One read of Claude Code CLIclaude-code-20261001T233701Z
16 pages moved out of 220 read.
Pages moved
16
significant first
Pages read
220
in this capture
Captured
23:37 UTC
Corpus hash
82e961195f35
corpus-hash
What this read moved
1-16 of 16agent-teams Changed · +6 / -3 lines
from line 173
173173* **In-process mode**: use the up and down arrow keys in the agent panel to select a teammate, then press Enter to view its session and type to send it a message. Press `x` on a selected teammate to stop it. Press Ctrl+T to toggle the task list.
174174* **Split-pane mode**: click into a teammate's pane to interact with their session directly. Each teammate has a full view of their own terminal.
175175
176While you're viewing an in-process teammate, plain text and [skills](/docs/en/skills) go to that teammate, but built-in commands still run in the lead's session.
176While you're viewing an in-process teammate, plain text and [skills](/docs/en/skills) go to that teammate, and built-in commands go to the lead's session, with these safeguards:
177177
178A teammate's model and fast mode are fixed when it spawns, so `/model` and `/fast` only change the lead's settings. As of v2.1.199, typing either command while viewing a teammate shows a notice that the change applies to the lead; earlier versions applied it to the lead with no indication. `/effort` still applies to the viewed teammate's later turns, because teammates follow the lead's [effort level](/docs/en/model-config#adjust-effort-level).
178* `/compact`, `/clear`, and `/rewind` act on the lead's conversation, so Claude Code asks you to confirm before running one of them from this view.
179* `/model` and `/fast` set the lead's model and fast mode, not the teammate's, so they don't run from this view. A notice tells you why.
180
181A teammate's model and fast mode are fixed when it spawns. `/effort` still applies to the viewed teammate's later turns, because teammates follow the lead's [effort level](/docs/en/model-config#adjust-effort-level).
179182
180183### Assign and claim tasks
181184
agent-view Changed · +26 / -6 lines
from line 206
206206
207207Most of the time the peek panel is enough and you don't need to open the full transcript.
208208
209Type a reply in the peek panel and press `Enter` to send it to that session. When the session asks a question with predefined choices, the peek panel shows them as a numbered list and you can press a number key to pick one. A permission prompt shows as text describing what the session wants to run, without numbered options. Type a reply to answer it, or attach to answer with the standard prompt. For other blocked sessions, press `Tab` to fill the input with a suggested reply you can edit before sending. Prefix a reply with `!` to send a Bash command instead.
209Type a reply in the peek panel and press `Enter` to send it to that session. Prefix a reply with `!` to send a Bash command instead. What happens to the reply depends on the session and on what you send:
210210
211* A session that's working: the reply joins the session's [message queue](/docs/en/interactive-mode#queue-messages-while-claude-works) instead of interrupting the response, and takes effect [when queued input does](/docs/en/interactive-mode#when-claude-code-sends-what-you-queued). A [command](/docs/en/commands) waits for the turn to end, even one that runs as soon as you type it at a session's own prompt
212* A reply that is exactly `/stop`: stops the session at once instead of being delivered to it, whether the session is working or waiting on you
213* A [shell job](#run-a-shell-command): the reply, `/stop` included, goes to the command's terminal as typed input
214
215When the session is waiting on you, how you answer from the peek panel depends on what it's waiting for:
216
217* A question with predefined choices: the panel lists the choices by number. With the reply input empty, press a choice's number to fill it in, then `Enter` to send it, or type your own answer instead
218* A question without predefined choices: type your answer. When the empty input shows a suggested reply, press `Tab` to fill it in and edit it before sending
219* A permission prompt or another dialog, such as a [sandbox](/docs/en/sandboxing) prompt or an MCP server's [request for input](/docs/en/mcp#respond-to-mcp-elicitation-requests): replying doesn't answer it. Your reply waits in the queue. To answer the dialog, attach with `→`
220
211221When a [`PermissionRequest`](/docs/en/hooks#permissionrequest) or [`PreToolUse`](/docs/en/hooks#pretooluse) hook returns output Claude Code can't validate for the call the session is asking about, the row shows the hook event and `hook output invalid:` with the validation error before the pending request's text. For a hook that fails another way, the row says the hook failed. The session still waits on the same request.
212222
213223A reply that can't be delivered, because the background service is unreachable or the send fails, is saved and sent to the session as its next prompt when its process starts again, and the error message says the reply was saved. A reply prefixed with `!` isn't saved, because the saved text would reach the session as a plain prompt rather than run as a Bash command.
from line 287
277287* Press `Ctrl+T` to pin a session to the top and [keep its process running](#the-supervisor-process) while idle
278288* Press `Shift+↑` or `Shift+↓` to reorder sessions
279289* Press `Ctrl+R` to rename a session
280* Press `Enter` on a group header to collapse it
290* Press `Enter` on a group header to collapse it, except while a [filter](#filter-sessions) is active, when every group stays expanded
281291
282292To remove a session from the list, press `Ctrl+X` to stop it and `Ctrl+X` again within two seconds to delete it. Pressing `Ctrl+X` on a group header deletes every session in that group after confirmation.
283293
from line 308
298308
299309### Filter sessions
300310
301Type in the dispatch input to filter instead of dispatching:
311Start the dispatch input with one of these filters to narrow the list as you type:
302312
303313| Filter | Shows |
304314| :- | :- |
305315| `a:<name>` | Sessions running the named agent |
306| `s:<state>` | Sessions in the given state, such as `s:working`. Also accepts `s:blocked` for everything waiting on you |
307| `#<number>` or a pull or merge request URL | The session working on that pull request or merge request |
316| `s:<state>` | Sessions in the given state, such as `s:working`, or under the given group header, such as `s:ready` for `Ready for review`. `s:blocked` lists everything waiting on you |
317| `n:<text>` | Sessions whose name or first prompt contains the text, such as `n:login`. Requires Claude Code v2.1.287 or later |
318| `o:<text>` | Sessions whose result contains the text, such as `o:merged`. A bare `o:` lists every session that has reported a result |
319| A pull or merge request number, such as `#1234`, or its URL | The session working on that pull request or merge request |
308320| Any other URL | The session whose first prompt contained that URL |
309321
322To combine filters, start with `a:`, `s:`, `n:`, or `o:` and add more, separated by spaces. The list shows the sessions that match all of them. For example, `s:blocked a:reviewer` lists the `reviewer` sessions that are waiting on you.
323
324While a filter is active, groups you collapsed expand to show their matches and the first match is selected, so pressing `Enter` opens it. Clear the input to remove the filter, and those groups collapse again.
325
310326### Keyboard shortcuts
311327
312328Press `?` in agent view to see every shortcut in context. The table below summarizes them.
from line 330
314330| Shortcut | Action |
315331| :- | :- |
316332| `↑` / `↓` | Move between rows |
317| `Enter` | Attach to the selected session, or dispatch if there's text in the input |
333| `PgUp` / `PgDn` | Move up or down by a screenful of rows |
334| `Home` / `End` | Jump to the first or last row |
335| `Enter` | Attach to the selected session, or submit the input's text if it isn't a [filter](#filter-sessions) |
318336| `Space` | Open or close the peek panel for the selected session |
319337| `Shift+Enter` | Insert a newline in the dispatch input, [as in the main prompt](/docs/en/terminal-config#enter-multiline-prompts) |
320338| `Ctrl+Enter` | Dispatch and attach immediately, in terminals where the `?` overlay lists `ctrl+enter to start and open` |
from line 970
952970
953971| Version | Change |
954972| - | - |
973| v2.1.287 | The [`n:<text>` filter](#filter-sessions) finds sessions by name or first prompt. While any filter is active, groups you collapsed expand to show their matches and the first match is selected, so `Enter` opens it. |
974| v2.1.287 | A command sent as a [peek reply](#peek-and-reply) runs when the session's current turn ends, including the commands that run as soon as you type them at a session's own prompt. A reply that is exactly `/stop` stops the session at once. |
955975| v2.1.281 | A [`--setting-sources`](/docs/en/cli-reference#cli-flags) restriction [carries over](#what-carries-over-when-you-background) to a session you background with `←` or `/bg` and to the sessions you dispatch from agent view. Before this release, the spawned session loaded every settings source. |
956976| v2.1.281 | `claude --bg`, and the commands that restart a session, check workspace trust for the session's directory first. From a terminal in that directory, [the trust dialog appears](#from-your-shell) if you haven't accepted it; where no dialog can appear, such as in a script, the command exits with a [`Workspace not trusted`](/docs/en/errors#workspace-not-trusted-when-dispatching-a-background-session) error. |
957977| v2.1.274 | After an auto-update, an agent view you've been away from for about an hour can relaunch itself onto the new build. When it does, it keeps the [dispatch defaults](#dispatch-defaults) you opened it with: `--model`, `--effort`, `--permission-mode`, `--allow-dangerously-skip-permissions`, and `--agent`. Before this release, the relaunched view kept only `--cwd` and configuration flags such as `--settings` and `--mcp-config`, so sessions you dispatched afterward started without those defaults. |
headless Changed · +8 / -0 lines
from line 54
5454| Custom agents | `--agents <json>` |
5555| A plugin | `--plugin-dir <path>`, `--plugin-url <url>` |
5656
57Bare mode also limits what happens while the session runs:
58
59* **MCP servers**: only servers supplied on the command line connect, for example with `--mcp-config`. In an interactive session, Claude Code also skips the automatic IDE connection unless you pass `--ide`.
60* **System reminders**: Claude gets your prompts and the tool results without the [system reminders](/docs/en/glossary#system-reminder) Claude Code would add alongside them. For example, Claude isn't told when a file it read earlier changes on disk, and it doesn't get the list of available skills, including skills from an `--add-dir` folder.
61* **Background tasks**: none run. A command that reaches its [timeout](/docs/en/tools-reference#timeout-and-output-limits) stops instead of [moving to the background](/docs/en/tools-reference#background-commands).
62
63Before v2.1.286, these limits held only partly: an interactive `--bare` session connected the MCP servers that a normal session would, every `--bare` session sent system reminders, and background tasks stayed available.
64
5765<Note>
5866 `--bare` is the recommended mode for scripted and SDK calls, and will become the default for `-p` in a future release.
5967</Note>
remote-control Changed · +17 / -1 lines
### "Remote Control is disabled by your organization's policy"
from line 335
335335* **Extended network outage**: if your machine is awake but can't reach the network, what you do next depends on the mode:
336336 * **Server mode**: Claude Code gives up after roughly 10 minutes and the `claude remote-control` process exits. Run `claude remote-control` again to start a new session.
337337 * **Interactive session**: keep working locally. Claude Code retries for as long as the outage lasts and reconnects on its own when the network returns.
338* **Attachments that don't download**: if a file you attach from your phone or browser can't be downloaded to your machine, Claude still receives your message and the files that were downloaded. In place of the missing files, Claude Code adds a note such as `[1 of 3 attachments did not arrive]` to the message.
338339* **Presence heartbeats failing**: if an interactive session disconnects with `could not reach the Remote Control server for about 30 minutes`, run `/remote-control` to reconnect.
339340* **Forwarded dialogs expire**: Claude Code keeps permission prompts and `AskUserQuestion` questions open until you answer them. When Claude Code forwards another kind of dialog to the remote session, such as the model-choice prompt shown after a safety refusal, it waits five minutes by default, then closes the dialog and continues with the dialog's no-action default. Set [`dialogExpiry`](/docs/en/settings-reference#dialogexpiry) to adjust or disable the deadline. Requires Claude Code v2.1.224 or later.
340341* **The Fable usage-credits consent prompt isn't forwarded**: Claude Code shows the mid-session [Fable usage-credits consent prompt](/docs/en/model-config#fable-and-usage-credits) only where the session runs, not on your device. When the session runs in a terminal and nobody there answers before Claude Code closes the prompt, the turn ends without sending the request; see [The prompt to confirm went unanswered](/docs/en/errors#the-prompt-to-confirm-went-unanswered).
from line 395
394395
395396The message names what routed the session away from the Anthropic API, such as `CLAUDE_CODE_USE_BEDROCK` or a custom `ANTHROPIC_BASE_URL`. If you have an eligible claude.ai login, unset the named variable, remove it from the `env` key in [settings](/docs/en/settings) if you set it there, and restart the session.
396397
397### "Remote Control is disabled by your organization's policy"
398<h3 id="remote-control-is-disabled-by-your-organizations-policy">
399 "Remote Control is disabled by your organization's policy"
400</h3>
398401
399402A policy blocks Remote Control. Check these causes in order:
400403
from line 407
404407* **Otherwise, an Owner hasn't enabled it for your organization**: Remote Control is off by default on Team and Enterprise plans. An Owner can enable it at [claude.ai/admin-settings/claude-code](https://claude.ai/admin-settings/claude-code) by turning on the **Remote Control** toggle. This toggle is a server-side organization setting.
405408
406409Before v2.1.281, this message also appeared when Claude Code hadn't loaded your organization's policy on this machine, for example after starting offline. Later versions report that state as [`Couldn't verify your organization's policy for remote control`](#couldnt-verify-your-organizations-policy-for-remote-control) instead.
410
411<h3 id="remote-control-was-turned-off-by-your-organizations-policy">
412 "Remote Control was turned off by your organization's policy"
413</h3>
414
415Your organization's policy stopped allowing Remote Control while a session was connected, so Claude Code disconnected it. What happens to the session depends on how you started Remote Control:
416
417* **With `/remote-control`, `claude --remote-control`, or [auto-connect](#enable-remote-control-for-all-sessions)**: the session keeps running without Remote Control, and Claude Code archives it at claude.ai
418* **With `claude remote-control`**: the server stops and archives the sessions it was serving, then exits
419
420You can still find an archived session by [filtering for archived sessions](/docs/en/claude-code-on-the-web#archive-sessions).
421
422Remote Control doesn't reconnect on its own. To turn it back on after your organization allows it again, run `/remote-control` in the session or `claude remote-control` in your shell. Either command fails with [`Remote Control is disabled by your organization's policy`](#remote-control-is-disabled-by-your-organizations-policy) until Claude Code on this machine has fetched the changed policy. An open session fetches it about once an hour. To find out what is blocking Remote Control, match the full text the command prints against that entry.
407423
408424<h3 id="couldnt-verify-your-organizations-policy-for-remote-control">
409425 "Couldn't verify your organization's policy for remote control"
security Changed · +14 / -18 lines
from line 10
1010
1111### Permission-based architecture
1212
13In Manual mode, Claude Code starts with read-only permissions. When Claude Code needs to edit files, run tests, or execute commands, it asks you first, and you choose whether to approve the action once or allow it from then on.
13A session's permission mode sets which actions Claude can take without asking you first. Auto mode is the built-in starting permission mode for interactive terminal and VS Code sessions. [Which mode a session starts in](/docs/en/permission-modes#which-mode-a-session-starts-in) covers earlier versions, other surfaces, and the settings that change the starting permission mode.
1414
15In Manual mode, Claude Code also asks before running Bash commands that can modify your system. It runs a built-in set of [read-only commands](/docs/en/permissions#read-only-commands) such as `ls`, `cat`, and `git status` without asking. You and your organization configure these permissions directly.
15* **Auto mode**: A separate classifier model reviews actions instead of you and blocks the ones it judges unsafe. [How the classifier evaluates actions](/docs/en/permission-modes#how-the-classifier-evaluates-actions) lists which actions Claude Code approves outright, which it sends to the classifier, and which Claude Code still asks you about. Your explicit ask and deny rules still apply, and your organization can [turn auto mode off](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)
16* **Manual mode**: Claude Code starts with read-only permissions. When it needs to edit files, run tests, or execute commands, it asks you first, and you choose whether to approve the action once or allow it from then on. It runs a built-in set of [read-only commands](/docs/en/permissions#read-only-commands) such as `ls`, `cat`, and `git status` without asking
1617
17In [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), a separate classifier model reviews actions instead of you and blocks the ones it judges unsafe. [How the classifier evaluates actions](/docs/en/permission-modes#how-the-classifier-evaluates-actions) lists which actions Claude Code approves outright, which it sends to the classifier, and which Claude Code still asks you about. Your explicit ask and deny rules still apply, and your organization can [turn auto mode off](/docs/en/permission-modes#eliminate-prompts-with-auto-mode).
18You and your organization configure these permissions directly. For detailed permission configuration, see [Permissions](/docs/en/permissions).
1819
19Which permission mode a session starts in depends on your plan, the surface you start it from, and your settings and your organization's; see [Permission modes](/docs/en/permission-modes#which-mode-a-session-starts-in).
20
21For detailed permission configuration, see [Permissions](/docs/en/permissions).
22
2320### Built-in protections
2421
2522To mitigate risks in agentic systems:
2623
2724* **Sandboxed bash tool**: [Sandbox](/docs/en/sandboxing) bash commands with filesystem and network isolation, reducing permission prompts while maintaining security. Configure with `/sandbox` to define boundaries where Claude Code can work autonomously
28* **Working directory boundary**: In Manual mode, Claude Code can only write to the folder where it was started and its subfolders, and can't modify files in parent directories without explicit permission. In Manual mode, Claude Code also asks you before reading paths outside this boundary with the Read, Grep, and Glob tools. Extend the boundary with [additional directories](/docs/en/permissions#working-directories) to skip the prompt, or restrict the broader read access available to read-only Bash commands with [sandbox `denyRead` rules](/docs/en/sandboxing#filesystem-isolation), which apply only when sandboxing is enabled
25* **Working directory boundary**: In Manual mode, Claude Code asks you before its file tools read or write outside the folder where it was started and its subfolders. The boundary is a permission prompt, so a Bash command you approve can still write anywhere your user account can
26 * To read a folder without the prompt, add it as an [additional directory](/docs/en/permissions#working-directories)
27 * To restrict Bash commands at the operating system level, turn on [sandboxing](/docs/en/sandboxing#filesystem-isolation)
2928* **Prompt fatigue mitigation**: Support for allowlisting frequently used safe commands per-user, per-codebase, or per-organization
3029* **Accept Edits mode**: Auto-approves file edits and a fixed set of filesystem Bash commands like `mkdir`, `touch`, `rm`, `mv`, `cp`, and `sed` for paths in the working directory. Other Bash commands and out-of-scope paths still prompt
3130
3231### User responsibility
3332
34Claude Code only has the permissions you grant it. You're responsible for reviewing proposed code and commands for safety before approval.
33You're responsible for reviewing proposed code and commands for safety before approval.
3534
3635## Protect against prompt injection
3736
from line 39
4039### Core protections
4140
4241* **Permission system**: In Manual mode, sensitive operations require explicit approval
43* **Context-aware analysis**: Detects potentially harmful instructions by analyzing the full request
44* **Input sanitization**: Prevents command injection by processing user inputs
4542* **Network command approval**: Commands that fetch content from the web such as `curl` and `wget` are not auto-approved by default. In Manual mode they prompt like any other non-read-only Bash command, so you can still approve once or add an explicit allow rule like `Bash(curl *)`. To stop Claude from running them, add them to [`permissions.deny`](/docs/en/permissions#tool-specific-permission-rules). A deny rule matches the command [as written](/docs/en/permissions#bash-rule-limits); for network enforcement that doesn't depend on the command text, see [sandbox network isolation](/docs/en/sandboxing#network-isolation)
4643
4744### Privacy safeguards
from line 54
5754### Additional safeguards
5855
5956* **Network request approval**: In Manual mode, most tools that make network requests require user approval by default
60* **Isolated context windows**: Web fetch uses a separate context window to avoid injecting potentially malicious prompts
61* **Trust verification**: First-time codebase runs and new MCP servers require trust verification
62 * Note: Trust verification is disabled when running non-interactively with the `-p` flag
57* **Web page summaries**: For most fetches, WebFetch runs a separate model call over the page, and Claude receives that call's answer instead of the raw page. See [WebFetch tool behavior](/docs/en/tools-reference#webfetch-tool-behavior)
58* **Trust verification**: In an interactive session, Claude Code shows the workspace trust dialog when you start it in a folder you haven't trusted. Servers in a project's `.mcp.json` have their own approval prompt, and [Project scope](/docs/en/mcp#project-scope) lists the sessions that skip it
59 * Note: A `-p` session shows neither prompt. [What runs before you trust a folder](/docs/en/permissions#what-runs-before-you-trust-a-folder) lists what a repository's files can run there
6360 * Note: When you start Claude Code directly in your home directory, trust acceptance is held for the current session only and is not written to disk, so the prompt reappears on each launch. There is no setting to persist it. Start Claude Code from a project subdirectory instead, where trust acceptance is saved per directory
64* **Command injection detection**: In Manual mode, suspicious bash commands require manual approval even if previously allowlisted
61* **Command injection detection**: In Manual mode, Claude Code asks before running a Bash command it can't fully analyze. An allow rule for part of a command, such as `Bash(git *)`, doesn't skip that prompt. [Sandboxed commands](/docs/en/permissions#how-permissions-interact-with-sandboxing) can run without it
6562* **Fail-closed matching**: In Manual mode, unmatched commands require approval by default
66* **Natural language descriptions**: Complex bash commands include explanations for user understanding
67* **Secure credential storage**: API keys and tokens are stored in the macOS Keychain when available, and protected by file permissions on Windows and Linux. See [Credential Management](/docs/en/authentication#credential-management)
63* **Secure credential storage**: API keys and tokens are stored in the macOS Keychain when available. On Linux they're stored in a file with mode `0600`, and on Windows in a file that inherits the access controls of your user profile directory. See [Credential Management](/docs/en/authentication#credential-management)
6864
6965<Warning>
7066 **Windows WebDAV security risk**: When running Claude Code on Windows, we recommend against enabling WebDAV or allowing Claude Code to access paths such as `\\*` that may contain WebDAV subdirectories. [WebDAV has been deprecated by Microsoft](https://learn.microsoft.com/en-us/windows/whats-new/deprecated-features#:~:text=The%20Webclient%20\(WebDAV\)%20service%20is%20deprecated) due to security risks. Enabling WebDAV may allow Claude Code to trigger network requests to remote hosts, bypassing the permission system.
from line 82
8682
8783## MCP security
8884
89Claude Code allows users to configure Model Context Protocol (MCP) servers. The list of allowed MCP servers is configured in your source code, as part of Claude Code settings engineers check into source control.
85You can connect Claude Code to Model Context Protocol (MCP) servers. Project-scoped servers are defined in `.mcp.json`, which you can check into source control. Servers at [other scopes](/docs/en/mcp#mcp-installation-scopes) and [claude.ai connectors](/docs/en/mcp#how-connectors-reach-claude-code) are configured outside the repository, and plugins can add servers too, so reviewing `.mcp.json` doesn't show every server a session can load. To restrict which servers run in your organization, see [Managed MCP configuration](/docs/en/managed-mcp).
9086
9187We encourage either writing your own MCP servers or using MCP servers from providers that you trust. You are able to configure Claude Code permissions for MCP servers. Anthropic reviews connectors against its [listing criteria](https://claude.com/docs/connectors/building/review-criteria) before adding them to the [Anthropic Directory](https://claude.ai/directory), but does not security-audit or manage any MCP server.
9288
skills Changed · +8 / -0 lines
### Run your checks before each commit
from line 48
4848
4949Claude edits the recorded file only when it steered a run wrong, such as a command that failed or a missing step, so you can commit the file without per-session diffs. Before v2.1.205, the bundled skill told Claude to fold in anything a run learned, which caused frequent merge conflicts.
5050
51### Run your checks before each commit
52
53When a session starts with a skill named `verify` or `simplify` in place, Claude Code's commit instructions tell Claude to run it right before each commit, except for changes to docs or tests. This requires Claude Code v2.1.286 or later. Claude gets that instruction when these conditions hold at the start of the session:
54
55* **Location**: the skill loads from the enterprise, personal, project, or additional-directory [location](#where-skills-live), or from a `.claude/commands/` file with that name. The recipe that `/verify` records at your repo root is a project skill, so it counts. The bundled `/verify` and `/simplify`, plugin skills, and skills from your claude.ai account don't count.
56* **Invocation**: Claude can invoke the skill. If you've [stopped Claude from invoking it](#control-who-invokes-a-skill), for example with `disable-model-invocation: true`, Claude doesn't get the instruction.
57* **Git instructions**: you haven't turned off [`includeGitInstructions`](/docs/en/settings-reference#includegitinstructions). Turning it off removes this instruction together with the rest of the built-in commit and PR instructions.
58
5159### Work on Claude API projects
5260
5361The bundled `/claude-api` skill loads [Claude API](https://platform.claude.com/docs/en/api/overview) and [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) reference material for your project's language. Claude also activates it automatically when your code imports `anthropic` or `@anthropic-ai/sdk`.
sub-agents Changed · +6 / -1 lines
from line 1167
11671167| `x` | Stop the selected fork if it's running, or dismiss its row if it's no longer running. On the main session row, or on the row of the fork whose transcript you opened with `Enter`, `x` types into the prompt instead |
11681168| `Esc` | Return focus to the prompt input |
11691169
1170With a fork's or subagent's transcript open, follow-up messages and [skills](/docs/en/skills) go to that agent, but built-in commands still run in your main conversation. As of v2.1.199, typing `/model` or `/fast` in that view shows a notice that it changes the main conversation's model or fast mode, not the viewed agent's, instead of running it silently.
1170With a fork's or subagent's transcript open, follow-up messages and [skills](/docs/en/skills) go to that agent, and built-in commands go to your main conversation, with these safeguards:
1171
1172* `/compact`, `/clear`, and `/rewind` act on the main conversation, so Claude Code asks you to confirm before running one of them from this view.
1173* `/model` and `/fast` set the main conversation's model and fast mode, not the viewed agent's, so they don't run from this view. A notice tells you why.
1174
1175To have the viewed agent read your message before the work it's waiting on finishes, send it with [`Ctrl+Enter` or `Ctrl+X Ctrl+S`](/docs/en/keybindings#chat-actions). Any shell command or subagent the agent is waiting on that can move to the [background](/docs/en/tools-reference#background-commands) moves there and keeps running. When the agent is writing a response, or waiting on work that can't move to the background, it keeps going and reads your message once that finishes. Requires Claude Code v2.1.286 or later.
11711176
11721177### How forks differ from other subagents
11731178
ultrareview Changed · +6 / -6 lines
from line 133
133133
134134## Track a running review
135135
136A review typically takes 5 to 10 minutes. The review runs as a background task, so you can keep working in your session, start other commands, or close the terminal entirely. If you chose to [post the findings to the pull request](#post-findings-to-the-pull-request), keep the session open until the review finishes; if the session ends first, Claude Code posts nothing.
136A review typically takes 5 to 10 minutes. The review runs as a background task, so you can keep working in your session or start other commands. If you chose to [post the findings to the pull request](#post-findings-to-the-pull-request), keep the session open until the review finishes; if the session ends first, Claude Code posts nothing.
137137
138138Use `/tasks` to see running and completed reviews, open the detail view for a review, or stop a review that is in progress. If you stop a review, Claude Code archives the cloud session and doesn't return partial findings.
139139
from line 159
159159
160160You consent to the whole-repository fallback and to the billing and terms prompt when you run the subcommand, so the run starts without waiting for input. Running it yourself is what counts as consent. When Claude runs the subcommand for you instead, for example through the Bash tool, Claude Code refuses the whole-repository review.
161161
162On Claude Code v2.1.218 or later, you can also start the cloud review by running `/code-review ultra` in a non-interactive session, for example `claude -p '/code-review ultra'`. Claude Code launches the review and prints a tracking link without waiting for the findings, unlike `claude ultrareview`, which blocks until they arrive. When the review would bill usage credits, Claude Code stops before launching and points you to `claude ultrareview`, because the billing confirmation needs an interactive session. Before v2.1.218, `/code-review ultra` in a non-interactive session ran a local review.
162`claude -p '/code-review ultra'` doesn't get you the findings, so use `claude ultrareview` in scripts. The `-p` run launches the cloud review and exits without waiting for it. When the review would bill usage credits, the `-p` run stops without launching it. Before v2.1.218, `/code-review ultra` in a non-interactive session ran a local review.
163163
164Progress messages and the live session URL go to stderr so stdout stays parseable. Use these flags to control the output, the timeout, and whether to post the findings:
164`claude ultrareview` writes its progress messages to stderr so stdout stays parseable. Use these flags to control its output, the timeout, and whether to post the findings:
165165
166166| Flag | Description |
167167| - | - |
from line 178
178178* **1**: the review failed to launch or was stopped before it finished, the cloud session errored, or the timeout elapsed
179179* **130**: you interrupted the subcommand with Ctrl-C
180180
181If you interrupt the subcommand, the remote review keeps running; follow the session URL printed to stderr to watch it in the browser.
181If the subcommand exits before the findings arrive, they never reach your terminal, and running it again starts a new review rather than resuming that one. The new review [counts as a run](#pricing-and-free-runs) of its own.
182182
183183With `--post`, the subcommand starts the post right after printing the findings, and prints the link to stderr.
184184
185* If the run fails, is stopped, or times out, or if you interrupt it, the subcommand posts nothing.
185* If the run fails, is stopped, or times out, the subcommand posts nothing.
186186* If the review completes but the comment isn't posted, Claude Code prints the reason to stderr, and the findings stay on stdout so you can post them by hand.
187187
188188For automatic reviews on GitHub pull requests, [Code Review](/docs/en/code-review) integrates with your repository directly and posts findings as inline PR comments without a CLI step.
agent-sdk/hooks Changed · +1 / -1 lines
from line 243
243243
244244* **Top-level fields** are accepted on every event: `systemMessage` shows a message to the user, and `continue` (`continue_` in Python) determines whether the agent keeps running after this hook. Some events discard them or deliver them elsewhere. Each [event's section](/docs/en/hooks#hook-events) on the hooks page says where they land.
245245* **`hookSpecificOutput`** controls the current operation. The fields you set inside depend on the hook event type:
246 * For `PreToolUse` hooks, this is where you set `permissionDecision` (`"allow"`, `"deny"`, `"ask"`, or `"defer"`), `permissionDecisionReason`, and `updatedInput`. If you return `"defer"`, the query ends so you can [resume it later](/docs/en/hooks#defer-a-tool-call-for-later).
246 * For `PreToolUse` hooks, this is where you set `permissionDecision` (`"allow"`, `"deny"`, `"ask"`, or `"defer"`), `permissionDecisionReason`, and `updatedInput`. If you return `"defer"`, the turn ends with a result message whose `stop_reason` is `"tool_deferred"`, so you can [resume the call later](/docs/en/hooks#defer-a-tool-call-for-later).
247247 * For `PostToolUse` hooks, you can set `additionalContext` to append information to the tool result. To replace the tool's output before Claude sees it, set `updatedToolOutput`, which works for any tool in both SDKs. The older `updatedMCPToolOutput` field replaces MCP tool output only and is deprecated.
248248 * In the TypeScript SDK, a `PostToolUse` callback can also return `classifierContext`, a short note about the tool call's result for the [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) permission classifier. Because your callback runs in your application's own process, the classifier may weigh a user statement you relay in the note as user intent. The field requires TypeScript Agent SDK v0.3.236 or later. [Annotate a result for the auto mode classifier](/docs/en/hooks#annotate-a-result-for-the-auto-mode-classifier) covers the length cap, the synchronous-only rule, and what not to put in the note.
249249
agent-sdk/typescript 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 1602
16021602Claude Code echoes the answered message's `uuid` on three kinds of frame:
16031603
16041604* **The result**: every result of a turn that answered a message you sent. Every such result carries it on Agent SDK v0.3.265 or later. Before v0.3.265, the success result of a turn that a regular message started lacked it when the turn sent no API request or ended with a deferred tool call. Before v0.3.246, error results lacked it too, and before v0.3.216 every result did.
1605* **The turn's first reply**: the first [assistant message](#sdkassistantmessage), or with `includePartialMessages` the first [stream event](#sdkpartialassistantmessage) whose `event.type` isn't `ping`, so you can bind the reply before the result arrives. When a turn streams nothing, Claude Code sets it on the first assistant message instead. The first-reply echo requires Agent SDK v0.3.246 or later. When the message the turn is answering changes mid-turn, the first reply after the change carries the field too, on Agent SDK v0.3.265 or later; earlier versions set it on one reply frame per turn.
1605* **The turn's first reply**: the first [assistant message](#sdkassistantmessage), and with `includePartialMessages` also the first [stream event](#sdkpartialassistantmessage) whose `event.type` isn't `ping`, so you can bind the reply before the result arrives. The first-reply echo requires Agent SDK v0.3.246 or later. Before v0.3.269, with `includePartialMessages`, Claude Code set it on that first stream event only, or on the first assistant message when the turn streamed nothing. When the message the turn is answering changes mid-turn, the first reply after the change carries the field too, on Agent SDK v0.3.265 or later; earlier versions set it on one reply frame per turn.
16061606* **Every [`thinking_tokens`](#sdkthinkingtokensmessage) frame of the turn**: so you can attribute thinking progress to the message you sent without waiting for the turn's first reply. Requires Agent SDK v0.3.260 or later.
16071607
16081608Claude Code omits the field in these cases:
from line 5454
54545454| `network` | [`SandboxNetworkConfig`](#sandboxnetworkconfig) | `undefined` | Network-specific sandbox configuration |
54555455| `filesystem` | [`SandboxFilesystemConfig`](#sandboxfilesystemconfig) | `undefined` | Filesystem-specific sandbox configuration for read/write restrictions |
54565456| `ignoreViolations` | `Record<string, string[]>` | `undefined` | Map of command substrings, or `*` for every command, to substrings of the violation text to ignore, such as `{ "*": ['/etc/hosts'] }`; see [`sandbox.ignoreViolations`](/docs/en/settings-reference#sandbox-ignoreviolations) |
5457| `enableWeakerNestedSandbox` | `boolean` | `false` | Enable a weaker nested sandbox for compatibility |
5458| `ripg
5457| `enableWeakerNestedSandbox`
claude-tag 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.
Nothing in the body moved in this read. What changed is above.
code-review Changed · +1 / -3 lines
from line 379
379379 Ultrareview requires authentication with a claude.ai account and is not available on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry, or to organizations with Zero Data Retention enabled. When ultrareview is not available, `/code-review ultra` runs a local review in your session instead.
380380</Note>
381381
382To start a cloud review from a script or CI, run `claude -p '/code-review ultra'`. Claude Code launches the review and prints a link for tracking it. Requires Claude Code v2.1.218 or later.
383
384When the review would bill [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans), Claude Code stops before launching, because the billing confirmation needs an interactive session. Run the [`claude ultrareview` subcommand](/docs/en/ultrareview#run-ultrareview-non-interactively) instead; by running it, you consent to the charge.
382To run a cloud review from a script or CI job, use the [`claude ultrareview` subcommand](/docs/en/ultrareview#run-ultrareview-non-interactively), which waits for the findings and prints them to stdout.
385383
386384The command was named `/simplify` before v2.1.147, when it applied fixes by default. `/simplify` runs a separate cleanup-only review that applies fixes without hunting for bugs. If you scripted `/simplify` for bug-finding, switch to `/code-review --fix`.
387385
errors Changed · +2 / -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 69
6969| `Remote Control stopped — the app running this session is now signed in to a different Claude account` | [Authentication](#remote-control-stopped-because-the-app-running-the-session-signed-out-or-switched-accounts) |
7070| `Remote Control stopped — the app running this session is signed out of Claude` | [Authentication](#remote-control-stopped-because-the-app-running-the-session-signed-out-or-switched-accounts) |
7171| `Couldn't verify your organization's policy for remote control` | [Troubleshoot Remote Control](/docs/en/remote-control#couldnt-verify-your-organizations-policy-for-remote-control) |
72| `Remote Control is disabled by your organization's policy` | [Troubleshoot Remote Control](/docs/en/remote-control#remote-control-is-disabled-by-your-organizations-policy) |
73| `Remote Control was turned off by your organization's policy` | [Troubleshoot Remote Control](/docs/en/remote-control#remote-control-was-turned-off-by-your-organizations-policy) |
7274| `OAuth token revoked` / `OAuth token has expired` | [Authentication](#oauth-token-revoked-or-expired) |
7375| `API Error: 401 Invalid authentication credentials` | [Authentication](#api-error-401-invalid-authentication-credentials) |
7476| `Login expired · Please run /login` | [Authentication](#login-expired) |
from line 2828
28262828
28272829When Claude Code can't read the working directory for a different reason, such as a permissions change, the message names the error code instead: `Can't read the current directory (EACCES). Start Claude Code from a different directory.`
28282830
2829On macOS, `EPERM` for a directory in `~/Desktop`, `~/Documents`, `~/Downloads`, or iCloud Drive usually means macOS is blocking your terminal app from that folder. Other commands that read that folder fail the same way: `ls` there reports `Operation not permitted`, even with `sudo`.
2830
2831**What to do:**
2832
2833* Change to a directory that exists, such as your home or project directory, then run `claude` again
2834* If the direct
2831On macOS, `EPERM` for a directory in `~/Desktop`, `~/Documen
fullscreen Changed · +2 / -0 lines
from line 93
9393* **Click a setting's value in the `/config` panel** to change it, and scroll the settings list with the mouse wheel. Requires Claude Code v2.1.271 or later.
9494* **Scroll a select or multi-select menu with the mouse wheel** when it has more options than it shows at once, such as the `/model` list in a short terminal window. The wheel scrolls the list while the pointer is over its options. Requires Claude Code v2.1.280 or later.
9595* **Scroll an overflowing list with its scrollbar.** In list panels such as `/skills`, `/mcp`, and `/plugin`'s Installed list, a scrollbar appears beside a list with more rows than fit while the pointer is over it. Click the track to jump to that point, or drag the thumb. Requires Claude Code v2.1.281 or later.
96 * Where the bar has `↑` and `↓` arrows at its ends, click an arrow to scroll a single row, or hold it to keep scrolling. The arrows require Claude Code v2.1.286 or later.
97* **Click the `↑ N more` or `↓ N more` row at the edge of a list** to jump to that end of the list without choosing an option. Requires Claude Code v2.1.286 or later.
9698* **Click a collapsed tool result** to expand it and see the full output. Click again to collapse. The tool call and its result expand together. Only messages that have more to show are clickable.
9799 * Clicking also expands the output of a `!` shell command, whether an older truncated result or the live progress row while the command runs. Requires Claude Code v2.1.257 or later.
98100 * Clicking also expands a dim `Message from @<sender>` line when the sender is a [teammate](/docs/en/agent-teams) or another agent running in your session. The line for a message from [one of your other sessions](/docs/en/cross-session-messaging#what-a-message-looks-like) also shows the message's first line and isn't clickable, so press `Ctrl+o` to read that one.
managed-settings Changed · +3 / -1 lines
from line 430
430430| [`wslInheritsWindowsSettings`](/docs/en/settings-reference#wslinheritswindowssettings) | When set in the HKLM registry or a file under `C:\Program Files\ClaudeCode`, have WSL read the Windows policy chain, and read `/etc/claude-code` only when [no Windows admin document is present](#present-admin-documents); the entry gives the order |
431431
432432<Note>
433 On Team and Enterprise plans, an Owner enables or disables [Remote Control](/docs/en/remote-control) and [cloud sessions](/docs/en/claude-code-on-the-web) organization-wide in [Claude Code admin settings](https://claude.ai/admin-settings/claude-code). Remote Control can additionally be disabled per device with the [`disableRemoteControl`](/docs/en/settings-reference#disableremotecontrol) setting. Cloud sessions have no per-device managed settings key.
433 On Team and Enterprise plans, an Owner enables or disables [Remote Control](/docs/en/remote-control) and [cloud sessions](/docs/en/claude-code-on-the-web) organization-wide in [Claude Code admin settings](https://claude.ai/admin-settings/claude-code). When an Owner turns Remote Control off, already-connected sessions that run Claude Code v2.1.286 or later disconnect too. Each one disconnects the next time it refreshes your organization's policy, about once an hour. For what happens in those sessions, see [`Remote Control was turned off by your organization's policy`](/docs/en/remote-control#remote-control-was-turned-off-by-your-organizations-policy).
434
435 Remote Control can additionally be disabled per device with the [`disableRemoteControl`](/docs/en/settings-reference#disableremotecontrol) setting. Cloud sessions have no per-device managed settings key.
434436
435437 To check whether these organization settings reached a given machine, run `claude doctor` there and read the `Organization policy` line, which says where Claude Code loaded the policy from or why it didn't load. Requires Claude Code v2.1.261 or later. In a running session, `/status` shows the same line when the policy didn't load.
436438</Note>
tools-reference Changed · +1 / -1 lines
from line 201
201201
202202When a foreground command reaches its timeout without finishing, Claude Code moves it to the background instead of stopping it, unless the command starts with `sleep`. A moved command's [time limit](#time-limit-for-background-commands) counts from the move, and a foreground subagent's moved command still stops when that subagent's run ends.
203203
204Setting [`CLAUDE_CODE_DISABLE_BACKGROUND_TASKS=1`](/docs/en/env-vars#variables) disables auto-backgrounding along with the rest of the background task functionality.
204Setting [`CLAUDE_CODE_DISABLE_BACKGROUND_TASKS=1`](/docs/en/env-vars#variables) or running in [bare mode](/docs/en/headless#start-faster-with-bare-mode) disables auto-backgrounding along with the rest of the background task functionality, so a command that reaches its timeout stops instead.
205205
206206The result of a command moved to the background states what happened:
207207