claude-code-20260925T210701Z / documentation capture

errors Changed · +21 / -0 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 285

285285| `Claude Code's fullscreen renderer didn't finish starting last time on this machine` / `Claude Code's fullscreen renderer has repeatedly failed to start on this machine` | [Configuration warnings](#fullscreen-failed-start-notice) |

286286| `Claude Code exited after an unrecoverable interface error (...)` | [Configuration warnings](#exited-after-an-unrecoverable-interface-error) |

287287| `Agent descriptions are over the 15.0k-token limit` | [Configuration warnings](#agent-descriptions-are-over-the-15000-token-limit) |

288| `Not loaded: rename <path>, then restart — its name uses "<name>", a name reserved for the skills synced from your claude.ai account` | [Configuration warnings](#a-skill-command-or-workflow-wasnt-loaded-because-its-name-is-reserved) |

288289| `Ignoring N permissions.allow entries from ... this workspace has not been trusted` | [Configuration warnings](#workspace-has-not-been-trusted) |

289290| `is a network path, which cannot be added as a working directory` | [Configuration warnings](#working-directory-is-a-network-path) |

290291| `Remote managed settings failed to load (<cause>)` | [Configuration warnings](#remote-managed-settings-failed-to-load) |

from line 1900

18991900Context is 94k tokens past the 200k-token compaction window — run /compact to reduce usage.

19001901```

19011902

1902Both forms name `/clear` instead of `/compact` when you have set [`DISABLE_COMPACT`](/docs/en/env-vars).

1903

1904**What to do:**

1905

1906* In a multi-turn conversation, run `/compact` to summarize earlier turns and free space. To start fresh instead, run `/clear`

1907* For more ways to reduce usage, see [Prompt is too long](#prompt-is-too-long)

1908

1909Before v2.1.216, `/context` showed usage above 100% with no warning line explaining what

1903Both forms name `/clear

settings-reference Changed · +15 / -0 lines

### `maxProseWidth`

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 687

688688| [`managedSourcesBehavior`](#managedsourcesbehavior) | Compose every [managed source](/docs/en/managed-settings#how-claude-code-combines-managed-sources) you deploy instead of using the highest-priority one alone | Enterprise and managed settings | Managed |

from line 3175

31743175* **Type**: string, `"classic"` or `"readline"`

31753176* **Default**: unset

31763177

3177### `prefersReducedMotion`

3178### `maxProseWidth`

31783179

3179Reduce or turn off interface animations such as the spinner, shimmer, and flash effects. Appears in `/config` as **Reduce motion**.

3180Cap the width of the prose in Claude's responses so lines stay readable in a wide terminal. Paragraphs, headings, lists, and blockquotes wrap within this many columns, while tables and code blocks keep the full terminal width. Requires Claude Code v2.1.282 or later.

31803181

31813182* **Scope**: [`Any file`](#scopes)

3182* **Type**: Boolean

3183 * `true`: Claude Code reduces or turns off interface animations such as the spinner, shimmer, and flash effects

3184 * `false`: the same as unset; Claude Code shows its animations

3185* **Default**: `false`

3186

3187```json settings.json theme={null}

3188{

3189 "prefersReducedMotion": true

3190}

3191```

3192

3193### `promptSuggestionEnabled`

3194

3195Show or hide [prompt suggestions](/docs/en/interactive-mode#prompt-suggestions), the grayed-out predictions that appear in your prompt input. Set it to `false`, or turn off **Prompt suggestions** in `/config`, to hide them.

3196

3197* **Scope**: [`Any file`](#scopes)

3198* **Type**: Boole

3183* **Type**: number of terminal columns, a whole number, minimum `40`. Claude Code ignor

skills Changed · +23 / -10 lines

from line 123

123123Skill folders also follow these rules:

124124

125125* **Symlinked folders**: a `<skill-name>` entry in the enterprise, personal, or project location can be a symlink to a directory elsewhere on disk. Claude Code reads `SKILL.md` from the target and loads the skill once even if several locations point at the same target. Plugin skills [handle symlinks differently](/docs/en/plugins/host-marketplace#share-files-within-a-marketplace-with-symlinks).

126* **Reserved name**: don't name a skill folder `synced`, in any capitalization. Claude Code uses `~/.claude/skills/synced/` for [skills downloaded from claude.ai](#where-synced-skills-load) and skips a skill you author at that name in the enterprise, personal, and project locations.

126* **Reserved name `synced`**: don't name a skill folder `synced`, in any capitalization. Claude Code uses `~/.claude/skills/synced/` for [skills downloaded from claude.ai](#where-synced-skills-load) and skips a skill you author at that name in the enterprise, personal, and project locations.

127* **Reserved name `anthropic-skills`**: outside a plugin, a skill folder or command file whose name is `anthropic-skills` or starts with `anthropic-skills:` doesn't load. See [Names reserved for synced skills](#names-reserved-for-synced-skills).

127128* **Command files**: a Markdown file in `.claude/commands/` is the older format and still works. It supports the same [frontmatter](#frontmatter-reference) except `name` and `paths`. To find the name you type to invoke it, see [How a skill gets its command name](#how-a-skill-gets-its-command-name). Prefer a skill for new work, since skills also support [supporting files](#add-supporting-files).

128129* **Skill folder as a plugin**: add a `.claude-plugin/plugin.json` to a skill folder and it loads as a [plugin](/docs/en/plugins/loading#plugins-shared-through-a-repository) named `<name>@skills-dir`, so it can bundle agents, hooks, and MCP servers. In a project's `.claude/skills/`, this requires accepting the workspace trust dialog first.

129130

from line 157

156157

157158When two skills share a name, where each one came from decides which one `/name` runs. The table covers the enterprise, personal, project, nested, plugin, and claude.ai locations, bundled skills, and command files:

158159

159| Same name in | Which one runs |

160| :------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

161| Two of enterprise, personal, and project | Enterprise over personal, and personal over project. With `deploy` in both `~/.claude/skills/` and the project's `.claude/skills/`, `/deploy` runs the personal one |

162| Any of those locations and a [bundled skill](#bundled-skills) | Your skill replaces the bundled command, but not its aliases. A project `code-review` skill replaces `/code-review`, and the bundled alias `/review` never runs your skill |

163| A skill and a file in `.claude/commands/` | The skill |

164| A project-root skill and a nested skill | Both load. See [monorepos and subdirectories](#discovery-from-parent-and-nested-directories) |

165| A plugin skill and a skill at any of the locations above | Both load, because plugin skills are namespaced as `/plugin-name:skill-name` |

166| Any of the above and a skill [synced from your claude.ai account](#how-synced-skills-behave) | The other skill or command. The synced skill still runs as `/anthropic-skills:<name>`. See [When a synced skill name matches another command](#when-a-synced-skill-name-matches-another-command) |

160| Same name in | Which one runs |

161| :------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

162| Two of enterprise, personal, and project | Enterprise over personal, and personal over project. With `deploy` in both `~/.claude/skills/` and the project's `.claude/skills/`, `/deploy` runs the personal one |

163| Any of those locations and a [bundled skill](#bundled-skills) | Your skill replaces the bundled command, but not its aliases. A project `code-review` skill replaces `/code-review`, and the bundled alias `/review` never runs your skill |

164| A skill and a file in `.claude/commands/` | The skill |

165| A project-root skill and a nested skill | Both load. See [monorepos and subdirectories](#discovery-from-parent-and-nested-directories) |

166| A plugin skill and a skill at any of the locations above | Both load, because plugin skills are namespaced as `/plugin-name:skill-name` |

167| Any of the above and the short name of a skill [synced from your claude.ai account](#how-synced-skills-behave) | The other skill or command. The synced skill still runs as `/anthropic-skills:<name>`. See [When a synced skill name matches another command](#when-a-synced-skill-name-matches-another-command) |

167168

168169<h3 id="skills-in-cowork-and-cloud-sessions">

169170 Use skills in Cowork and cloud sessions

from line 233

232233

233234A 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.

234235

236<h4 id="names-reserved-for-synced-skills">

237 Names reserved for synced skills

238</h4>

239

240Claude Code reserves the name `anthropic-skills`, and every name inside that namespace such as `anthropic-skills:pdf`, for skills synced from claude.ai, so a synced skill's full name never runs anything else. The name is reserved in every session, whether or not you sign in with a claude.ai account.

241

242* **A skill folder, a frontmatter `name`, a file or subfolder in `.claude/commands/`, or a [saved workflow](/docs/en/workflows#save-the-workflow-for-reuse)**: it doesn't load. A [startup notice](/docs/en/errors#a-skill-command-or-workflow-wasnt-loaded-because-its-name-is-reserved) names the first item to rename or edit.

243* **A plugin named `anthropic-skills`**: it loads. When one of its skills and a synced skill are both named `<name>`, `/anthropic-skills:<name>` runs the synced skill.

244* **An MCP server named `anthropic-skills`**: it connects and its tools work, but [its prompts don't appear as commands](/docs/en/mcp#use-mcp-prompts-as-commands). Rename the server in your MCP configuration to list them.

245

235246#### How Claude Code handles the frontmatter of a synced skill

236247

237248Claude Code applies two rules to a synced skill's frontmatter:

from line 775

764775Skill(deploy *)

765776```

766777

767Permission syntax: `Skill(name)` for exact match, `Skill(name *)` for prefix match with any arguments.

778Permission syntax: `Skill(name)` for exact match, `Skill(name *)` for prefix match with any arguments. In an `allow` rule, a prefix outside the [namespace reserved for synced skills](#names-reserved-for-synced-skills) doesn't match the names inside it: `Skill(anthropic *)` doesn't cover `anthropic-skills:pdf`.

768779

769780If your `deny` rule names an alias or an unqualified name rather than the skill's own name, Claude Code still blocks the skill: with `Skill(review)` it blocks the bundled `/code-review` through its `/review` alias, and with `Skill(deploy)` it blocks a [nested skill](#where-skills-live) listed as `apps/web:deploy` through its unqualified name. Before v2.1.260, Claude Code didn't block a nested skill listed under its qualified name when the deny rule named only the unqualified name.

770781

771782Claude Code matches an `allow` rule only against the skill's own name and the name in Claude's invocation.

783

784To approve a [synced skill](#how-synced-skills-behave) without a prompt, name it inside its [reserved namespace](#names-reserved-for-synced-skills): `Skill(anthropic-skills:pdf)` approves the synced `pdf` skill, and `Skill(anthropic-skills *)` approves every synced skill.

772785

773786**Hide individual skills** by adding `disable-model-invocation: true` to their frontmatter. This removes the skill from Claude's context entirely.

774787

terminal-config Changed · +4 / -0 lines

## Cap response width in wide terminals

from line 303

303303 ```

304304</CodeGroup>

305305

306## Cap response width in wide terminals

307

308In a wide terminal, each line of prose in Claude's responses runs the full width of the window. To wrap the prose at a set number of columns instead, set [`maxProseWidth`](/docs/en/settings-reference#maxprosewidth) in your settings.

309

306310## Paste large content

307311

308312When you paste more than 800 characters or more than three lines into the prompt, Claude Code collapses the input to a placeholder such as `[Pasted text #1 +120 lines]` so the input box stays usable, and still sends the full content when you submit. For very large inputs such as entire files or long logs, write the content to a file and ask Claude to read it instead of pasting. The conversation transcript stays readable and Claude can refer to the file by path in later turns. The VS Code integrated terminal can also drop characters from very large pastes before they reach Claude Code, so use a file there.

llm-gateway-protocol Changed · +3 / -1 lines

from line 229

229229

230230### Disable pre-release capabilities

231231

232`CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` stops Claude Code from sending pre-release capabilities and their body fields on every provider, including context management and the beta tool fields. The variable doesn't affect adaptive reasoning, which is selected by model rather than by beta. It never suppresses the OAuth capability that subscription authentication requires.

232`CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` stops Claude Code from sending pre-release capabilities and their body fields, including context management and the beta tool fields. The variable doesn't affect adaptive reasoning, which is selected by model rather than by beta. It never suppresses the OAuth capability that subscription authentication requires.

233

234When a host platform that embeds Claude Code sets [`CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST`](/docs/en/env-vars), `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` doesn't stop auto mode sessions on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or a [Claude apps gateway](/docs/en/claude-apps-gateway) from asking the server for [classifier review](/docs/en/permission-modes#server-side-classifier-review). That review adds an `anthropic-beta` value and a `safeguards` request field. Set `CLAUDE_CODE_AUTO_MODE_SERVER=0` to stop it there.

233235

234236On Claude Code v2.1.227 or later, your organization can keep [MCP tool search](/docs/en/mcp#scale-with-mcp-tool-search) on under this variable through [managed settings](/docs/en/managed-settings). What Claude Code sends with that override in place depends on how you connect:

235237

mcp Changed · +2 / -0 lines

from line 1491

14911491

14921492MCP servers can expose prompts that become available as commands in Claude Code.

14931493

1494Prompts from a server named `anthropic-skills` don't appear, because Claude Code [reserves that name](/docs/en/skills#names-reserved-for-synced-skills) for skills synced from claude.ai. The server's tools still work. Rename the server in your MCP configuration to list its prompts.

1495

14941496### Execute MCP prompts

14951497

14961498<Steps>

permission-modes Changed · +1 / -1 lines

from line 323

323323* **The server doesn't review the session**: a response completes with no review results, or the server answers that it doesn't review this session. The most common causes are an LLM gateway or proxy that drops the request for review or the results, and a platform, region, or credential that doesn't have server-side checks yet. Claude Code falls back to its own classifier requests. Once that fallback holds for the rest of the session, it shows a [notice about classifier request charges](/docs/en/auto-mode-classifier-billing) on accounts where those requests are billed.

324324* **The server gives no verdict for an action**: Claude Code denies the action rather than run it unreviewed. On any connection, this happens when the response ends before the review results arrive or the results arrive in a form Claude Code can't read. An LLM gateway or proxy that cuts responses short or rewrites the results can cause either. On a direct connection to the Anthropic API, it also happens when the server's check fails for the action, for example by timing out. [The server returned no safety verdict](/docs/en/errors#the-server-returned-no-safety-verdict) covers the denial message, what happens when denials repeat, and what to do.

325325

326To skip asking the server and always use Claude Code's own classifier requests, set [`CLAUDE_CODE_AUTO_MODE_SERVER=0`](/docs/en/env-vars). On a direct connection to the Anthropic API, the variable requires Claude Code v2.1.281 or later. Setting it to `1` there turns server review on in a session that doesn't have it yet, such as a `-p` or Agent SDK session, unless you've also set `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1`. If you set `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` and leave `CLAUDE_CODE_AUTO_MODE_SERVER` unset, Claude Code also stops asking the server.

326To skip asking the server and always use Claude Code's own classifier requests, set [`CLAUDE_CODE_AUTO_MODE_SERVER=0`](/docs/en/env-vars). On a direct connection to the Anthropic API, the variable requires Claude Code v2.1.281 or later. Setting it to `1` there turns server review on in a session that doesn't have it yet, such as a `-p` or Agent SDK session, unless you've also set `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1`. If you set `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` and leave `CLAUDE_CODE_AUTO_MODE_SERVER` unset, Claude Code also stops asking the server, except as [Disable pre-release capabilities](/docs/en/llm-gateway-protocol#disable-pre-release-capabilities) describes.

327327

328328### What the classifier blocks by default

329329

plugin-evals Changed · +2 / -2 lines

from line 12

1212* Catch regressions when you change the plugin or a new model is released

1313* See what the plugin contributes compared with no plugin

1414

15This page is for plugin and skill authors who have a working plugin and want to test its behavior, and for teams that gate plugin changes in CI. Its case format is separate from the `evals/evals.json` file the [skill-creator plugin](/docs/en/skills#run-evals-with-skill-creator) uses. To create a plugin, see [Create a plugin](/docs/en/plugins/create); to check a plugin's files for syntax and schema errors rather than its behavior, use [`claude plugin validate`](/docs/en/plugins/cli-reference#plugin-validate).

15This page is for plugin and skill authors who have a working plugin and want to test its behavior, and for teams that gate plugin changes in CI. For iterating on one skill inside a Claude Code conversation, the [skill-creator plugin](/docs/en/skills#run-evals-with-skill-creator) runs a similar comparison with its own `evals/evals.json` format, and neither tool reads the other's case files. To create a plugin, see [Create a plugin](/docs/en/plugins/create); to check a plugin's files for syntax and schema errors rather than its behavior, use [`claude plugin validate`](/docs/en/plugins/cli-reference#plugin-validate).

1616

1717<Note>

1818 Every eval run and every judge grader is a real model call on your account, counted against your plan's usage or your API bill, so check the [requirements](#requirements) first. Then [create your first eval suite](#create-your-first-eval-suite), or go to [Run evals in CI](#run-evals-in-ci) if you already have one.

from line 408

408408| 130 | Interrupted. Partial results are written |

409409| 143 | Terminated, such as by a CI timeout |

410410

411Problems writing or publishing the HTML report never change the exit code.

411The with-minus-without delta is reported but never changes the exit code, and neither do problems writing or publishing the HTML report.

412412

413413To see why a case scored low, run it locally without `--json` so the per-run progress and grader lines print.

414414

plugins/install Changed · +1 / -1 lines

from line 135

135135A plugin's install scope decides who gets the plugin and which settings file records it as enabled:

136136

137137* **User scope**: the plugin is enabled for you in every project on this machine. The entry goes in `enabledPlugins` in `~/.claude/settings.json`.

138* **Project scope**: the plugin is enabled for everyone who works in this repository. The entry goes in `.claude/settings.json`, which you commit.

138* **Project scope**: the plugin is enabled for everyone who works in this repository. The entry goes in `.claude/settings.json`, which you commit. Committing that entry turns the plugin on for your collaborators but doesn't download it to their machines, so each collaborator also runs `claude plugin install <name>@<marketplace> --scope project` once; see [Enabled in project settings but not installed](/docs/en/plugins/loading#enabled-in-project-settings-but-not-installed).

139139* **Local scope**: the plugin is enabled for you in this repository only. The entry goes in `.claude/settings.local.json`.

140140

141141Some plugins are set by their author to start turned off, through the [`defaultEnabled`](/docs/en/plugins/manifest-reference#defaultenabled) field. Such a plugin is installed but stays off until you turn it on with `claude plugin enable <name>` in your shell, or from the **Installed** tab of `/plugin` in a session.

remote-control Changed · +1 / -0 lines

from line 60

6060 | `--capacity <N>` | Maximum number of concurrent sessions. Default is 32. Cannot be used with `--spawn=session`. |

6161 | `--[no-]create-session-in-dir` | Pre-create one session in the current directory when the server starts, so you have somewhere to type immediately. In `worktree` mode this session stays in the current directory while on-demand sessions get isolated worktrees. On by default. If you pass `--no-create-session-in-dir` to start with none, Claude Code archives the server's sessions when you stop it, so there's nothing to [resume](#resume-sessions-after-stopping-the-server). |

6262 | `--permission-mode <mode>` | Set the starting [permission mode](/docs/en/permission-modes) for the server's sessions, such as `acceptEdits`. Accepts `manual` as an alias for `default`; an unrecognized mode stops the server at startup and lists the valid modes. |

63 | `-d`, `--debug[=<filter>]` | Turn on debug logging for the server, optionally filtered by category. Pass a filter only in the `=` form, such as `--debug=api,hooks`. Requires Claude Code v2.1.282 or later; earlier versions reject the flag as an unknown argument. |

6364 | `--debug-file <path>` | Write debug logs to the given file. |

6465 | `--verbose` | Show detailed connection and session logs. |

6566 | `--sandbox` / `--no-sandbox` | Enable or disable [sandboxing](/docs/en/sandboxing) for filesystem and network isolation. Off by default. |

One read of Claude Code CLIclaude-code-20260925T210701Z

What this read moved