One read of Claude Code CLIclaude-code-20261003T013702Z
17 pages moved out of 220 read.
Pages moved
17
significant first
Pages read
220
in this capture
Captured
01:37 UTC
Corpus hash
a86609d2eb2d
corpus-hash
What this read moved
1-17 of 17champion-kit Changed · +6 / -6 lines
from line 38
3838Examples of reusable techniques:
3939
4040* "I learned that @-mentioning a directory works. Pointing it at `@src/components/` and asking which were missing tests surfaced two I had overlooked."
41* "Plan mode (`Shift+Tab`) shows exactly which files will be touched before any edit is made, which is why I am comfortable using it on shared code."
41* "Plan mode (`Shift+Tab`) lays out the proposed changes first, which is why I am comfortable using it on shared code."
4242* "I configured a Stop hook so I receive a desktop notification when a long task completes. Configuration is in the thread."
4343* "Running `/init` generates a `CLAUDE.md` from the repository so the assistant stops re-asking about our conventions."
4444
from line 73
7373
7474```text theme={null}
7575Plan mode is the reason I am comfortable using this on code that matters.
76Press Shift+Tab until you see "plan"; it lays out exactly which files it
77intends to touch before changing anything.
76Press Shift+Tab until you see "plan"; it lays out the changes it proposes
77without editing your source.
7878```
7979
8080## Be the person people ask
from line 102
102102| Question | Suggested response | Follow-up resource |
103103| - | - | - |
104104| "What should I try it on first?" | Recommend a real but contained task, ideally a bug or chore the person has been postponing because it is tedious rather than difficult. | [Common workflows](/docs/en/common-workflows) |
105| "How do I trust it with my code?" | Introduce plan mode: pressing `Shift+Tab` cycles into it, Claude proposes exactly what it intends to change, and nothing is modified until the user approves. | [Permissions](/docs/en/permissions) |
105| "How do I trust it with my code?" | Introduce plan mode: pressing `Shift+Tab` cycles into it, and Claude researches and proposes changes without editing your source. | [Permissions](/docs/en/permissions) |
106106| "Is the setup worth the effort?" | Installation takes roughly two minutes, runs in the terminal, and requires no IDE extension. Running `/init` once is sufficient to begin working. | [Quickstart](/docs/en/quickstart) |
107107| "It produced an incorrect result." | Encourage them to provide the failure back to Claude. Pasting the error message or failing test is far more effective than rephrasing the original request. | [Common workflows](/docs/en/common-workflows) |
108108| "It does not understand our codebase conventions." | Suggest running `/init` to generate a `CLAUDE.md` file, then adding the team's conventions, test commands, and any directories that should be avoided. | [Memory](/docs/en/memory) |
from line 165
165165| Concern | Suggested response | Evidence to offer |
166166| - | - | - |
167167| "I am faster without it." | That is likely true for code the person writes routinely. Suggest trying it on the work they tend to avoid: legacy files, unfamiliar services, or test scaffolding, where it helps the most. | Time one tedious task both ways and compare. |
168| "I do not trust AI to touch production code." | Agree that no change should land unread. Plan mode combined with normal diff review means nothing is applied that the engineer has not inspected, the same standard as any pull request. | Demonstrate plan mode on a real file. |
168| "I do not trust AI to touch production code." | Agree that no change should land unread. Suggest plan mode to see the proposed changes first, then review the diff to the same standard as any pull request. | Demonstrate plan mode on a real file. |
169169| "It will make junior engineers weaker." | Used well, it is an effective explainer. Encourage junior engineers to ask Claude to explain a file and its call sites before asking it to change anything. | Run "Explain @file and where it is called from" together. |
170170| "I tried it once and it hallucinated." | This is usually a context problem rather than a model problem. @-mentioning the relevant files, running `/init`, and providing the actual error output typically resolves it. | Re-run their original prompt with proper `@`-context. |
171171| "We do not have time to learn another tool." | Claude Code is a terminal command rather than a platform. If it does not return value within the first session, it is reasonable to set it aside. | A two-minute install followed by one real bug. |
from line 177
177177| Technique | How to apply it |
178178| - | - |
179179| Provide the right context | Use `@file` or `@directory/` references, or paste the error or log output directly. Supplying relevant context is more effective than elaborate prompting. |
180| Review the plan before the edit | Press `Shift+Tab` to enter plan mode. Claude will describe the intended changes for your approval before executing them. |
180| Review the plan before the edit | Press `Shift+Tab` to enter plan mode. Claude researches and proposes changes without editing your source. |
181181| Teach it your repository | Run `/init` to generate a `CLAUDE.md` file, then add your conventions, test commands, and any directories that should not be modified. See [Memory](/docs/en/memory). |
182182| Reuse a workflow | Save a `SKILL.md` file in `.claude/skills/<name>/` to create a `/name` skill that the entire team can use. See [Skills](/docs/en/skills). |
183183| Stay informed during long tasks | Configure a Stop hook to receive a desktop notification when a long-running task completes. See [Hooks](/docs/en/hooks-guide). |
communications-kit Changed · +14 / -18 lines
from line 39
3939 As of today you have access to Claude Code, an AI coding agent that runs in
4040 your terminal, reads your actual codebase, and works through real tasks end
4141 to end: debugging, refactors, tests, PRs. It is not autocomplete and it is
42 not a chat window. It edits files, runs your commands, and asks permission
43 before anything risky.
42 not a chat window. It edits files and runs your commands.
4443
4544 Get running in two minutes:
4645
from line 57
5857 - "Look at my working diff and tell me what's risky before I push"
5958
6059 Where your code goes: Claude Code runs in your terminal and talks directly
61 to Anthropic's API, with no third-party servers in the loop. It asks before
62 editing files or running commands. On our Team or Enterprise plan, Anthropic
63 does not use your code or prompts to train its models.
60 to Anthropic's API. On our Team or Enterprise plan, Anthropic does not use
61 your code or prompts to train its models.
6462 Details: https://code.claude.com/docs/en/data-usage
6563 https://code.claude.com/docs/en/security
6664
from line 77
7977 🚀 *Claude Code is live for [team]*
8078
8179 AI coding agent, runs in your terminal, reads your repo, does real work:
82 bugs, refactors, tests, PRs. Asks before it touches anything.
80 bugs, refactors, tests, PRs.
8381
8482 `curl -fsSL https://claude.ai/install.sh | bash` → `cd your-repo` → `claude`
8583
from line 84
8684 *First thing to try* → run `/init`, then: "the test in [file] is flaky,
8785 figure out why and fix it."
8886
89 🔒 Runs in your terminal, talks only to Anthropic's API. On our Team or
87 🔒 Runs in your terminal, talks directly to Anthropic's API. On our Team or
9088 Enterprise plan, your code and prompts are not used to train models.
9189 Data usage → https://code.claude.com/docs/en/data-usage
9290
from line 168
170168[Continue with "Get running in two minutes" from the standard announcement]
171169
172170One extra thing for pilots: on your first multi-file change, press Shift+Tab
173until you see "plan". Claude will lay out exactly what it intends to do
174before it touches a file. It is the fastest way to calibrate how much to
171until you see "plan". Claude will lay out what it intends to do
172without editing your source. It is the fastest way to calibrate how much to
175173trust it.
176174```
177175
from line 303
305303`default` setting value) asks before file edits and most shell commands, *acceptEdits* lets file
306304edits and common filesystem commands
307305flow through while still checking before other shell commands, and *plan*
308proposes changes for your approval before anything is touched. Plan mode is
306researches and proposes changes without editing your source. Plan mode is
309307the trust-builder, so start there for anything touching multiple files.
310308
311309*Try it now:* on your next refactor, hit Shift+Tab until you see "plan",
312then describe the change. You'll get a full proposal before a single file
313moves.
310then describe the change. You'll get a full proposal to review.
314311
315312📖 Permission modes → https://code.claude.com/docs/en/permissions
316313```
from line 458
461458Someone on your team is going to ask "wait, where does my code go?"
462459Here's the short version you can paste.
463460
464Permission-first by design. Every file edit, shell command, and external
465call is gated by your approval. The CLI runs in your terminal and talks
466directly to Anthropic's API, with no third-party servers, and supports
467optional OS-level sandboxing for shell commands. On a Team or Enterprise plan,
461A permission mode sets which actions Claude can take without asking you
462first. The CLI runs in your terminal, talks directly to Anthropic's API,
463and supports optional OS-level sandboxing for shell commands. On a Team or Enterprise plan,
468464Anthropic does not use your code or prompts to train its models.
469465
470466*Try it now:* save these two links for the next time the question comes up.
from line 500
504500| - | - |
505501| "Does it work in VS Code?" | Yes. There is a VS Code extension and a JetBrains plugin with the same features, embedded in your editor. [VS Code →](/docs/en/vs-code) |
506502| "Do I have to configure anything first?" | No. Install, then run `claude` in any repo. Run `/init` once and you're set. [Quickstart →](/docs/en/quickstart) |
507| "Where does my code go?" | The CLI runs in your terminal and sends context to Anthropic's API for inference, with no third-party servers. On a Team or Enterprise plan, your code and prompts are not used to train models. [Data usage →](/docs/en/data-usage) |
508| "Can it see my whole repo?" | It reads what you give it access to. File reads inside your working directory don't prompt; permission prompts gate edits, non-read-only shell commands, and file-tool reads outside that directory. A built-in set of read-only shell commands such as `ls` and `cat` runs without prompting; restrict it with [sandbox `denyRead` rules](/docs/en/sandboxing#filesystem-isolation). [Permissions →](/docs/en/permissions) |
503| "Where does my code go?" | The CLI runs in your terminal and sends context to Anthropic's API for inference. On a Team or Enterprise plan, your code and prompts are not used to train models. [Data usage →](/docs/en/data-usage) |
504| "Can it see my whole repo?" | It reads what you give it access to. File reads inside your working directory don't prompt. [Permissions →](/docs/en/permissions) |
509505| "How is this different from Copilot?" | Copilot autocompletes lines. Claude Code is an agent that reads files, runs commands, and makes multi-file edits. [Overview →](/docs/en/overview) |
510506| "What should I try first?" | A bug you've been putting off because it's tedious. "The test in \[file] is flaky, figure out why." [Quickstart →](/docs/en/quickstart) |
511507
keybindings Changed · +27 / -1 lines
from line 60
6060| `EffortSlider` | Effort slider opened by `/effort` |
6161| `Select` | Generic select/list components |
6262| `Plugin` | Plugin dialog (browse, discover, manage) |
63| `Pane` | A pane drawn by a [mod](/docs/en/plugins/mods/interface#know-which-keys-your-mod-can-receive) has keyboard focus |
64| `PaneField` | An input field or select in a mod's pane has keyboard focus |
6365| `Agents` | [Agent view](/docs/en/agent-view) (`claude agents`) |
6466| `Scroll` | Conversation scrolling and text selection in fullscreen mode |
6567
from line 524
522524
523525This also works for chord bindings. Unbinding every chord that shares a prefix frees that prefix for use as a single-key binding. A chord in any active context keeps its prefix reserved, so you must unbind each chord in the context that defines it.
524526
525Claude Code binds these default chords on the `ctrl+x` prefix: `ctrl+x ctrl+k`, `ctrl+x ctrl+e`, `ctrl+x enter`, `ctrl+x ctrl+a`, `ctrl+x ctrl+s`, and `ctrl+x tab` in `Chat`, `ctrl+x ctrl+b` in `Task`, and `ctrl+x b` in `DiffPanel`. The `ctrl+x enter` chord requires v2.1.247 or later, `ctrl+x b`, `ctrl+x ctrl+a`, and `ctrl+x tab` require v2.1.260 or later, and `ctrl+x ctrl+s` requires v2.1.275 or later.
527Claude Code binds these default chords on the `ctrl+x` prefix, by context:
526528
529* `Chat`: `ctrl+x ctrl+k`, `ctrl+x ctrl+e`, `ctrl+x enter`, `ctrl+x ctrl+a`, `ctrl+x ctrl+s`, and `ctrl+x tab`
530* `Task`: `ctrl+x ctrl+b`
531* `DiffPanel`: `ctrl+x b`
532* `Pane`: `ctrl+x left`, `ctrl+x right`, `ctrl+x up`, `ctrl+x down`, and `ctrl+x x`
533* `PaneField`: `ctrl+x x`
534
535The `ctrl+x enter` chord requires v2.1.247 or later, `ctrl+x b`, `ctrl+x ctrl+a`, and `ctrl+x tab` require v2.1.260 or later, and `ctrl+x ctrl+s` requires v2.1.275 or later.
536
527537To reclaim `ctrl+x` itself as a single-key binding, unbind all of them:
528538
529539```json theme={null}
from line 549
539549 "context": "DiffPanel",
540550 "bindings": {
541551 "ctrl+x b": null
552 }
553 },
554 {
555 "context": "Pane",
556 "bindings": {
557 "ctrl+x left": null,
558 "ctrl+x right": null,
559 "ctrl+x up": null,
560 "ctrl+x down": null,
561 "ctrl+x x": null
562 }
563 },
564 {
565 "context": "PaneField",
566 "bindings": {
567 "ctrl+x x": null
542568 }
543569 },
544570 {
plugins/mods/create Changed · +6 / -1 lines
from line 355
355355
356356## Share your mod
357357
358A mod is a plugin, so you version it in the manifest and people install and update it with the `/plugin` commands. To give it to other people, [add it to a marketplace](/docs/en/plugins/publish).
358A mod is a plugin, so you version it in the manifest and people install and update it with the `/plugin` commands. How you share it depends on who it's for:
359
360* **A few people**: send them the plugin's directory or a `.zip` of it. See [Share a plugin without a marketplace](/docs/en/plugins/publish#share-a-plugin-without-a-marketplace)
361* **Your team**: list it in [your own marketplace](/docs/en/plugins/publish#publish-through-your-own-marketplace), such as a private repository with one directory for each plugin. To add that marketplace for everyone who works in a repository, [register it in the repository's settings](/docs/en/plugins/host-marketplace#register-the-marketplace-for-everyone-in-a-repository)
362* **Your whole organization**: an administrator can [install your organization's mods](/docs/en/plugins/mods/admin#install-your-organizations-mods) through managed settings
363* **Anyone**: make your marketplace's repository public, or [submit the plugin to Anthropic's directory](/docs/en/plugins/publish#submit-to-anthropics-directory)
359364
360365Before you do, check the plugin's `name`: `claude plugin validate` fails a name that [looks like one of Anthropic's own](/docs/en/plugins/manifest-reference#name), such as one that starts with `claude-`. The events and methods can change between releases, so your README is the place to say which Claude Code version you tested with.
361366
sandboxing Changed · +2 / -4 lines
from line 419
419419
420420### Mask credentials
421421
422When you mask a credential, Claude Code shows sandboxed commands a per-session placeholder called the sentinel, and the [sandbox proxy](#network-isolation) substitutes the real value on outbound requests to hosts you allow. A `deny` entry under [Protect credentials](#protect-credentials) blocks the credential instead. For files on macOS, Claude Code [blocks the file instead](#mask-credential-files) of masking it.
422When you mask a credential, Claude Code shows sandboxed commands a per-session placeholder called the sentinel, and the [sandbox proxy](#network-isolation) substitutes the real value on outbound requests to hosts you allow. A `deny` entry under [Protect credentials](#protect-credentials) blocks the credential instead. For files on macOS, Claude Code [blocks the file instead](#mask-credential-files) of masking it. The [`sandbox.credentials`](/docs/en/settings-reference#sandbox-credentials) reference lists every field.
423423
424Masking environment variables requires Claude Code v2.1.199 or later. The [`sandbox.credentials`](/docs/en/settings-reference#sandbox-credentials) reference lists every field.
425
426424Masking requires the following:
427425
428426* **TLS termination**: the proxy substitutes the real value inside request contents, so it has to see them. Set [`network.tlsTerminate`](/docs/en/settings-reference#sandbox-network-tlsterminate) so the proxy terminates TLS itself. Without it, masking fails without exposing anything: the command still sees only the sentinel, but the sentinel reaches the server unchanged and authentication fails. Claude Code reports this misconfiguration at startup.
from line 564
566564In a `WebFetch(domain:...)` rule, the sandbox honors two wildcard forms: a leading `*.`, such as `*.example.com`, and a bare `*`. The bare `*` form requires Claude Code v2.1.186 or later. A wildcard in any other position, such as `WebFetch(domain:example.*)`, still matches fetches but has no effect on sandboxed commands.
567565
568566<Note>
569 The built-in proxy enforces the allowlist based on the requested hostname and, by default, does not terminate or inspect TLS traffic. The experimental [`network.tlsTerminate`](/docs/en/settings-reference#sandbox-network-tlsterminate) setting, available in Claude Code v2.1.199 and later, makes the built-in proxy terminate TLS itself, which [`mask` credential entries](#mask-credentials) require. See [Security limitations](#security-limitations) for the implications of the default, and [Custom proxy configuration](#custom-proxy-configuration) if your threat model requires TLS inspection.
567 The built-in proxy enforces the allowlist based on the requested hostname and, by default, does not terminate or inspect TLS traffic. The experimental [`network.tlsTerminate`](/docs/en/settings-reference#sandbox-network-tlsterminate) setting makes the built-in proxy terminate TLS itself, which [`mask` credential entries](#mask-credentials) require. See [Security limitations](#security-limitations) for the implications of the default, and [Custom proxy configuration](#custom-proxy-configuration) if your threat model requires TLS inspection.
570568</Note>
571569
572570#### Hosts outside your allowed domains
settings-reference Changed · +5 / -7 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 2331
23312331
23322332### `sandbox.credentials.envVars`
23332333
2334Protect environment variables from sandboxed commands. With `"mode": "deny"`, Claude Code removes the variable from the environment of sandboxed commands. With `"mode": "mask"`, sandboxed commands see a per-session sentinel value, and the sandbox proxy substitutes the real value on outbound requests to that entry's `injectHosts`, so tools such as `gh` and `npm` keep authenticating without ever holding the real credential. `"mode": "mask"` requires Claude Code v2.1.199 or later.
2334Protect environment variables from sandboxed commands. With `"mode": "deny"`, Claude Code removes the variable from the environment of sandboxed commands. With `"mode": "mask"`, sandboxed commands see a per-session sentinel value, and the sandbox proxy substitutes the real value on outbound requests to that entry's `injectHosts`, so tools such as `gh` and `npm` keep authenticating without ever holding the real credential.
23352335
23362336* **Scope**: [`Any file`](#scopes). Claude Code drops `mask` entries from project `.claude/settings.json` and local `.claude/settings.local.json`.
23372337* **Type**: array of objects, each with `name` and a `mode` of `"deny"` or `"mask"`, plus the optional [mask fields for environment variables](#mask-fields-for-environment-variables)
from line 2352
23522352}
23532353```
23542354
2355The `name` must start with a letter or underscore and contain only letters, digits, and underscores. Claude Code merges the arrays from every settings scope the session loads, and applies `deny` when the same variable appears with both modes. [Protect credentials](/docs/en/sandboxing#protect-credentials) covers what still applies from sources you exclude with `--setting-sources`. `mask` entries require Claude Code v2.1.199 or later.
2355The `name` must start with a letter or underscore and contain only letters, digits, and underscores. Claude Code merges the arrays from every settings scope the session loads, and applies `deny` when the same variable appears with both modes. [Protect credentials](/docs/en/sandboxing#protect-credentials) covers what still applies from sources you exclude with `--setting-sources`.
23562356
23572357`mask` substitution runs only through the sandbox proxy, so set [`sandbox.network.tlsTerminate`](#sandbox-network-tlsterminate), or [`allowPlaintextInject`](#sandbox-credentials-allowplaintextinject) for plain-HTTP test networks; see [Mask credentials](/docs/en/sandboxing#mask-credentials). Claude Code accepts but ignores the `mask` fields on a `deny` entry.
23582358
from line 2376
23762376| `onExtractNoMatch` | `"warn"`, `"deny"`, or `"error"`; default `"warn"`. On an entry with `decode`, only `"warn"` is accepted | What happens when `extract` matches nothing. `warn` passes the variable through unmasked, `deny` unsets it inside the sandbox, and `error` stops sandbox setup until you fix the configuration. Requires v2.1.224 or later |
23772377| `decode` | the string `"jwt"` | Verify the whole value is a JWT and replace it with a structurally valid fake token, so code inside the sandbox that decodes the token keeps working; the proxy substitutes the whole real token on egress. A value that doesn't verify passes through unmasked with a warning. Requires v2.1.224 or later |
23782378| `maskClaims` | array of strings, at least one claim name; requires `decode` | Mask only the named top-level payload claims inside the decoded JWT and rebuild the token around the modified payload, so the other claims stay readable. When no named claim matches, the variable passes through unmasked with a warning. Requires v2.1.224 or later |
2379| `injectHosts` | array of strings, each a host that [`sandbox.network.allowedDomains`](#sandbox-network-alloweddomains) also admits | Narrow the hosts where the sandbox proxy substitutes the real value. When unset, the proxy substitutes it on requests to every host in `sandbox.network.allowedDomains`. Write an IPv6 destination as the bare compressed address, such as `"::1"`, not the bracketed form; see [IPv6 destinations in `injectHosts`](/docs/en/sandboxing#ipv6-destinations-in-injecthosts). Requires v2.1.199 or later |
2379| `injectHosts` | array of strings, each a host that [`sandbox.network.allowedDomains`](#sandbox-network-alloweddomains) also admits | Narrow the hosts where the sandbox proxy substitutes the real value. When unset, the proxy substitutes it on requests to every host in `sandbox.network.allowedDomains`. Write an IPv6 destination as the bare compressed address, such as `"::1"`, not the bracketed form; see [IPv6 destinations in `injectHosts`](/docs/en/sandboxing#ipv6-destinations-in-injecthosts) |
23802380
23812381This masks only the password inside `DATABASE_URL`, unsets the variable if the pattern matches nothing, and masks a JWT in `SERVICE_JWT` while leaving every claim except `api_key` readable:
23822382
from line 2405
24052405
24062406### `sandbox.credentials.allowPlaintextInject`
24072407
2408Allow `mask` substitution on plain HTTP requests as well as TLS-terminated HTTPS. On plain HTTP the upstream identity is unverified and the credential travels in cleartext, so leave this off outside trusted test networks. Requires Claude Code v2.1.199 or later.
2408Allow `mask` substitution on plain HTTP requests as well as TLS-terminated HTTPS. On plain HTTP the upstream identity is unverified and the credential travels in cleartext, so leave this off outside trusted test networks.
24092409
24102410* **Scope**: [`User or managed`](#scopes)
24112411* **Type**: Boolean
from line 2423
24232423}
24242424```
24252425
2426Requires Claude Code v2.1.199 or later.
2427
24282426### `sandbox.credentials.awsPairs`
24292427
24302428Group masked environment variables that form one AWS credential for [SigV4 re-signing](/docs/en/sandboxing#re-sign-aws-requests) when your credential lives in variables with non-standard names. Claude Code links the conventional `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, and `AWS_SESSION_TOKEN` trio automatically when you mask their whole values, so you need this key only for other names. Requires Claude Code v2.1.224 or later.
from line 2738
27402738}
27412739```
27422740
2743When more than one honored source sets it, Claude Code uses the value from the highest-precedence source: managed settings, then the `--settings` flag, then user settings. Requires Claude Code v2.1.199 or later.
2741When more than one honored source sets it, Claude Code uses the value from the highest-precedence source: managed settings, then the `--settings` flag, then user settings.
27442742
27452743<span id="context-and-memory" />
27462744
from line 4044
40464044
40474045Mods built into Claude Code keep running in both cases. Each has [its own switch](/docs/en/plugins/mods/overview#mods-built-into-claude-code).
40484046
4049Keeping Agent SDK hooks running when managed settings set this k
4047Keeping Agent SDK hooks running when managed settings set this key requires Claude Code v2.1.242 or later.
4048
4049The [`/goal`](/docs/en/goal) command can't run while hooks are disabled, and the `/hooks` menu shows a notice instead of your hooks.
4050
4051#### Status line and file suggestion gates
4052
4053Claude Code makes two decisions for `s
setup Changed · +5 / -5 lines
from line 35
3535 <Tab title="Native Install (Recommended)">
3636 **macOS, Linux, WSL:**
3737
38 ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
38 ```bash theme={null}
3939 curl -fsSL https://claude.ai/install.sh | bash
4040 ```
4141
4242 **Windows PowerShell:**
4343
44 ```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
44 ```powershell theme={null}
4545 irm https://claude.ai/install.ps1 | iex
4646 ```
4747
4848 **Windows CMD:**
4949
50 ```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
50 ```batch theme={null}
5151 curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd
5252 ```
5353
from line 65
6565 </Tab>
6666
6767 <Tab title="Homebrew">
68 ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
68 ```bash theme={null}
6969 brew install --cask claude-code
7070 ```
7171
from line 77
7777 </Tab>
7878
7979 <Tab title="WinGet">
80 ```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
80 ```powershell theme={null}
8181 winget install Anthropic.ClaudeCode
8282 ```
8383
skills Changed · +5 / -4 lines
from line 180
180180
181181### Resolve skills that share a name
182182
183When two skills share a directory or file name, where each one came from decides which one `/name` runs. For a name set by the frontmatter `name` field, see [How a skill gets its command name](#how-a-skill-gets-its-command-name). The table covers the enterprise, personal, project, nested, plugin, and claude.ai locations, bundled skills, and command files:
183When two skills share a directory or file name, where each one came from decides which one `/name` runs. For a name set by the frontmatter `name` field, see [How a skill gets its command name](#how-a-skill-gets-its-command-name). The table covers the enterprise, personal, project, nested, plugin, and claude.ai locations, bundled skills, built-in commands, and command files:
184184
185185| Same name in | Which one runs |
186186| :- | :- |
187187| 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 |
188188| 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 |
189| Any of those locations and a [built-in command](/docs/en/commands) | In a local terminal session, your skill replaces the built-in command, but not its aliases. A project `usage` skill replaces `/usage`, and the built-in alias `/cost` still runs the built-in command |
189190| A skill and a file in `.claude/commands/` | The skill |
190191| A project-root skill and a nested skill | Both load. See [monorepos and subdirectories](#discovery-from-parent-and-nested-directories) |
191192| A plugin skill and a skill at any of the locations above | Both load, because plugin skills are namespaced as `/plugin-name:skill-name` |
from line 383
382383| `allowed-tools` | No | Tools Claude can use without asking permission during the turn that invokes this skill. The grant clears when you send your next message. Accepts a space- or comma-separated string, or a YAML list. See [Pre-approve tools for a skill](#pre-approve-tools-for-a-skill). |
383384| `disallowed-tools` | No | Tools removed from Claude's available pool while this skill is active. Use for autonomous skills that should never call certain tools, such as `AskUserQuestion` for a background loop. Accepts a space- or comma-separated string, or a YAML list. The restriction clears when you send your next message. Like deny rules, the field can't remove [`EndConversation`](/docs/en/tools-reference#endconversation-tool-behavior) while any other tool remains. |
384385| `model` | No | Model to use when this skill is active. The override applies for the rest of the current turn and isn't saved to settings. The session model resumes when you send your next prompt. Accepts the same values as [`/model`](/docs/en/model-config), or `inherit` to keep the active model. A value excluded by your organization's [`availableModels`](/docs/en/model-config#restrict-model-selection) allowlist isn't used, and the session keeps its current model. In [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), and in [plan mode while the classifier reviews commands](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), a model that auto mode doesn't support also isn't used, and the session keeps its current model. With `context: fork`, the value sets the [forked subagent's model](#run-skills-in-a-subagent) instead, and an excluded value follows the [same rules as a subagent model override](/docs/en/model-config#restrict-model-selection). |
385| `effort` | No | [Effort level](/docs/en/model-config#adjust-effort-level) when this skill is active. Overrides the session effort level. Default: inherits from session. Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model. |
386| `effort` | No | [Effort level](/docs/en/model-config#adjust-effort-level) when this skill is active. Overrides the session effort level. When you omit it, the level comes from the [effort resolution order](/docs/en/model-config#adjust-effort-level). Options: `low`, `medium`, `high`, `xhigh`, `max`; available levels depend on the model. |
386387| `context` | No | Set to `fork` to run in a forked subagent context. See [Run skills in a subagent](#run-skills-in-a-subagent). |
387388| `agent` | No | Which subagent type to use when `context: fork` is set. |
388389| `background` | No | Only applies with `context: fork`. Set to `false` to wait for the forked subagent's result in the turn that invoked the skill, instead of [running it in the background](#run-skills-in-a-subagent). Default: `true`. Requires Claude Code v2.1.218 or later. |
from line 613
612613
613614If you invoke a skill with arguments but no placeholder in the skill's content receives one, Claude Code appends `ARGUMENTS: <your input>` to the end of the skill content so Claude still sees what you typed. A placeholder is `$ARGUMENTS`, an indexed form such as `$1`, or a named argument. An indexed placeholder with no argument at its position stays as literal text and doesn't count as receiving one. A named placeholder counts even when its position has no argument, because it expands to an empty string.
614615
615You can also stack several skills at the start of one message. Typing `/write-tests /fix-issue 123` loads both skills and passes the trailing text `123` as `$ARGUMENTS` to each of them. Before v2.1.199, only the first skill loaded and received `/fix-issue 123` as literal argument text.
616You can also stack several skills at the start of one message. Typing `/write-tests /fix-issue 123` loads both skills and passes the trailing text `123` as `$ARGUMENTS` to each of them.
616617
617618Claude Code expands the first skill plus up to five more stacked after it. Expansion stops at the first token that isn't an inline user-invocable skill, so a skill that runs as a [forked subagent](#run-skills-in-a-subagent), such as [`/code-review`](/docs/en/code-review#review-a-diff-locally), or one whose arguments may themselves start with a slash command, such as `/loop`, also ends the run there. That token and everything after it become the argument text for every expanded skill. `/code-review` runs as a forked subagent from v2.1.218; on earlier versions it ran inline and stacked.
618619
from line 854
853854
854855The `/skills` menu labels the `"user-invocable-only"` state `user-only`.
855856
856As of v2.1.199, `"off"` also hides the skill from the command lists advertised to [Remote Control](/docs/en/remote-control) clients and to [Agent SDK](/docs/en/agent-sdk/skills#discover-available-commands) callers, in addition to the terminal `/` menu. Invoking a hidden skill by its full name still returns the `skillOverrides` error instead of running it.
857`"off"` also hides the skill from the command lists advertised to [Remote Control](/docs/en/remote-control) clients and to [Agent SDK](/docs/en/agent-sdk/skills#discover-available-commands) callers, in addition to the terminal `/` menu. Invoking a hidden skill by its full name returns the `skillOverrides` error instead of running it.
857858
858859A skill that is absent from `skillOverrides` is treated as `"on"`. The example below collapses one skill to its name and turns another off entirely:
859860
agent-teams Changed · +1 / -1 lines
from line 79
7979* **Enter**: open the selected teammate's transcript and message it directly
8080* **Escape**: clear the selection. While you're viewing a teammate's transcript, Escape interrupts that teammate's current turn
8181
82As of v2.1.199, an idle teammate's row stays in the panel while any teammate or subagent is still working, so you can select it to review its transcript or send it more work. Once every agent in the panel is idle, idle rows hide after 30 seconds and reappear on the teammate's next turn; the teammate stays running and addressable while hidden. In v2.1.181 through v2.1.198, an idle row hid 30 seconds after its own turn ended, even while other teammates were still working; idle rows are not hidden on versions before v2.1.181.
82An idle teammate's row stays in the panel while any teammate or subagent is still working, so you can select it to review its transcript or send it more work. Once every agent in the panel is idle, idle rows hide after 30 seconds and reappear on the teammate's next turn; the teammate stays running and addressable while hidden.
8383
8484When more than three teammates are idle at once, the rows beyond the first three collapse into a single row that counts the collapsed teammates, such as `2 idle agents` when five are idle. Select it and press Enter to expand the collapsed rows, or press Esc to collapse them again. Working teammates, failed teammates, and the teammate you're viewing always keep their own rows.
8585
cloud-environments Changed · +2 / -2 lines
from line 102
102102
103103#### Add a credential
104104
105You add credentials one at a time from the editor of an environment that already exists. The dialog for a new environment doesn't offer them. There's no edit, either. To change a credential's hosts or value, delete it and add it again.
105You add credentials one at a time, and you can't edit a credential after you add it. To change a credential's hosts or value, delete it and add it again.
106106
107107<Steps>
108108 <Step title="Open the environment's API credentials">
109 [Open the environment for editing](#configure-your-environment) at [claude.ai/code](https://claude.ai/code). In the **Edit cloud environment** dialog, find **API credentials** below **Environment variables**. You see the credentials already on the environment, each with the hosts it applies to.
109 [Open the environment for editing](#configure-your-environment) at [claude.ai/code](https://claude.ai/code). In the **Edit environment** dialog, find the **API credentials** section. You see the credentials already on the environment, each with the hosts it applies to.
110110 </Step>
111111
112112 <Step title="Add the credential">
errors Changed · +1 / -1 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 1895
18951895These steps change one of your own environments. An [organization-shared environment](/docs/en/cloud-environments#organization-shared-environments) opens read-only in the selector, so ask an Owner to change its network access from the **Cloud environments** page in [admin settings](https://claude.ai/admin-settings).
18961896
18971897* Open your environment for editing, either from the [routine's form](/docs/en/routines#environments-and-network-access) or from the [environment selector](/docs/en/cloud-environments#configure-your-environment) where you start cloud sessions.
1898* In the **Edit cloud environment** dialog, change **Network access** from **Trusted** to **Custom**, then add the blocked domain to **Allowed domains**. Enter one domain per line. Check **Also include default list of common package managers** to keep the [default allowlist](/docs/en/cloud-environments#default-allowed-domains) alongside your custom domains. Select **Full** instead if you want unrestricted access.
1898* In the **Edit environment** dialog, change **Network access** from **Trusted** to **Custom**, then add the blocked domain to **Allowed domains**. Enter one domain per line. Check **Also include default list of common package managers** to keep the [default allowlist](/docs/en/cloud-environments#default-allowed-domains) alongside your custom domains. Select **Full** instead if you want unrestricted access.
18991899* Click **Save changes**. The next run uses the updated allowlist. For a cloud session that's already open, see [when a network access change reaches existing sessions](/docs/en/cloud-environments#network-access).
19001900
19011901See [Network access](/docs/en/cloud-environments#network-access) for access levels and the default allowlist. Local CLI sessions are not affected by this policy.
from line 2800
28002800
28012801What follows the first line depends on how the value failed. Claude Code runs these checks in order and stops at the first one that fails. If your value has two kinds of problem, you see the second only after you fix the first:
28022802
28031. When the value begins with `{` but doesn't parse as JSON, or the contents of an `--age
28031. When the value begins with `{` but doesn't parse as JSON, or the contents of an `--agents` f
hooks Changed · +1 / -1 lines
from line 1821
18211821
18221822In [non-interactive mode](/docs/en/headless) with the `-p` flag, Claude Code offers `AskUserQuestion` and `ExitPlanMode` only when the run has a [permission host](/docs/en/headless#turn-off-permission-prompts-in-unattended-runs) to receive the prompt, such as an Agent SDK `canUseTool` callback. These tools require user interaction. Returning `permissionDecision: "allow"` together with `updatedInput` satisfies that requirement: the hook reads the tool's input from stdin, collects the answer through your own UI, and returns it in `updatedInput` so the tool runs without prompting. Returning `"allow"` alone is not sufficient for these tools. For `AskUserQuestion`, echo back the original `questions` array and add an [`answers`](#askuserquestion) object mapping each question's text to the chosen answer.
18231823
1824As of v2.1.199, an MCP tool whose server marks it with [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) is stricter: a hook can't skip its approval prompt with `"allow"`, with or without `updatedInput`, because Claude Code can't confirm the hook collected the interaction the tool needs.
1824An MCP tool whose server marks it with [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) is stricter: a hook can't skip its approval prompt with `"allow"`, with or without `updatedInput`, because Claude Code can't confirm the hook collected the interaction the tool needs.
18251825
18261826<Note>
18271827 PreToolUse previously used top-level `decision` and `reason` fields, but these are deprecated for this event. Use `hookSpecificOutput.permissionDecision` and `hookSpecificOutput.permissionDecisionReason` instead. The deprecated values `"approve"` and `"block"` map to `"allow"` and `"deny"` respectively. Other events like PostToolUse and Stop continue to use top-level `decision` and `reason` as their current format.
mcp Changed · +0 / -2 lines
from line 1361
13611361}
13621362```
13631363
1364The `anthropic/requiresUserInteraction` annotation requires Claude Code v2.1.199 or later. Earlier versions ignore it and apply the standard permission flow.
1365
13661364Some surfaces, such as [Remote Control](/docs/en/remote-control) and applications built on the [Agent SDK](/docs/en/agent-sdk/overview), normally let you approve tool calls with one tap. For a tool marked with this annotation, Claude Code withholds the one-tap action and shows the tool's full permission prompt instead, so approval still comes from a person answering the prompt rather than a tap.
13671365
13681366Claude Code withholds one-tap approval the same way for any permission request that only the terminal dialog can render in full, such as one that carries a safety warning or an always-allow option the remote surface can't show. You answer that request in the terminal dialog rather than from Remote Control. Requires Claude Code v2.1.214 or later.
permission-modes Changed · +1 / -1 lines
from line 544
544544
545545If you set `dontAsk` mode, Claude Code auto-denies every tool call that would otherwise prompt you. Claude still runs actions that need no approval in Manual mode, such as file reads inside your working directories and [read-only Bash commands](/docs/en/permissions#read-only-commands), plus actions matching your `permissions.allow` rules and calls approved by a [PreToolUse hook](/docs/en/permissions#extend-permissions-with-hooks). Use this mode for CI pipelines or restricted environments where you pre-define what Claude may do; the session never waits for input. The status bar shows `⏵⏵ don't ask on` while this mode is active.
546546
547Claude Code denies calls matching your explicit [`ask` rules](/docs/en/permissions#manage-permissions) rather than prompting. It also denies the built-in `AskUserQuestion` tool even if your allow rules match it, and does the same to connector tools [your organization set to `ask`](/docs/en/mcp#organization-controls-on-connector-tools) in sessions where that setting reaches Claude Code. It denies MCP tools marked [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) the same way, because their approval card needs an answer this mode never collects; this requires Claude Code v2.1.199 or later.
547Claude Code denies calls matching your explicit [`ask` rules](/docs/en/permissions#manage-permissions) rather than prompting. It also denies the built-in `AskUserQuestion` tool even if your allow rules match it, and does the same to connector tools [your organization set to `ask`](/docs/en/mcp#organization-controls-on-connector-tools) in sessions where that setting reaches Claude Code. It denies MCP tools marked [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) the same way, because their approval card needs an answer this mode never collects.
548548
549549`rm` and `rmdir` removals targeting a [critical path](#critical-paths), such as `rm -rf /` and `rm -rf ~`, are denied even when an allow rule matches them or a `PreToolUse` hook allows them.
550550
plugins/mods/interface Changed · +3 / -0 lines
from line 507
507507| Up and Down | Move between controls while your drawing fits. When the pane or band has more rows than it can show, they scroll it. |
508508| Enter | Presses the focused `Button`, submits the focused `Input`, or picks in a `Select` |
509509| A button's hotkey | Presses that button. While an `Input` has the focus, every printable key goes to the field. |
510| Page Up, Page Down, Home, and End | Scroll your pane or band when it has more rows than it can show |
511| Ctrl+X then an arrow key | Resizes your pane. Left or Up gives it more room, and Right or Down gives the room back. |
512| Ctrl+X then X | Closes your pane, even while one of its fields has the focus |
510513| Esc | Returns keyboard focus to the prompt. With `closeOnEscape: true`, it also closes the pane. |
511514
512515A mod can't bind Tab or the arrow keys to anything else, so a game steers with `w`, `a`, `s`, and `d`.
routines Changed · +1 / -1 lines
from line 359
359359 </Step>
360360
361361 <Step title="Change the network access level">
362 In the **Edit cloud environment** dialog, change **Network access** to **Custom** and enter your domains in **Allowed domains**. Check **Also include default list of common package managers** to keep the [default allowlist](/docs/en/cloud-environments#default-allowed-domains) alongside your custom domains. Select **Full** instead for unrestricted access.
362 In the **Edit environment** dialog, change **Network access** to **Custom** and enter your domains in **Allowed domains**. Check **Also include default list of common package managers** to keep the [default allowlist](/docs/en/cloud-environments#default-allowed-domains) alongside your custom domains. Select **Full** instead for unrestricted access.
363363 </Step>
364364
365365 <Step title="Save">
sub-agents Changed · +2 / -2 lines
from line 926
926926
927927When something [cuts off a subagent's response mid-stream](/docs/en/errors#the-response-above-may-be-incomplete), and the partial response contains text but no tool calls, Claude Code prompts the subagent to continue rather than ending the run. This happens in interactive sessions too. The run ends on the error only once those continuations are used up.
928928
929As of v2.1.199, a subagent whose run ends on an API error, such as a usage limit or a repeated server error, reports that failure back to Claude instead of returning the error text as if it were the subagent's findings. What Claude receives depends on where the subagent ran:
929A subagent whose run ends on an API error, such as a usage limit or a repeated server error, reports that failure back to Claude. What Claude receives depends on where the subagent ran:
930930
931931* **Foreground**: if a rate limit, overload, or server error cuts off a subagent that already produced text output, the Agent tool returns that partial output with a note that the subagent was cut off and didn't finish its task. A subagent that produced nothing, or whose only output was tool calls, fails with [`Agent terminated early due to an API error`](/docs/en/errors#agent-terminated-early-due-to-an-api-error), followed by the error detail. In v2.1.199, a rate limit, overload, or server error that cut off the tool-calls-only shape returned an empty partial result containing only the cut-off note instead.
932932* **Background**: the subagent is marked failed, and the message Claude receives when it ends names the API error and includes the subagent's last output, so partial work isn't lost.
from line 1106
11061106
11071107Resuming starts a new run of the agent under the same ID, so a subagent that had already failed or completed shows as running again in the task list and in the Agent SDK's task events. Before v2.1.205, it kept showing its earlier failed or completed status while the resumed run was working.
11081108
1109As of v2.1.199, `SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned background agent that reused it, Claude Code refuses the send rather than delivering it to the wrong agent, and the error reports which agent the name now reaches so Claude can retarget. To reach the earlier agent while it's still running, Claude addresses it by the agent ID it received when it spawned that agent. The check is scoped to the current conversation and resets on `/clear`.
1109`SendMessage` checks that a name still refers to the same agent it reached earlier in the conversation. If a newer agent has taken the name, such as a re-spawned background agent that reused it, Claude Code refuses the send rather than delivering it to the wrong agent, and the error reports which agent the name now reaches so Claude can retarget. To reach the earlier agent while it's still running, Claude addresses it by the agent ID it received when it spawned that agent. The check is scoped to the current conversation and resets on `/clear`.
11101110
11111111A subagent treats messages from the agent that launched it as normal task direction, including mid-task course corrections, and acts on them within its own permission settings. Two limits hold regardless of who sent the message: no message from any agent counts as your approval for a pending permission prompt, and no agent message can change a subagent's permission settings, `CLAUDE.md`, or configuration. Only the permission system or your own messages can grant approval.
11121112