DISABLE_FILE_MENTIONS`](/docs/en/env-vars#variables), which stops Claude Code from expanding `@` mentions of files and directories.

from line 2359

23542359* [`CLAUDE_CODE_RESTRICTED`](/docs/en/env-vars#variables), which Claude Code reads from the launch environment only, is ignored from every file.

23552360* [`CLAUDE_CODE_DISABLE_POWERSHELL_CMD_RM_DENY`](/docs/en/env-vars#variables), which Claude Code reads from the launch environment only, is ignored from every file. The variable requires Claude Code v2.1.283 or later.

23562361* [`CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT`, `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT`, `CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT`, and `CLAUDE_CODE_DISABLE_MOUNTED_DRIVE_RM_PROMPT`](/docs/en/env-vars#variables), which Claude Code reads from the launch environment only, are ignored from every file.

2362* [`CLAUDE_CODE_WARN_DISK_FREE_GIB` and `CLAUDE_CODE_WARN_MEMORY_FREE_GIB`](/docs/en/env-vars#variables), which Claude Code reads from the launch environment only, are ignored from every file. The variables require Claude Code v2.1.304 or later.

23572363

23582364### `fileCheckpointingEnabled`

23592365

from line 2387

23812387Idle compaction is on by default for conversations that meet all of these conditions:

23822388

23832389* **Session**: you're in an interactive terminal session

2390* **Auto-compaction**: [`autoCompactEnabled`](#autocompactenabled) is on

23842391* **Prompt cache**: the conversation is on the [one-hour prompt cache TTL](/docs/en/prompt-caching.md#which-ttl-each-request-gets)

23852392* **Feature flags**: Claude Code can [fetch feature flags from Anthropic](/docs/en/env-vars.md#features-that-need-feature-flag-fetching)

23862393* **Size**: the conversation's context has reached the token threshold, which you can [change](#change-the-idle-compaction-threshold) from its default of 200,000

from line 2548

25412548

25422549Render screen-reader friendly output: flat text without decorative borders or animations. Screen-reader mode uses the classic renderer, so the `tui` setting has no effect while it is active; attached [background sessions](/docs/en/agent-view.md) still render fullscreen.

25432550

2544* **Scope**: [`Any file`](#scopes)

2551* **Scope**: [`User or managed`](#scopes). You can also set the key in a file you pass with `--settings`. Claude Code ignores the key in project and local settings, so neither a repository nor your own `.claude/settings.local.json` can turn screen-reader mode on or off.

25452552* **Type**: Boolean

25462553 * `true`: Claude Code renders flat text without decorative borders or animations, using the classic renderer

25472554 * `false`: Claude Code renders normally

from line 3707

37003707 * `"off"`: Claude doesn't see the skill and `/name` is hidden from autocomplete

37013708* **Default**: unset, so every skill is `"on"`

37023709

3703This example lists `legacy-context` to Claude by name only and hides `deploy` from Claude and from `/` autocomplete:

3704

3705```json settings.json theme={null}

3706{

3707 "skillOverrides": {

3708 "legacy-context": "name-only",

3709 "deploy": "off"

3710 }

3711}

3712```

3713

3714Overrides don't apply to plugin skills, which you manage through `/plugin`.

3715

3716In managed settings and files passed with `--settings`, a key on a bundled skill's alias, such as `checkup` for `/doctor`, also applies to the skill; see [how alias keys combine with keys on the skill's own name](/docs/en/skills.md#override-skill-visibility-from-settings).

3717

3718### `syncClaudeAiSkills`

3719

3720Turn off the download of the [skills enabled for your claude.ai account](/docs/en/skills.md#how-synced-skills-behave). Claude Code downloads them into `~/.claude/skills/synced/` in [terminal sessions where you sign in with your claude.ai account](/docs/en/skills.md#where-synced-skills-load), interactive or non-interactive, and in Cowork and cloud sessions. Set `false` to stop that download and stop loading the skills it already synced. Claude Code honors only `false`: `true` is the same as unset and doesn't turn syncing on where it's otherwise off.

3721

3722* **Scope**: [`User, local, or managed`](#scopes), and files passed with `--settings`. A repository can't turn it off for you.

3723* **Type**: Boolean

3724 * `false`: Claude Code stops downloading synced skills and stops loading the ones already in `~/.claude/skills/synced/`. In user or managed settings, it also moves them to `~/.claude/skills/.trash/`

3725 * `true`: the same as unset

3726* **Default**: unset, so sessions signed in with your claude.ai account sync your skills

3727

3728This example keeps a machine from downloading the account's skills in any session:

3729

3730```json

3710This example lists `legacy-context` to Claude by name only and hides `deploy` from Claude and from `/` autocom

code-review-troubleshooting Changed · +1 / -0 lines

from line 14

1414| **Code review found no issues** | The review finished and found nothing to flag | Nothing |

1515| A title that says issues were found | The review finished with findings | If you don't see them on the diff, see [Find issues that aren't showing as inline comments](#find-issues-that-aren’t-showing-as-inline-comments) |

1616| **Code review skipped — no new changes** | An automatic review didn't run on your latest push | To get a review anyway, comment `@claude review` |

17| **Code review not repeated — earlier findings still open** | An automatic review didn't run on your latest push, and Important findings from the earlier review are still open | Push a fix, or to get a review anyway, comment `@claude review`. See [When a push keeps the earlier result](/docs/en/code-review-pull-requests.md#when-a-push-keeps-the-earlier-result) |

1718| **Code review failed** or **Code review timed out** | The review didn't finish | To run it again, see [Retrigger a failed or timed-out review](#retrigger-a-failed-or-timed-out-review) |

1819| **Code review declined** | The review didn't run | Read the check run's summary. If it names a budget or a spend limit, see [Review didn't run and the PR shows a budget message](#review-didn’t-run-and-the-pr-shows-a-budget-message) |

1920| No check run | No review started | Comment `@claude review`. If no check run appears after that, see [A comment command didn't start a review](#a-comment-command-didn’t-start-a-review) |

desktop-scheduled-tasks Changed · +1 / -1 lines

from line 23

2323| Persistent across restarts | Yes | Yes | Restored on `--resume`, with [exceptions](/docs/en/scheduled-tasks.md#limitations) |

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

2727| Customizable schedule | Yes | Yes | Yes |

2929

managed-settings Changed · +2 / -0 lines

from line 97

9797* **macOS configuration profile**: the `com.anthropic.claudecode` managed preferences domain. Use the same top-level keys as `managed-settings.json`, with nested settings as dictionaries and lists as plist arrays.

9898* **Windows HKLM registry**: the JSON as a `REG_SZ` or `REG_EXPAND_SZ` value named `Settings` under `HKLM\SOFTWARE\Policies\ClaudeCode`.

9999* **File-based**: `managed-settings.json`, an optional `managed-settings.d/` directory, and `managed-mcp.json` in the system directory: `/Library/Application Support/ClaudeCode/` on macOS, `/etc/claude-code/` on Linux and WSL, and `C:\Program Files\ClaudeCode\` on Windows. Claude Code doesn't read the legacy Windows path `C:\ProgramData\ClaudeCode\managed-settings.json`.

100

101 You can deploy any of these files as a symbolic link, and Claude Code reads the file the link leads to. The policy still applies when the link leads outside the system directory or Claude Code can't confirm that it stays inside. A warning naming the file then appears in `/status` and `claude doctor`. To clear the warning, point the link at a target inside the system directory.

100102* **Windows HKCU registry**: the same `Settings` value under `HKCU\SOFTWARE\Policies\ClaudeCode`.

101103

102104### Split a file-based policy across teams

mcp Changed · +1 / -1 lines

from line 332

332332

333333On v2, Claude Code also:

334334

335* Asks HTTP, stdio, and claude.ai connector servers whether they support the newer revision, and uses it with those that do. It connects to every other server as v1 does.

335* Asks HTTP, stdio, and claude.ai connector servers whether they support the newer revision and uses it with those that do. That includes the connectors of cloud and [Remote Control](/docs/en/remote-control.md) sessions. Claude Code connects to every other server as v1 does.

336336* Receives `list_changed` notifications from servers on the newer revision over a [stream it holds open](#notification-streams-on-the-v2-runtime).

337337* Doesn't register a [channel](#push-messages-with-channels) server that connects on the newer revision, because that revision can't carry channel messages.

338338* Fails an [MCP OAuth sign-in](#authenticate-with-remote-mcp-servers) whose authorization response names an unexpected issuer.

model-config Changed · +1 / -1 lines

from line 950

950950When you pin a model on a third-party provider, its row in the `/model` picker shows the model's name by default if Claude Code recognizes the pinned ID, and the raw ID otherwise:

951951

952952* **Recognized**: the exact ID of a model Claude Code knows, such as its Anthropic API ID or your provider's or gateway's form of it, with or without the `[1m]` suffix. Pin `us.anthropic.claude-sonnet-4-5-20250929-v1:0` and the row reads `Sonnet 4.5`.

953* **Not recognized**: any other ID, such as an application inference profile ARN or a model version Claude Code doesn't know, unless a [`modelOverrides`](#override-model-ids-per-version) entry maps a model to that exact string. On Microsoft Foundry, deployment names are user-defined, so Claude Code never recognizes a pinned ID there, mapped or not, and the row shows the deployment name by default.

953* **Not recognized**: any other ID, such as an application inference profile ARN or a model version Claude Code doesn't know, unless a [`modelOverrides`](#override-model-ids-per-version) entry maps a model to that ID. On Microsoft Foundry, deployment names are user-defined, so Claude Code never recognizes a pinned ID there, mapped or not, and the row shows the deployment name by default.

954954

955955When a row shows the model's name, its default description includes the pinned ID so you can still see which ID is pinned.

956956

scheduled-tasks Changed · +1 / -1 lines

from line 25

2525| Persistent across restarts | Yes | Yes | Restored on `--resume`, with [exceptions](/docs/en/scheduled-tasks.md#limitations) |

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

2929| Customizable schedule | Yes | Yes | Yes |

3131

One read of Claude Code CLIclaude-code-20261022T183701Z

What this read moved