One read of Claude Code CLIclaude-code-20260926T030701Z
18 pages moved out of 210 read.
Pages moved
18
significant first
Pages read
210
in this capture
Captured
03:07 UTC
Corpus hash
ce8a2972a698
corpus-hash
What this read moved
1-18 of 18agent-sdk/permissions Changed · +6 / -2 lines
from line 35
3535 </Step>
3636
3737 <Step title="Allow rules">
38 Check `allow` rules (from `allowed_tools` and settings.json). If a rule matches, the tool is approved. A call the tool approves on its own is resolved at this step too, with no rule needed: for example a file read inside your working directories or a [read-only Bash command](/docs/en/permissions#read-only-commands). `rm` and `rmdir` removals targeting a [critical path](/docs/en/permission-modes#critical-paths) are never approved by an allow rule: they reach your callback in the modes that prompt, go to the [classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) in `auto` mode on Claude Code v2.1.218 or later, and are denied in `dontAsk` mode.
38 Check `allow` rules (from `allowed_tools` and settings.json). If a rule matches, the tool is approved. A call the tool approves on its own is resolved at this step too, with no rule needed: for example a file read inside your working directories or a [read-only Bash command](/docs/en/permissions#read-only-commands).
39
40 `rm` and `rmdir` removals targeting a [critical path](/docs/en/permission-modes#critical-paths) are never approved by an allow rule. Whether they then reach your callback depends on the permission mode: in an Agent SDK session in `auto` mode, for example, Claude Code denies them by default without calling it. The [Critical paths](/docs/en/permission-modes#critical-paths) mode table lists what each mode does with them.
3941 </Step>
4042
4143 <Step title="canUseTool callback">
from line 83
8183Use `//path` for an absolute filesystem path: a deny rule of `Edit(//secrets/**)` blocks writes anywhere under `/secrets` on disk. With a single leading slash, `Edit(/secrets/**)` anchors at the rule's source instead. For rules passed through `allowed_tools` or `disallowed_tools`, that means the session's working directory, so the rule doesn't block `/secrets` on disk. See [Read and Edit rules](/docs/en/permissions#read-and-edit) for the four anchor forms and how rules from settings files resolve.
8284
8385<Warning>
84 **Auto-approved tools never reach `canUseTool`.** A tool call approved at any earlier step, by `acceptEdits` or `bypassPermissions`, or by an allow rule, skips your `canUseTool` callback, so permission checks you put there are silently bypassed for that tool. `AskUserQuestion`, MCP tools marked [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool), connector tools [your organization set to `ask`](/docs/en/mcp#organization-controls-on-connector-tools), and `rm` and `rmdir` removals targeting a [critical path](/docs/en/permission-modes#critical-paths) still reach the callback, even when an allow rule matches. In `auto` mode, critical-path removals go to the [classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) instead of the callback, while the other calls listed here still reach it; the classifier routing requires Claude Code v2.1.218 or later. In `dontAsk` mode these calls are denied instead, without invoking the callback.
86 **Auto-approved tools never reach `canUseTool`.** A tool call approved at any earlier step, by `acceptEdits` or `bypassPermissions`, or by an allow rule, skips your `canUseTool` callback, so permission checks you put there are silently bypassed for that tool.
87
88 An allow rule never auto-approves `AskUserQuestion`, MCP tools marked [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool), connector tools [your organization set to `ask`](/docs/en/mcp#organization-controls-on-connector-tools), or `rm` and `rmdir` removals targeting a [critical path](/docs/en/permission-modes#critical-paths). In `dontAsk` mode Claude Code denies these calls without invoking the callback. In other modes the first three reach the callback. Depending on the [permission mode](/docs/en/permission-modes#critical-paths), a critical-path removal reaches the callback too or Claude Code denies it without calling it, as it does by default for an Agent SDK session in `auto` mode.
8589
8690 Coverage depends on the entry's form: a bare name like `Read` or `mcp__github__get_issue` auto-approves every call to that tool apart from the exceptions above, while a scoped rule like `Bash(npm test *)` auto-approves only matching calls, and other `Bash` calls that need approval still fall through to the callback. For checks that must run on every tool call, use a [`PreToolUse` hook](/docs/en/agent-sdk/hooks): hooks run before every other step, and a hook deny applies even in `bypassPermissions` mode.
8791</Warning>
agents Changed · +7 / -7 lines
from line 4
44
55Claude Code has five ways to work on several tasks at once: [subagents](/docs/en/sub-agents), [agent view](/docs/en/agent-view), [agent teams](/docs/en/agent-teams), [dynamic workflows](/docs/en/workflows), and [projects](/docs/en/claude-projects). They differ in how involved you stay, from steering each conversation yourself to letting Claude coordinate a group of workers, and in whether the work runs on your machine or in the cloud.
66
7| Approach | What it gives you | Use it when |
8| :--------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
9| [Subagents](/docs/en/sub-agents) | Delegated workers inside one session that do a side task in their own context and return a summary | A side task would flood your main conversation with search results, logs, or file contents you won't reference again |
10| [Agent view](/docs/en/agent-view) | One screen to dispatch and monitor sessions running in the background, opened with `claude agents`. Research preview | You have several independent tasks and want to hand them off, check status at a glance, and step in only when one needs you |
11| [Agent teams](/docs/en/agent-teams) | Multiple coordinated sessions with a shared task list and inter-agent messaging, managed by a lead. Experimental and disabled by default | You want Claude to split a project into pieces, assign them, and keep the workers in sync |
12| [Projects](/docs/en/claude-projects) | One ongoing conversation at claude.ai/code or in the desktop app. Claude starts parallel cloud sessions called threads, gives each one the project's repositories, instructions, and memory, and shows you which ones need you. Public beta on Pro and Max | The work spans many tasks over days or weeks, should keep running when your machine is off, and you'd rather describe it once than dispatch and track each session |
13| [Dynamic workflows](/docs/en/workflows) | A script that runs many subagents and cross-checks their results, for work too big to coordinate one turn at a time or that needs more than a single pass | A job outgrows a handful of subagents, or you want findings verified against each other: a codebase-wide audit, a 500-file migration, cross-checked research, or a plan drafted from several angles |
7| Approach | What it gives you | Use it when |
8| :--------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
9| [Subagents](/docs/en/sub-agents) | Delegated workers inside one session that do a side task in their own context and return a summary | A side task would flood your main conversation with search results, logs, or file contents you won't reference again |
10| [Agent view](/docs/en/agent-view) | One screen to dispatch and monitor sessions running in the background, opened with `claude agents`. Research preview | You have several independent tasks and want to hand them off, check status at a glance, and step in only when one needs you |
11| [Agent teams](/docs/en/agent-teams) | Multiple coordinated sessions with a shared task list and inter-agent messaging, managed by a lead. Experimental and disabled by default | You want Claude to split a project into pieces, assign them, and keep the workers in sync |
12| [Projects](/docs/en/claude-projects) | One ongoing conversation at claude.ai/code or in the desktop app. Claude starts parallel sessions called threads, in the cloud or, when you ask, on your computer through Remote Control, gives each one the project's instructions, and shows you which ones need you. Public beta on Pro and Max | The work spans many tasks over days or weeks, should keep running when your machine is off, and you'd rather describe it once than dispatch and track each session |
13| [Dynamic workflows](/docs/en/workflows) | A script that runs many subagents and cross-checks their results, for work too big to coordinate one turn at a time or that needs more than a single pass | A job outgrows a handful of subagents, or you want findings verified against each other: a codebase-wide audit, a 500-file migration, cross-checked research, or a plan drafted from several angles |
1414
1515In every approach the workers are Claude sessions. To involve a different tool, expose it to Claude as an [MCP server](/docs/en/mcp).
1616
best-practices Changed · +3 / -3 lines
from line 191
191191 To get fewer prompts without giving up control, pre-approve the tools you trust with `/permissions` and let sandboxed commands run without asking with `/sandbox`. Switch to Manual mode when you want to approve edits and commands yourself.
192192</Tip>
193193
194On Pro, Max, and Team plans, auto mode is the [built-in starting permission mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for interactive terminal and VS Code sessions: a separate classifier model reviews most actions instead of you and blocks only what looks risky, such as scope escalation, unknown infrastructure, or hostile-content-driven actions.
194With Claude Code v2.1.283 or later, auto mode is the [built-in starting permission mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for interactive terminal and VS Code sessions: a separate classifier model reviews most actions instead of you and blocks only what looks risky, such as scope escalation, unknown infrastructure, or hostile-content-driven actions. On earlier versions, auto mode is the built-in starting permission mode only on Pro, Max, and Team plans.
195195
196In Manual mode, the built-in starting permission mode on other plans, Claude Code asks before actions that might modify your system: file writes, Bash commands, MCP tools. That's safe but tedious. After the tenth approval you're clicking through rather than reviewing. Two tools cut those interruptions in Manual mode and apply in auto mode as well:
196In Manual mode, Claude Code asks before actions that might modify your system: file writes, Bash commands, MCP tools. That's safe but tedious. After the tenth approval you're clicking through rather than reviewing. Two tools cut those interruptions in Manual mode and apply in auto mode as well:
197197
198198* **Permission allowlists**: permit specific tools you know are safe, like `npm run lint` or `git commit`
199199* **Sandboxing**: enable OS-level isolation that restricts filesystem and network access, allowing Claude to work more freely within defined boundaries
claude-projects Changed · +44 / -6 lines
### Run a thread on your own computer ### Lost contact with your folder
from line 8
88
99A project is one ongoing conversation where Claude coordinates a stream of related work for you. You tell it what needs doing and it starts a thread for each task.
1010
11Each thread is usually a [cloud session](/docs/en/claude-code-on-the-web): Claude Code running in the cloud rather than on your machine. When a task needs something only your computer has, you can ask Claude to run that thread on your computer instead through [Remote Control](/docs/en/remote-control). Threads run in parallel and you can check on them and steer them from your phone. Cloud threads keep going after you close the laptop.
11Each thread is usually a [cloud session](/docs/en/claude-code-on-the-web): Claude Code running in the cloud rather than on your machine. When a task needs something only your computer has, you can ask Claude to [run that thread on your computer](#run-a-thread-on-your-own-computer) instead of in the cloud, through [Remote Control](/docs/en/remote-control). Threads run in parallel, and you can check on them and steer them from your phone. Cloud threads keep going after you close your laptop, while a thread on your computer runs only while that computer is awake.
1212
1313Without a project, running several sessions means doing the coordinating yourself: you decide what each one works on, repeat the same background at the start of each, and check back to see which finished or needs an answer. With a project, you instead:
1414
from line 24
2424
2525* **One goal across many repositories**: "Bring every service up to the new lint config." Claude can run a thread per repository, each with its own pull request, and the [**Overview** pane](#see-what-needs-you-in-overview) shows which ones are ready for review.
2626* **An area you keep feeding**: the bugs, stack traces, and review requests for one service, pasted into the conversation as they reach you. A pitfall you tell Claude to remember after one fix is in [project memory](#give-a-project-standing-context) for the next.
27* **A build or migration bigger than a session**: "Build what `docs/spec.md` describes" or "Move the app off the deprecated ORM." The work splits into threads that each take a part, decisions you ask Claude to remember early on reach the later threads, and the spec changes and bugs you find during the build go into the same conversation.
27* **A build or migration bigger than a session**: "Build what `docs/spec.md` describes" or "Move the app off the deprecated ORM." The work splits into threads that each take a part, decisions you ask Claude to remember early on reach the later cloud threads, and the spec changes and bugs you find during the build go into the same conversation.
2828* **Work that isn't code**: a folder of contracts or a support-ticket export you keep coming back to with new questions, such as "find the ten most common integration mistakes in these tickets." Upload the documents instead of adding a repository, and threads deliver each write-up as a file on the project's [**Library** tab](#see-what-needs-you-in-overview).
2929
3030In any of them you can send a batch of tasks, tell Claude to start without asking you to confirm, walk away, and find the threads that need you under [**Waiting on you**](#see-what-needs-you-in-overview) when you're back, or ask Claude to put part of the work on a schedule as a [routine](/docs/en/routines). If one of these is your situation, [create a project](#create-a-project).
from line 31
3131
3232### When something else fits better
3333
34Cloud threads work on GitHub repositories and on the files, folders, and Google Drive folders you upload to the project, not on files or tools that exist only on your machine. If a task needs your machine, ask Claude to run its thread there through [Remote Control](/docs/en/remote-control). [Limitations](#limitations) lists what that needs. Something else fits better in these cases:
34A project still fits when only some tasks need your machine. Cloud threads work on GitHub repositories and on the files, folders, and Google Drive folders you upload to the project, and for the occasional task that needs a local database or a tool on your computer, you can ask Claude to [run that task's thread on your computer](#run-a-thread-on-your-own-computer). Something other than a project fits better in these cases:
3535
3636* **One task that fits in a session**: "Fix the flaky login test." Start a [cloud session](/docs/en/claude-code-on-the-web) yourself.
3737* **Work where every task needs your machine**: a local database, a device emulator, or an API behind your VPN. Use a local session, or [agent view](/docs/en/agent-view) to run several at once. If the work only needs local files, upload them to the project instead.
from line 231
231231* "Tell me what's wrong in these repositories and don't fix anything yet", when you want to go through the findings before any of them becomes a thread
232232* "Answer that here instead of starting a thread", when Claude starts a thread for something you meant as a quick question
233233
234Claude saves preferences like these to [project memory](#give-a-project-standing-context) on its own and follows them in later threads. They're instructions Claude keeps to, not enforced settings, so a thread limit you give this way isn't a hard cap. Add one to project instructions when you want it worded exactly and applied to every thread from the start.
234Claude saves preferences like these to [project memory](#give-a-project-standing-context) on its own and follows them in later cloud threads. They're instructions Claude keeps to, not enforced settings, so a thread limit you give this way isn't a hard cap. Add one to project instructions when you want it worded exactly and applied to every thread from the start.
235235
236236### Unblock a thread waiting on approval
237237
from line 239
239239
240240Each approval covers that prompt, or the rest of that thread if you choose the broader option. To let every thread run certain commands without asking, or to block some, add [permission rules](/docs/en/permissions) to the repository's `.claude/settings.json`. Cloud threads apply them only in a project with one repository; see [What threads pick up from your repositories](#what-threads-pick-up-from-your-repositories).
241241
242### Run a thread on your own computer
243
244When a task needs something only your computer has, such as a local database, a device emulator, or an API behind your VPN, ask Claude to run the thread for that task on your computer instead of in the cloud. When you ask in the project conversation, the thread is a Claude Code session in a folder on your machine, connected through [Remote Control](/docs/en/remote-control). The project's other threads keep running in the cloud. Compared with a cloud thread, a thread on your computer:
245
246* Works with the files, tools, MCP servers, and Claude Code settings on that machine instead of the project's cloud environment
247* Starts with the project's instructions, but not with its memory files loaded
248* Runs only while that computer is awake with Remote Control turned on
249
250<Steps>
251 <Step title="Connect the folder">
252 On the computer that has the folder the task needs, make it available through Remote Control in one of two ways. Both need Claude Code v2.1.280 or later on that computer.
253
254 * **In the Claude desktop app**: open **Settings > Claude Code**, turn on **Use this computer from your phone and claude.ai**, and add the folder to the list under that switch. Threads can run on this computer while the app is open.
255 * **In a terminal**: run `claude remote-control` in the folder and leave it running.
256 </Step>
257
258 <Step title="Ask for the task with Work locally">
259 In the project conversation, choose **Work locally** from the **+** menu beside the message box, which tags your message **Local**, and write what you want done. Saying in the message that the task should run on your computer works too.
260 </Step>
261
262 <Step title="Allow it on the card">
263 Claude answers with an **Allow Claude to work in a folder on your device** card. Pick the folder if you connected several. Then click **Allow once**.
264 </Step>
265</Steps>
266
267The thread runs in [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), so Claude runs commands and edits files in that folder without asking you each time. If auto mode is unavailable or turned off in that computer's Claude Code, the thread runs without it, and any permission prompt it raises waits for your answer in the thread, as [Unblock a thread waiting on approval](#unblock-a-thread-waiting-on-approval) describes.
268
269While the thread runs, a laptop icon in its header shows whether your computer is connected. Click it to see which folder the thread is using or to turn the connection off. The thread pauses while that computer is asleep, and stops if the desktop app or `claude remote-control` quits. [Lost contact with your folder](#lost-contact-with-your-folder) covers getting it going again. In the desktop app, turn on **Keep this computer awake for Remote Control** under **Settings > Claude Code** to stop the computer from sleeping on its own.
270
271A project can't run a thread on your computer while [**Require trusted devices**](/docs/en/remote-control#trusted-devices) is on for your account.
272
242273## Give a project standing context
243274
244275Project memory, project instructions, and the project's repositories, files, and environment carry context across threads. You set each one once.
from line 410
379410* **Claude Tag**: [Claude Tag](https://claude.com/docs/claude-tag/overview) is Claude in your team's Slack channels, on Team and Enterprise plans. Anyone in a channel can give it work, everyone in the channel sees and steers it, and it uses connections an admin set up for that channel. A project is yours alone: you're the only one who sends it work or sees its threads, it uses your own GitHub access and connectors, and it's on Pro and Max. [How Claude Tag differs from Cowork and Claude Code](https://claude.com/docs/claude-tag/concepts/how-it-works#how-claude-tag-differs-from-cowork-and-claude-code) has the side-by-side.
380411* **Cloud sessions**: every thread is a [cloud session](/docs/en/claude-code-on-the-web) unless you ask Claude to run it on your machine. Either way, Claude starts and tracks it instead of you. A cloud session you started yourself can become a project or feed one through [**Continue as a project** or **Move to project**](#start-from-an-existing-cloud-session).
381412* **Routines**: when you ask for scheduled work in a project, Claude creates a [routine](/docs/en/routines) that runs as threads in that project and appears on its **Routines** tab. Routines you create outside a project keep working on their own.
382* **Local sessions and agent view**: a session you start yourself in your terminal, IDE, or the desktop app's local environment can't be added to a project. A project reaches your machine only by running a thread there through [Remote Control](/docs/en/remote-control). [Agent view](/docs/en/agent-view) is a screen for tracking several local sessions you started yourself; it has no coordinator.
413* **Remote Control**: [Remote Control](/docs/en/remote-control) connects claude.ai to a Claude Code session running on your machine. When you ask Claude in a project to run a thread on your computer, the project [uses Remote Control to do it](#run-a-thread-on-your-own-computer).
414* **Local sessions and agent view**: a session you start yourself in your terminal, IDE, or the desktop app's local environment can't be added to a project. [Agent view](/docs/en/agent-view) is a screen for tracking several local sessions side by side, and you still start each one and give it its task yourself.
383415* **Worktrees**: a [worktree](/docs/en/worktrees) gives each local session its own working copy of a repository so parallel sessions on your machine don't overwrite each other. Cloud threads don't need them: each clones its repositories into its own cloud sandbox and works on its own branch.
384416* **Agent teams**: an [agent team](/docs/en/agent-teams) is one session that starts teammate sessions for a single task, on your machine or inside a cloud session, and ends with that task.
385417* **Projects in claude.ai chat and Cowork**: the [earlier Projects experience](https://support.claude.com/en/articles/9517075-what-are-projects), which groups conversations and reference files without threads or a coordinator. Those projects keep working as they do today until the redesigned experience reaches them.
from line 422
390422
391423* Projects are available at claude.ai/code, in the desktop app, and in the Claude mobile app, not in the terminal CLI or through Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. The CLI's [`claude project`](/docs/en/cli-reference) command, which manages local Claude Code state for a directory, is unrelated.
392424* Project threads are [cloud sessions](/docs/en/claude-code-on-the-web), or sessions on your own machine through [Remote Control](/docs/en/remote-control), with Anthropic as the model provider in both cases. [Security](/docs/en/security) and [Data usage](/docs/en/data-usage) cover how cloud sessions are isolated and what's retained, and [Connection and security](/docs/en/remote-control#connection-and-security) covers how a thread on your machine connects and what's stored.
393* You can't add a session you started yourself on your machine to a project. To let a project run a thread on your machine, connect the folder it should work in through [Remote Control](/docs/en/remote-control#requirements): turn on Remote Control under **Settings > Claude Code** in the Claude desktop app, or run `claude remote-control` in the folder and leave it running. That machine needs Claude Code v2.1.280 or later. A project also can't run a thread on your machine while **Require trusted devices** is on in your claude.ai settings.
425* You can't add a session you started yourself on your machine to a project. A project reaches your machine only by [running a thread there through Remote Control](#run-a-thread-on-your-own-computer), and that section lists what it needs.
394426* A cloud thread's sandbox pauses between turns and resumes when the thread continues. If the sandbox can't be resumed, the thread continues from a fresh clone, so uncommitted changes can be lost. On long tasks, ask Claude to commit and push work in progress.
395427* A project belongs to one user. You can't share a project or its threads with another user, and thread transcripts don't have the share option other cloud sessions have. There are no organization-level controls for projects during the beta.
396428* A thread belongs to the one project that started it. You can't move or copy a thread to another project, or move it out to stand alone. [**Move to project**](#start-from-an-existing-cloud-session) goes the other way only: it brings a cloud session's work into a project.
from line 475
443475
444476A thread or the project conversation made a request your plan covers only with usage credits, such as one to a model or context size your plan doesn't include, and usage credits aren't turned on for your account. [Add usage credits to your subscription](/docs/en/costs#add-usage-credits-to-your-subscription) covers who can turn them on or buy them on each plan. Once credits are available, send another message to retry.
445477
478### Lost contact with your folder
479
480A thread running on your computer shows this when the Claude Code session there stopped responding, usually because the computer went to sleep or the desktop app or `claude remote-control` quit. Wake the computer, and if the desktop app or `claude remote-control` is no longer running there, start it again: reopen the app and confirm **Use this computer from your phone and claude.ai** is still on under **Settings > Claude Code**, or run `claude remote-control` again in the same folder.
481
446482<h3 id="context-limit">
447483 Other messages
448484</h3>
from line 493
457493| "The project's environment was removed" | Choose a different environment in **Project settings > Environment**; the change applies to new threads |
458494| "Setup script failed" | Click **Edit setup script** on the error, fix the script in the environment, then send another message. [Setup script failed](/docs/en/web-quickstart#setup-script-failed) lists common causes |
459495| "Claude ran out of context on this turn" | The thread filled its context window. If the message says the thread continues in a fresh session, it carries on by itself; otherwise ask Claude in the project conversation to start a new thread for the remaining work |
496| "Couldn't start in" followed by your folder's name | You allowed a thread to run on your computer, but the session couldn't start there. When a line under the message gives the reason, fix that, then ask Claude to run the task again |
497| "Claude is out of date on your device" | The computer you picked to run a thread has a Claude Code version older than v2.1.280. Update Claude Code there, or update the desktop app if that's what connects the folder, then ask Claude to run the task again |
460498| "Reached the turn limit" | The thread reached the cap on agentic turns that [`CLAUDE_CODE_MAX_TURNS`](/docs/en/env-vars) sets. Send another message to continue, or raise or remove that variable where it's set |
461499
462500## Related resources
env-vars Changed · +3 / -3 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 241
241241| `CLAUDE_CODE_DISABLE_CFC_PROMPT` | Set to `1` to keep the [Claude in Chrome](/docs/en/chrome) browser tools available while omitting the Chrome section of the system prompt and the `/claude-in-chrome` [bundled skill](/docs/en/skills#bundled-skills). For hosts that embed Claude Code and supply their own browser guidance. Requires Claude Code v2.1.257 or later |
242242| `CLAUDE_CODE_DISABLE_CLAUDE_MDS` | Set to `1` to prevent loading any CLAUDE.md memory files into context, including user, project, and auto memory files |
243243| `CLAUDE_CODE_DISABLE_CRON` | Set to `1` to disable [scheduled tasks](/docs/en/scheduled-tasks). The `/loop` skill and cron tools become unavailable and any already-scheduled tasks stop firing, including tasks that are already running mid-session |
244| `CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT` | Set to `1` to turn off the time limit on [critical-path removal](/docs/en/permission-modes#critical-paths) prompts. In `auto` mode Claude Code then sends these removals to the classifier instead, and in `bypassPermissions` mode the prompt waits for your answer. Set it in the environment that launches Claude Code, since Claude Code ignores a copy delivered through a settings `env` block. Requires Claude Code v2.1.281 or later |
244245| `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS` | Set to `1` to strip Anthropic-specific `anthropic-beta` request headers and beta tool-schema fields (such as `defer_loading` and `eager_input_streaming`) from API requests. Use this when a proxy gateway rejects requests with errors like "Unexpected value(s) for the `anthropic-beta` header" or "Extra inputs are not permitted". Standard fields (`name`, `description`, `input_schema`, `cache_control`) are preserved. [MCP tool search](/docs/en/mcp#scale-with-mcp-tool-search) is disabled and all MCP tools load upfront, even when you set `ENABLE_TOOL_SEARCH`. On Claude Code v2.1.227 or later, [managed settings](/docs/en/managed-settings) can keep tool search on. [Disable pre-release capabilities](/docs/en/llm-gateway-protocol#disable-pre-release-capabilities) covers where the override applies |
245246| `CLAUDE_CODE_DISABLE_EXPLORE_PLAN_AGENTS` | Set to `1` to disable the built-in [Explore and Plan subagents](/docs/en/sub-agents#built-in-subagents). Claude explores with its search tools or the general-purpose subagent instead, and [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode) reads files directly rather than launching Explore and Plan agents. Custom subagents named `Explore` or `Plan` are unaffected. To remove every built-in subagent type in the Agent SDK or non-interactive mode, use `CLAUDE_AGENT_SDK_DISABLE_BUILTIN_AGENTS` instead. Requires Claude Code v2.1.198 or later |
246247| `CLAUDE_CODE_DISABLE_FAST_MODE` | Set to `1` to disable [fast mode](/docs/en/fast-mode) |
from line 259
258259| `CLAUDE_CODE_DISABLE_PERMISSION_PROMPT_NOTIFY_HOOKS` | Set to `1` to stop Claude Code from running your [`Notification` hooks for unanswered permission requests](/docs/en/hooks#notification) in sessions where Claude Code sends them to the Agent SDK's `canUseTool` callback, which is how Claude Desktop and the VS Code extension host Claude Code. Has no effect in terminal sessions. Requires Claude Code v2.1.233 or later |
259260| `CLAUDE_CODE_DISABLE_POLICY_SKILLS` | Set to `1` to skip loading skills from the system-wide managed skills directory. Useful for container or CI sessions that should not load operator-provisioned skills |
260261| `CLAUDE_CODE_DISABLE_POWERSHELL_CMD_RM_DENY` | Set to `1` to turn off the [PowerShell tool](/docs/en/tools-reference#powershell-tool) check that denies the `cmd` built-ins `rd`, `rmdir`, `del`, and `erase` on a [system path](/docs/en/permission-modes#remove-item-in-powershell), such as a drive root or your home directory. Claude Code ignores this variable in a settings file's `env` block. Requires Claude Code v2.1.283 or later |
262| `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT` | Set to `1` to turn off the [critical-path](/docs/en/permission-modes#critical-paths) check for a recursive `rm` whose target is entirely the output of a command substitution, such as `rm -rf "$(pwd)"`. The other critical-path checks keep running. Set it in the environment that launches Claude Code, since Claude Code ignores a copy delivered through a settings `env` block. Requires Claude Code v2.1.281 or later |
261263| `CLAUDE_CODE_DISABLE_TERMINAL_TITLE` | Set to `1` to disable automatic terminal title updates based on conversation context. This also skips the background small/fast-model request that [generates a session title](/docs/en/sessions#name-your-sessions) |
262264| `CLAUDE_CODE_DISABLE_THINKING` | Set to `1` to omit the `thinking` parameter from API requests entirely. This is a compatibility option for proxies and gateways that reject the parameter. On models that think by default, omitting the parameter means the model may still think. To explicitly disable [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) on the Anthropic API, use `MAX_THINKING_TOKENS=0` instead. Neither variable turns thinking off on Opus 5.5 or the Fable models, which can't have thinking turned off. On [third-party providers](/docs/en/third-party-integrations), `MAX_THINKING_TOKENS=0` likewise omits the parameter, so the two variables behave the same there |
263265| `CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT` | Set to `1` to skip proactive [auto-compaction](/docs/en/costs#reduce-token-usage) when Claude Code doesn't recognize the model ID, such as an [LLM gateway](/docs/en/llm-gateway) alias. Without this variable, Claude Code compacts at the context window it assumes for the ID. `CLAUDE_CODE_MAX_CONTEXT_TOKENS` can correct the assumed window instead; see [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id) for when each variable applies. Requires Claude Code v2.1.223 or later |
from line 318
316318| `CLAUDE_CODE_NEW_INIT` | Set to `1` to make `/init` run an interactive setup flow. The flow asks which files to generate, including CLAUDE.md, skills, and hooks, before exploring the codebase and writing them. Without this variable, `/init` generates a CLAUDE.md automatically without prompting |
317319| `CLAUDE_CODE_NONBLOCKING_STDOUT` | Set to `1` to write terminal output through a second non-blocking file descriptor, so a terminal that stops reading, such as a paused tmux control-mode pane or a stalled SSH connection, can't freeze Claude Code mid-session. Applies on macOS, Linux, and WSL when stdout is a terminal. Requires Claude Code v2.1.261 or later |
318320| `CLAUDE_CODE_NO_FLICKER` | Set to `1` to enable [fullscreen rendering](/docs/en/fullscreen), a research preview that reduces flicker and keeps memory flat in long conversations. Overrides the [`tui`](/docs/en/settings-reference#tui) setting; you can also switch with `/tui fullscreen` |
319| `CLAUDE_CODE_OAUTH_REFRESH_TOKEN` | OAuth refresh token for Claude.ai authentication. When set, `claude auth login` exchanges this token directly instead of opening a browser. Requires `CLAUDE_CODE_OAUTH_SCOPES`. Useful for provisioning authentication in automated environments |
320| `CLAUDE_CODE_OAUTH_SCOPES` | Space-separated OAuth scopes the refresh token was issued with, such as `"user:profile user:inference user:sessions:claude_code"`. Required when `CLAUDE_CODE_OAUTH_REFRESH_TOKEN` is set |
321| `CLAUDE_CODE_OAUTH_TOKEN` | OAuth access token for claude.ai authentication. Alternative to `/login` for SDK and automated environments. Takes precedence over keychain-stored credentials. Generate one with [`claude setup-token`](/docs/en/authentication#generate-a-long-lived-token). Unless you run [`/login`](/docs/en/authentication#authentication-precedence), Claude Code uses the token you set for the whole session. To replace an expired token, generate a new one and restart
321| `CLAUDE_CODE_OAUTH_REFRESH_TOKEN` | OAuth refresh token for Claude.ai authentication. When set, `claude auth login` exchanges this token directly instead of opening a browser. Requires `CLAUDE_CODE_OAUTH_SCOPES`. Useful for provisioning authentication in automated environments
mobile Changed · +6 / -6 lines
from line 32
3232
3333From the app you can start cloud sessions, open a project, drive a Claude Code session running on your computer, or message Dispatch a task. The app is the same for each; they differ in where the work happens.
3434
35| Feature | What you connect to | When to use |
36| :--------------------------------------------- | :------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------- |
37| [Cloud sessions](/docs/en/claude-code-on-the-web) | A session on cloud infrastructure, Anthropic-managed by default | Your repository is on GitHub and the task should keep running after you put your phone away. See the [cloud quickstart](/docs/en/web-quickstart) to set up. |
38| [Projects](/docs/en/claude-projects) | A conversation where Claude coordinates parallel cloud sessions as threads | You have a stream of related work rather than one task and want to see which threads finished or need you. |
39| [Remote Control](/docs/en/remote-control) | A Claude Code session running on your computer | The work needs your local filesystem, tools, or MCP servers. |
40| [Dispatch](/docs/en/desktop#sessions-from-dispatch) | The Desktop app on your computer | You want to message a task and let Dispatch decide how to run it. Requires a Pro or Max plan. |
35| Feature | What you connect to | When to use |
36| :--------------------------------------------- | :-------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------- |
37| [Cloud sessions](/docs/en/claude-code-on-the-web) | A session on cloud infrastructure, Anthropic-managed by default | Your repository is on GitHub and the task should keep running after you put your phone away. See the [cloud quickstart](/docs/en/web-quickstart) to set up. |
38| [Projects](/docs/en/claude-projects) | A conversation where Claude coordinates parallel threads of work and reports back | You have a stream of related work rather than one task and want to see which threads finished or need you. |
39| [Remote Control](/docs/en/remote-control) | A Claude Code session running on your computer | The work needs your local filesystem, tools, or MCP servers. |
40| [Dispatch](/docs/en/desktop#sessions-from-dispatch) | The Desktop app on your computer | You want to message a task and let Dispatch decide how to run it. Requires a Pro or Max plan. |
4141
4242If your computer will be off, use cloud sessions or a project, which run in the cloud and continue with your laptop closed. Remote Control and Dispatch drive your own machine, so it needs to stay on with Claude Code or the Desktop app running. If your machine sleeps during a Remote Control session, Claude Code reconnects when the machine comes back online.
4343
permission-modes Changed · +61 / -39 lines
from line 4
44
55A permission mode sets which actions Claude can take in a session without asking you first. In Manual mode, Claude Code stops and asks you before most actions that edit files, run shell commands, or reach the network. In [auto mode](#eliminate-prompts-with-auto-mode), a second model, the classifier, reviews actions instead of you; [how the classifier evaluates actions](#how-the-classifier-evaluates-actions) lists which actions it reviews and which skip it.
66
7On Pro, Max, and Team plans, the built-in starting permission mode is auto mode. [Which mode a session starts in](#which-mode-a-session-starts-in) covers the surfaces and settings that change the starting permission mode. You can also change a running session's permission mode at any time.
7With Claude Code v2.1.283 or later, auto mode is the built-in starting permission mode for interactive terminal and VS Code sessions. On earlier versions, it's the built-in starting permission mode only on Pro, Max, and Team plans. [Which mode a session starts in](#which-mode-a-session-starts-in) covers the surfaces and settings that change the starting permission mode. You can also change a running session's permission mode at any time.
88
99## Available modes
1010
from line 49
4949| Review every action yourself | Manual mode: `claude --permission-mode default` | None | Sensitive work, unfamiliar code |
5050| Iterate locally with fewer prompts, without a classifier | Manual mode plus the Bash sandbox in [auto-allow mode](/docs/en/sandboxing#sandbox-modes): `claude --permission-mode default`, then run `/sandbox` and select auto-allow | The built-in Bash sandbox, on macOS, Linux, and WSL2 | Deny rules still apply, and ask rules that name a command, such as `Bash(git push *)`, still prompt. To turn the sandbox on from a settings file instead, set [`sandbox.enabled`](/docs/en/settings-reference#sandbox-enabled) to `true` |
5151| Explore before changing anything | `claude --permission-mode plan` | None | Claude Code blocks edits until you [approve a plan](#review-and-approve-a-plan) |
52| Work hands-off in auto mode | `claude --permission-mode auto`, the [built-in starting permission mode](#which-mode-a-session-starts-in) on Pro, Max, and Team | None; a sandbox or container adds defense in depth | Requires a [supported model](#eliminate-prompts-with-auto-mode), and your organization can [turn auto mode off](#eliminate-prompts-with-auto-mode) |
52| Work hands-off in auto mode | `claude --permission-mode auto`, the [built-in starting permission mode](#which-mode-a-session-starts-in) with v2.1.283 or later | None; a sandbox or container adds defense in depth | Requires a [supported model](#eliminate-prompts-with-auto-mode), and your organization can [turn auto mode off](#eliminate-prompts-with-auto-mode) |
5353| Run in CI with an exact allowlist | `claude -p "run the test suite" --permission-mode dontAsk --allowedTools "Bash(npm test)" "Read"` | None beyond what your CI runner provides | [Cloud sessions](/docs/en/claude-code-on-the-web) ignore `dontAsk` from settings files |
5454| Run fully unattended inside a container | `claude -p "<prompt>" --dangerously-skip-permissions` | Required: a container, VM, or the [sandbox runtime](/docs/en/sandbox-environments#sandbox-runtime); on Linux and macOS, run it as a [non-root user](#skip-all-checks-with-bypasspermissions-mode) | Cloud sessions ignore this mode from settings files. In this `-p` run, the [few calls that would still prompt](#skip-all-checks-with-bypasspermissions-mode) are denied instead |
5555
from line 73
7373
7474The built-in `auto` default requires Claude Code v2.1.228 or later on macOS, Linux, and WSL, and v2.1.233 or later on native Windows. On earlier versions, the built-in default is Manual.
7575
76The built-in default depends on how you run Claude Code, on your plan, and on whether Claude Code could fetch its feature flags. The first row that matches your session applies. The table covers sessions you start in a terminal or through the VS Code extension; for the desktop app and claude.ai, see the Desktop and Web tabs in [Switch permission modes](#switch-permission-modes).
76The built-in default depends on how you run Claude Code. The first row that matches your session applies. The table covers sessions you start in a terminal or through the VS Code extension; for the desktop app and claude.ai, see the Desktop and Web tabs in [Switch permission modes](#switch-permission-modes).
7777
78| How you run Claude Code | Built-in starting permission mode |
79| :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------------------- |
80| Any settings file sets `disableAutoMode` to `"disable"` | `default` |
81| [Feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) is off | `default` |
82| Your [first session after you install Claude Code or upgrade](/docs/en/env-vars#first-session-after-an-install-or-upgrade) to a version that adds this default, unless, after a fresh install, Claude Code fetches the flags in time | `default` |
83| `claude -p` or the [Agent SDK](/docs/en/agent-sdk/permissions) | `default` |
84| Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), or a signed-in [Claude apps gateway](/docs/en/claude-apps-gateway) session | `default` |
85| A Pro, Max, or Team plan, in a terminal or through the [VS Code extension](/docs/en/vs-code) | `auto` |
86| An Enterprise plan or a Claude Console API key | `default` |
78| How you run Claude Code | Built-in starting permission mode |
79| :------------------------------------------------------------ | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
80| Any settings file sets `disableAutoMode` to `"disable"` | `default` |
81| `claude -p` or the [Agent SDK](/docs/en/agent-sdk/permissions) | `default` |
82| In a terminal or through the [VS Code extension](/docs/en/vs-code) | `auto` with Claude Code v2.1.283 or later; on earlier versions, `auto` on Pro, Max, or Team plans in sessions that [fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching), and `default` otherwise |
8783
88When feature-flag fetching is off, or in a [first session after an install or upgrade](/docs/en/env-vars#first-session-after-an-install-or-upgrade) where the flags haven't arrived yet, the VS Code extension ignores every settings file when choosing the starting permission mode.
84In your [first session after an install or upgrade](/docs/en/env-vars#first-session-after-an-install-or-upgrade), Claude Code can choose the starting permission mode before its feature flags arrive. That session can start in a different permission mode than the table gives, and your next session matches the table.
8985
9086When the flag, a settings file, or the built-in default selects `auto` but auto mode isn't available to the session, Claude Code starts the session in Manual instead. Auto mode is unavailable when the session doesn't meet the [availability requirements](#eliminate-prompts-with-auto-mode), such as a settings file turning it off or a model that doesn't support it, or when Anthropic has temporarily turned it off server-side.
9187
from line 163
167163
168164 1. `claudeCode.initialPermissionMode`
169165 2. The mode you last picked from the mode indicator, if it was Manual, Edit automatically, or Auto. Picking Plan or Bypass permissions applies to that conversation only
170 3. `permissions.defaultMode` from [managed settings](/docs/en/managed-settings) or `~/.claude/settings.json`, on Pro, Max, and Team plans with [feature-flag fetching](#which-mode-a-session-starts-in) available
166 3. `permissions.defaultMode` from [managed settings](/docs/en/managed-settings) or `~/.claude/settings.json`
171167 4. The [built-in default](#which-mode-a-session-starts-in) for your plan, provider, and organization settings
172168
173 The extension never reads a project's `.claude/settings.json` or `.claude/settings.local.json` for the starting permission mode, and in conversations that don't meet item 3's conditions it reads no settings file at all. When `claudeCode.claudeProcessWrapper` is set, items 3 and 4 don't apply either: those conversations start in Manual unless item 1 or item 2 sets a permission mode.
169 The extension never reads a project's `.claude/settings.json` or `.claude/settings.local.json` for the starting permission mode. When `claudeCode.claudeProcessWrapper` is set, items 3 and 4 don't apply: those conversations start in Manual unless item 1 or item 2 sets a permission mode.
174170
171 Before v2.1.283, item 3 applied only on Pro, Max, and Team plans in sessions that [fetch feature flags](/docs/en/env-vars#features-that-need-feature-flag-fetching).
172
175173 Auto appears in the mode indicator when [auto mode is available](#eliminate-prompts-with-auto-mode).
176174
177175 Bypass permissions requires the **Allow dangerously skip permissions** toggle in the extension settings. Without it, the permission mode doesn't appear in the indicator, and a `bypassPermissions` value from item 1 or item 3 starts the conversation in Manual instead. Auto from any item likewise starts the conversation in Manual when auto mode isn't available.
from line 202
204202 Use the mode dropdown next to the prompt box on [claude.ai/code](https://claude.ai/code) or in the mobile app. Permission prompts appear in claude.ai for approval. Which modes appear depends on where the session runs:
205203
206204 * **[Cloud sessions](/docs/en/claude-code-on-the-web)**: Accept edits, Plan, and Auto. Accept edits corresponds to `default` mode: cloud sessions pre-approve file edits regardless of mode, so the dropdown shows Accept edits instead of Manual. Cloud sessions still honor `defaultMode: "acceptEdits"` from settings. Auto mode appears only when your organization allows it and the selected model supports it. Bypass permissions isn't available.
207 * **[Remote Control](/docs/en/remote-control) sessions** on your local machine: Manual, Accept edits, and Plan. You can't select Auto or Bypass permissions from the app.
205 * **[Remote Control](/docs/en/remote-control) sessions** on your local machine: Manual, Accept edits, and Plan for a session you started yourself, and you can't select Auto or Bypass permissions from the app. For a project thread running on your computer, see [Run a thread on your own computer](/docs/en/claude-projects#run-a-thread-on-your-own-computer).
208206 * Except for Bypass permissions, the dropdown shows the permission mode the local session is in, including one set from the terminal. It updates when the permission mode changes in the app or in the terminal. The session never reports Bypass permissions to claude.ai, so switching into it from the terminal doesn't change what the dropdown shows.
209207 * Sessions hosted by the [desktop app](/docs/en/desktop) or the [VS Code extension](/docs/en/vs-code) report permission mode changes to claude.ai as they happen, the same as sessions hosted in a terminal.
210208 * Before v2.1.202, sessions connected with `/remote-control` or `claude --remote-control` didn't report their permission mode at all, so claude.ai and the mobile app could show a permission mode the session wasn't in. The mismatch affected only the label. Claude Code generated permission prompts from the session's actual permission mode, and they still appeared in the app for approval.
from line 235
237235
238236Plan mode tells Claude to research and propose changes without making them. Claude reads files, runs shell commands to explore, and writes a plan, but does not edit your source. Except in interactive terminal sessions with [bypass permissions available](#skip-all-checks-with-bypasspermissions-mode), edits stay blocked until you approve the plan.
239237
240When [auto mode](/docs/en/auto-mode-config) is available and the `useAutoModeDuringPlan` setting is on, which it is by default, the classifier reviews shell commands during planning instead of prompting you. Approved commands run, and rejected ones are blocked. Otherwise, commands outside the [built-in read-only set](/docs/en/permissions#read-only-commands) prompt for approval, including when the sandbox's [auto-allow mode](/docs/en/sandboxing#sandbox-modes) is enabled. In interactive terminal sessions with bypass permissions available, neither the classifier nor a prompt applies to planning commands; [Skip all checks with bypassPermissions mode](#skip-all-checks-with-bypasspermissions-mode) covers the few things that still prompt there. In v2.1.212 through v2.1.217, sessions without bypass permissions prompted for every command outside the read-only set, whether or not auto mode was available.
238What happens to a shell command during planning depends on the session, and the first of these cases that matches applies:
241239
240* **Interactive terminal sessions with bypass permissions available**: neither the classifier nor a prompt applies to planning commands. [Skip all checks with bypassPermissions mode](#skip-all-checks-with-bypasspermissions-mode) covers the few things that still prompt there.
241* **[Auto mode](/docs/en/auto-mode-config) available and the `useAutoModeDuringPlan` setting on**, which it is by default: the classifier reviews shell commands other than [critical-path removals](#critical-paths) instead of prompting you. Approved commands run, and rejected ones are blocked.
242* **Auto mode not available, or `useAutoModeDuringPlan` off**: commands outside the [built-in read-only set](/docs/en/permissions#read-only-commands) prompt for approval, including when the sandbox's [auto-allow mode](/docs/en/sandboxing#sandbox-modes) is enabled.
243
242244Enter plan mode by pressing `Shift+Tab` or prefixing a single prompt with `/plan`. You can also start in plan mode from the CLI:
243245
244246```bash theme={null}
from line 273
271273
272274Auto mode lets Claude execute without routine permission prompts. A separate classifier model reviews actions before they run, blocking anything that escalates beyond your request, targets unrecognized infrastructure, or appears driven by hostile content Claude read. Explicit [ask rules](/docs/en/permissions#manage-permissions) still force a prompt.
273275
274On Pro, Max, and Team plans, auto mode is the [built-in starting permission mode](#which-mode-a-session-starts-in).
276With Claude Code v2.1.283 or later, auto mode is the [built-in starting permission mode](#which-mode-a-session-starts-in) for interactive terminal and VS Code sessions on every plan and provider. On earlier versions, it's the built-in starting permission mode only on Pro, Max, and Team plans.
275277
276278The classifier also reviews each message Claude sends to another agent with [`SendMessage`](/docs/en/tools-reference), whether plain text or a structured [agent team](/docs/en/agent-teams) message, before Claude Code delivers it, both in auto mode and in [plan mode while the classifier reviews commands](#analyze-before-you-edit-with-plan-mode); the send review requires Claude Code v2.1.222 or later.
277279
278The classifier also reviews and approves or blocks `rm` and `rmdir` removals targeting a [critical path](#critical-paths), such as `rm -rf /` and `rm -rf ~`, including when the removal sits inside command or process substitution.
280By default, the classifier doesn't review `rm` and `rmdir` removals targeting a critical path, such as `rm -rf /` or `rm -rf ~`. [Critical paths](#critical-paths) covers what happens to them in each permission mode.
279281
280282Auto mode also nudges Claude to keep working without stopping for clarifying questions, though Claude still asks when your prompt or a skill explicitly relies on it. For stronger autonomous behavior in a mode that still prompts you, set the [Proactive output style](/docs/en/output-styles) instead.
281283
from line 302
300302 Auto mode on Bedrock, Agent Platform, or Foundry
301303</h3>
302304
303On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), [Microsoft Foundry](/docs/en/microsoft-foundry), and signed-in [Claude apps gateway](/docs/en/claude-apps-gateway) sessions, auto mode appears in the `Shift+Tab` cycle by default. Appearing in the cycle doesn't change the permission mode a session starts in: on these providers, terminal sessions start in your [`defaultMode`](/docs/en/settings-reference#permissions-defaultmode), which is Manual unless you change it, and conversations in the [VS Code extension](/docs/en/vs-code) start in Manual unless `claudeCode.initialPermissionMode` or a mode you picked in the extension sets one. Only Claude Sonnet 5, Opus 4.7 or later, and the Fable models are supported on these providers.
305On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), [Microsoft Foundry](/docs/en/microsoft-foundry), and signed-in [Claude apps gateway](/docs/en/claude-apps-gateway) sessions, auto mode is available by default. With Claude Code v2.1.283 or later, it's also the [built-in starting permission mode](#which-mode-a-session-starts-in) for interactive terminal and [VS Code](/docs/en/vs-code) sessions. To choose the starting permission mode yourself, set `permissions.defaultMode` as [Start in a different permission mode](#start-in-a-different-mode) describes, or pick a permission mode from the VS Code extension's mode indicator.
304306
305To make auto mode the default starting permission mode, set `"permissions": {"defaultMode": "auto"}` in user or managed settings. In sessions the VS Code extension starts, select **Auto** from the mode indicator instead. [Switch permission modes](#switch-permission-modes) covers what outranks that pick.
307Only Claude Sonnet 5, Opus 4.7 or later, and the Fable models are supported on these providers. On any other model, the session starts in Manual instead.
306308
307The [`/doctor`](/docs/en/commands#all-commands) checkup proposes this user-settings default on these providers the same way it does on the Anthropic API.
308
309309To prevent developers from using auto mode, set `disableAutoMode` to `"disable"` in [managed settings](/docs/en/managed-settings). This removes `auto` from the `Shift+Tab` cycle, and a session started with `--permission-mode auto` starts in Manual instead. A session already running in auto mode leaves it when the setting reaches that session from an [admin-deployed source](/docs/en/managed-settings#which-managed-source-claude-code-uses), and shows `auto mode disabled by settings`. Before v2.1.251, a running session kept auto mode until it ended.
310310
311311In v2.1.158 through v2.1.206, auto mode was off on these providers until you set `CLAUDE_CODE_ENABLE_AUTO_MODE=1`, and Claude Code ignored `defaultMode: "auto"` on these providers unless the variable was also set. The variable is still accepted for compatibility and has no effect from v2.1.207 onward.
from line 385
385385Claude Code v2.1.205 and later also block these by default:
386386
387387* Writing to Claude Code session transcripts, the `.jsonl` history files under `~/.claude/projects/` or your configured config directory, whether directly or through a shell command. The rule also covers the metadata lines Claude Code appends to each transcript entry for its own checks. Reading a transcript isn't blocked
388* A recursive forced delete such as `rm -rf "$VAR"` or `Remove-Item -Recurse -Force $dir` whose target is a shell variable, or a glob rooted at one, that isn't assigned anywhere in the conversation the classifier sees. The value came only from earlier command output, which the classifier never receives, so the classifier can't verify the deletion target against the other deletion rules. The block clears when you name the exact path being deleted, or when Claude re-runs the delete with the resolved literal path written into the command. Deletes whose target the classifier can resolve aren't affected. `Remove-Item` targets that are a bare `*` or end in `/*` or `\*` never reach the classifier: Claude Code [denies them outright](#remove-item-in-powershell)
388* A recursive forced delete such as `rm -rf "$VAR"` or `Remove-Item -Recurse -Force $dir` whose target is a shell variable that isn't assigned anywhere in the conversation the classifier sees, or a glob rooted at such a variable. The value came only from earlier command output, which the classifier never receives, so the classifier can't verify the deletion target against the other deletion rules. The block clears when you name the exact path being deleted, or when Claude re-runs the delete with the resolved literal path written into the command. Deletes whose target the classifier can resolve aren't affected.
389389
390 A glob directly under the variable, as in `rm -rf "$VAR"/*`, is a [critical path](#critical-paths) instead. `Remove-Item` targets that are a bare `*` or end in `/*` or `\*` never reach the classifier: Claude Code [denies them outright](#remove-item-in-powershell).
391
390392Claude Code v2.1.257 and later also block these by default:
391393
392394* Requesting credentials from the cloud instance-metadata endpoint, such as `169.254.169.254`, or explicitly authenticating a cloud, cluster, or registry call with the machine's own service-account or node identity
from line 471
469471 Each action goes through a fixed decision order. The first matching step wins:
470472
471473 1. Actions matching your [allow, ask, or deny rules](/docs/en/permissions#manage-permissions) resolve immediately, with these exceptions:
472 * Writes to [protected paths](#protected-paths) route to the classifier even when an allow rule matches, and so do `rm` and `rmdir` removals targeting a [critical path](#critical-paths) in Claude Code v2.1.218 and later
474 * Writes to [protected paths](#protected-paths) route to the classifier even when an allow rule matches
475 * No allow rule approves `rm` and `rmdir` removals targeting a [critical path](#critical-paths)
473476 * MCP tools marked [`requiresUserInteraction`](/docs/en/mcp#require-approval-for-a-specific-tool) prompt you directly even when an allow rule matches, and so do connector tools [your organization set to `ask`](/docs/en/mcp#organization-controls-on-connector-tools) in sessions where that setting reaches Claude Code
474477 * A shell command that carries [per-command allowed domains](/docs/en/sandboxing#per-command-allowed-domains-in-auto-mode) also routes to the classifier even when an allow rule matches, because a rule approves the command, not its hosts
475478 * Ask rules that match on a command's content, such as `Bash(git push *)`, fall back to a permission prompt
476479 2. Read-only actions and file edits in your working directory are auto-approved, except writes to [protected paths](#protected-paths) and [the first read outside the working directories](#first-read-outside-the-working-directories), which prompts you
477480 * In a session with [server-side classifier review](#server-side-classifier-review), read-only and [sandboxed](/docs/en/sandboxing#sandbox-modes) shell commands wait for that review and are blocked if it flags them
478 3. Everything else goes to the classifier. The connector tools and `requiresUserInteraction` MCP tools that prompt you directly in step 1 never reach the classifier, so neither an org-required approval nor a consent step is auto-approved
481 3. Everything else goes to the classifier, apart from [critical-path removals](#critical-paths) under their default handling. The connector tools and `requiresUserInteraction` MCP tools that prompt you directly in step 1 never reach the classifier either, so neither an org-required approval nor a consent step is auto-approved
479482 4. If the classifier blocks, Claude receives the reason and tries an alternative. In most sessions the reason names the rule the classifier matched, such as `[Data Exfiltration]`, rather than giving a written explanation; see [Review denials](/docs/en/auto-mode-config#review-denials)
480483
481484 On entering auto mode, broad allow rules that grant arbitrary code execution are dropped:
from line 630
627630
628631What happens instead depends on your permission mode:
629632
630| Mode | What Claude Code does with a critical-path removal |
631| :----------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
632| `default`, `acceptEdits` | Asks you to approve it |
633| `plan` | Asks you to approve it. With [auto mode available during planning](#analyze-before-you-edit-with-plan-mode) and no bypass permissions available, sends it to the classifier instead |
634| `auto` | Sends it to the [classifier](#eliminate-prompts-with-auto-mode) |
635| `dontAsk` | Denies it |
636| `bypassPermissions` | Asks you to approve it |
633| Mode | What Claude Code does with a critical-path removal |
634| :----------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
635| `default`, `acceptEdits` | Asks you to approve it |
636| `plan` | Asks you to approve it. When [the classifier reviews commands during planning](#analyze-before-you-edit-with-plan-mode) and no bypass permissions are available, handles it as in `auto` mode |
637| `auto` | Asks you to approve it in the terminal, with a time limit. Elsewhere, denies it |
638| `dontAsk` | Denies it |
639| `bypassPermissions` | Asks you to approve it, with a time limit in the terminal |
637640
638If an explicit [ask rule](/docs/en/permissions#manage-permissions) matches the command, Claude Code asks you even in `auto` mode. In modes that ask, a [`PermissionRequest` hook](/docs/en/hooks#permissionrequest) can answer the prompt the way it answers any other.
641If an explicit [ask rule](/docs/en/permissions#manage-permissions) matches the command, Claude Code asks you instead, even in `auto` mode and without a time limit. In modes that ask, a [`PermissionRequest` hook](/docs/en/hooks#permissionrequest) can answer the prompt.
639642
643The `auto` and `bypassPermissions` handling requires Claude Code v2.1.281 or later. To turn it off, set [`CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT=1`](/docs/en/env-vars#variables) in the environment that launches Claude Code. In `auto` mode, critical-path removals then go to the classifier instead, and in `bypassPermissions` mode the prompt has no time limit.
644
645In `auto` and `bypassPermissions` modes, the terminal prompt shows a two-minute countdown:
646
647* If the countdown runs out before you answer, Claude Code denies the command and tells Claude what to do instead, so an unattended session keeps working.
648* Press any key while the prompt is open to stop the countdown and keep the prompt waiting for your answer.
649* After three of these prompts run out unanswered in a session, Claude Code stops showing them and denies further critical-path removals immediately. Sending a new message starts the count over.
650
651In `auto` mode, wherever Claude Code can't show you a terminal prompt, it denies the command immediately, for example in [non-interactive runs](/docs/en/headless) with `-p`, in [Agent SDK](/docs/en/agent-sdk/permissions) sessions, and in the VS Code extension's chat panel and the Desktop app. The denial tells Claude to report what it wanted to delete and leave the removal to you.
652
640653Claude Code treats an `rm` or `rmdir` target as a critical path when it is any of the following:
641654
642655* The filesystem root
from line 666
653666* For a variable such as `$DIR`, guard each expansion so the shell stops with an error when the variable is unset or empty, as in `rm -rf "${DIR:?}"/*`, or use a literal path
654667* For a variable that is normally set, such as `$HOME`, use a literal path
655668
656A removal whose expansions are all guarded that way isn't a critical-path removal, so in `bypassPermissions` mode it runs without a prompt.
669A removal whose expansions are all guarded that way passes this check, so in `bypassPermissions` mode it runs without a prompt unless another check in this section flags it.
670
671Claude Code also treats these targets as critical paths:
672
673* **A shell variable followed by one top-level directory name**, such as `rm -rf "$TMPDIR/mnt"`: when the variable expands empty, the command removes `/mnt`. This covers common top-level names such as `mnt`, `tmp`, `usr`, and `Users`.
674* **A variable that the same command assigns from a directory-printing substitution**, such as `D=$(pwd); rm -rf "$D"` or an assignment from `$(git rev-parse --show-toplevel)`: the value can name your working directory or repository root. A `"${D:?}"` guard doesn't clear this check, because the variable isn't empty; use a literal path instead.
675* **A backslash-only target**, such as `rm -rf "\\"`: Git Bash on Windows reads a lone backslash as the current drive's root, so the check applies on every platform.
676* **Only the output of a command substitution**, such as `rm -rf "$(pwd)"`, when the `rm` is recursive: Claude Code can't check the target before the command runs, so the prompt tells Claude to run the substitution on its own first and then remove the literal paths it prints. To turn off this one check, set [`CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT=1`](/docs/en/env-vars#variables) in the environment that launches Claude Code.
677
678When a trailing command substitution can expand empty, as in `rm -rf ~/$(cmd)`, Claude Code checks the path that would remain, your home directory in this example.
657679
658680Hiding the removal inside a subshell with `(...)`, a brace group with `{ ...; }`, command substitution with `$(...)` or backticks, or process substitution with `<(...)`, doesn't skip the check. Claude Code finds a critical-path removal whether it sits inside the nested form, as in `(rm -rf ~)` or `echo "$(rm -rf ~)"`, or elsewhere in the same command.
659681
quickstart Changed · +6 / -6 lines
from line 25
2525 <Tab title="Native Install (Recommended)">
2626 **macOS, Linux, WSL:**
2727
28 ```bash theme={null}
28 ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
2929 curl -fsSL https://claude.ai/install.sh | bash
3030 ```
3131
3232 **Windows PowerShell:**
3333
34 ```powershell theme={null}
34 ```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
3535 irm https://claude.ai/install.ps1 | iex
3636 ```
3737
3838 **Windows CMD:**
3939
40 ```batch theme={null}
40 ```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
4141 curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd
4242 ```
4343
from line 55
5555 </Tab>
5656
5757 <Tab title="Homebrew">
58 ```bash theme={null}
58 ```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
5959 brew install --cask claude-code
6060 ```
6161
from line 67
6767 </Tab>
6868
6969 <Tab title="WinGet">
70 ```powershell theme={null}
70 ```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
7171 winget install Anthropic.ClaudeCode
7272 ```
7373
from line 173
173173
174174Claude Code finds the appropriate file and shows you the change. If it asks before making the change, select **Yes** to approve.
175175
176Auto mode is the [built-in starting permission mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for interactive terminal sessions on Pro, Max, and Team plans: a classifier reviews actions instead of you, and Claude edits most files and runs most commands without asking you. On other plans, Manual mode is the built-in starting permission mode. For the session you start right after installing, see [First session after an install or upgrade](/docs/en/env-vars#first-session-after-an-install-or-upgrade).
176With Claude Code v2.1.283 or later, auto mode is the [built-in starting permission mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for interactive terminal sessions: a classifier reviews actions instead of you, and Claude edits most files and runs most commands without asking you. On earlier versions, auto mode is the built-in starting permission mode only on Pro, Max, and Team plans. For the session you start right after installing, see [First session after an install or upgrade](/docs/en/env-vars#first-session-after-an-install-or-upgrade).
177177
178178<Note>
179179 Your settings or your organization can set a different starting permission mode. [Which permission mode a session starts in](/docs/en/permission-modes#which-mode-a-session-starts-in) lists what does. Press `Shift+Tab` at any time to switch the permission mode of the session you're in.
settings-reference Changed · +4 / -3 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 1468
14681468
14691469### `useAutoModeDuringPlan`
14701470
1471Choose whether Claude Code uses the auto mode classifier to review shell commands in plan mode. With the default `true`, the classifier reviews each command during planning when auto mode is available and you see no prompt. Set `false` to get a permission prompt for every command outside the built-in read-only set. Appears in `/config` as **Use auto mode during plan**.
1471Choose whether Claude Code uses the auto mode classifier to review shell commands in plan mode. With the default `true`, the classifier reviews each command during planning when auto mode is available and you see no prompt, except for [critical-path removals](/docs/en/permission-modes#critical-paths). Set `false` to get a permission prompt for every command outside the built-in read-only set. Appears in `/config` as **Use auto mode during plan**.
14721472
14731473* **Scope**: [`User, local, or managed`](#scopes). A repository can't turn it off for you.
14741474* **Type**: Boolean
1475 * `true`: the same as unset; when auto mode is available, the classifier reviews each shell command during planning instead of prompting you for it. A `false` in any of these files still turns it off
1475 * `true`: the same as unset; when auto mode is available, the classifier reviews each shell command during planning instead of prompting you for it, except [critical-path removals](/docs/en/permission-modes#critical-paths). A `false` in any of these files still turns it off
14761476 * `false`: you get a permission prompt for every command outside the built-in read-only set
14771477* **Default**: `true`
14781478
from line 1614
16141614
16151615### `permissions.defaultMode`
16161616
1617Set the [permission mode](/docs/en/permission-modes) new sessions start in. When you leave it unset, sessions start in the [built-in default](/docs/en/permission-modes#which-mode-a-session-starts-in) for your plan and surface.
1617Set the [permission mode](/docs/en/permission-modes) new sessions start in. When you leave it unset, sessions start in the [built-in default](/docs/en/permission-modes#which-mode-a-session-starts-in) for your surface.
16181618
16191619* **Scope**: [`Any file`](#scopes). `auto` and `bypassPermissions` don't take effect from project or local settings, so set them in `~/.claude/settings.json` instead. Before v2.1.257, `bypassPermissions` took effect from any file. For conversations the VS Code extension starts, Claude Code reads only user, managed, and `--settings` values.
16201620* **Type**: string, one of:
from line 2867
28672867* [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/sessions#name-the-project-directory-yourself), which Claude Code reads from the launch environment only, is ignored from every file; requires v2.1.234 or later.
28682868* [`CLAUDE_CODE_RESTRICTED`](/docs/en/env-vars#variables), which Claude Code reads from the launch environment only, is ignored from every file.
28692869* [`CLAUDE_CODE_DISABLE_POWERSHELL_CMD_RM_DENY`](/docs/en/env-vars#variables), which Claude Code reads from the launch environment only, is ignored from every file. The variable requires Claude Code v2.1.283 or later.
2870* [`CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT` and `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT`](/docs/en/env-vars#variables), which Claude Code reads from the launch environment only, are ignored from every file.
28702871
28712872### `fileCheckpointingEnabled`
28722873
from line 3147
31463147
31473148#### Command input and output
31483149
3149Claude Code runs the command with the same environment variables as [hooks](/docs/en/hooks), including `CLAUDE_PROJECT_DIR`, and stops waiting after five seconds. The command receives JSON on stdin with a `query` field holding what you've typed so far:
3150
3151```json theme={null}
3152{"query": "src/comp"}
3153```
3154
3155Print newline-separated file paths to stdout. Claude Code shows at most 15:
3156
3157```t
3150Claude Code runs the comm
admin-setup Changed · +1 / -1 lines
from line 85
8585| :------------------------------------------------------------------------------ | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------- |
8686| [Permission rules](/docs/en/permissions) | Allow, ask, or deny specific tools and commands | `permissions.allow`, `permissions.deny` |
8787| [Permission lockdown](/docs/en/permissions#managed-only-settings) | Make managed settings the [only settings source of permission rules](/docs/en/settings-reference#allowmanagedpermissionrulesonly). Disable `--dangerously-skip-permissions` | `allowManagedPermissionRulesOnly`, `permissions.disableBypassPermissionsMode` |
88| [Starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) | Choose the permission mode your developers' terminal sessions start in instead of the built-in starting permission mode, or remove auto mode. The VS Code extension reads a `defaultMode` you set only on Pro, Max, and Team plans; [Switch permission modes](/docs/en/permission-modes#switch-permission-modes) lists what the extension reads | `permissions.defaultMode`, `permissions.disableAutoMode` |
88| [Starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) | Choose the permission mode your developers' terminal sessions start in instead of the built-in starting permission mode, or remove auto mode. [Switch permission modes](/docs/en/permission-modes#switch-permission-modes) lists when the VS Code extension reads a `defaultMode` you set | `permissions.defaultMode`, `permissions.disableAutoMode` |
8989| [Sandboxing](/docs/en/sandboxing) | OS-level filesystem and network isolation with domain allowlists | `sandbox.enabled`, `sandbox.network.allowedDomains` |
9090| [Managed policy CLAUDE.md](/docs/en/memory#deploy-organization-wide-claude-md) | Org-wide instructions loaded in every session, can't be excluded | File at the managed policy path |
9191| [MCP server control](/docs/en/managed-mcp) | Restrict which MCP servers users can add or connect to, deploy a fixed set, or provide remote servers to every user alongside their own | `allowedMcpServers`, `deniedMcpServers`, `allowManagedMcpServersOnly`, `managedMcpServers`, or a deployed `managed-mcp.json` file |
auto-mode-config Changed · +1 / -1 lines
from line 281
281281
282282By default, narrow Bash and PowerShell allow rules such as `Bash(npm test)` stay in effect in auto mode. Claude Code resolves them before the classifier runs, unless the command carries [per-command allowed domains](/docs/en/sandboxing#per-command-allowed-domains-in-auto-mode). Claude Code suspends only the broad rules that grant arbitrary code execution, such as `Bash(*)` or wildcarded interpreters, together with every rule that names [`Monitor`](/docs/en/tools-reference#monitor-tool), because Monitor commands run through the shell. This means a narrow rule can still let a destructive argument through without the classifier seeing it, for example a script path or flag the rule's prefix didn't anticipate.
283283
284Set `autoMode.classifyAllShell` to `true` to suspend every Bash and PowerShell allow rule while auto mode is active, so the classifier evaluates every shell command regardless of your allow list.
284Set `autoMode.classifyAllShell` to `true` to suspend every Bash and PowerShell allow rule while auto mode is active, so the classifier evaluates every shell command regardless of your allow list, except [critical-path removals](/docs/en/permission-modes#critical-paths).
285285
286286```json theme={null}
287287{
feature-availability Changed · +1 / -1 lines
from line 205
205205</table>
206206
207207<span id="fn1" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>1</sup> On Google Cloud's Agent Platform, web search is available for Claude 4 models and later.<br />
208<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and the Fable models. See [Auto mode configuration](/docs/en/auto-mode-config). The built-in starting permission mode on these providers is Manual. See [which mode a session starts in](/docs/en/permission-modes#which-mode-a-session-starts-in). In v2.1.158 through v2.1.206, auto mode on these providers also required setting `CLAUDE_CODE_ENABLE_AUTO_MODE=1`; v2.1.207 removed the requirement.<br />
208<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5, Opus 4.7 or later, and the Fable models. See [Auto mode configuration](/docs/en/auto-mode-config). For the permission mode a session on these providers starts in, see [Which mode a session starts in](/docs/en/permission-modes#which-mode-a-session-starts-in). In v2.1.158 through v2.1.206, auto mode on these providers also required setting `CLAUDE_CODE_ENABLE_AUTO_MODE=1`; v2.1.207 removed the requirement.<br />
209209<span id="fn3" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>3</sup> Subject to your agreement with the cloud provider.<br />
210210<span id="fn4" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>4</sup> Dashboard and API only. [Contribution metrics](/docs/en/analytics#enable-contribution-metrics) requires a claude.ai Team or Enterprise organization.<br />
211211<span id="fn5" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>5</sup> Requires Claude Code v2.1.224 or later on macOS and Linux, including Linux inside WSL 2. On native Windows, requires Claude Code v2.1.234 or later. With API key authentication, messaging is same-machine only. On Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, and Microsoft Foundry, messaging is same-machine only and requires Claude Code v2.1.248 or later. Claude can find your [cloud sessions](/docs/en/claude-code-on-the-web) and your sessions on other machines only from a session that is connected to [Remote Control](/docs/en/remote-control). To connect, you need a claude.ai sign-in and the other [Remote Control requirements](/docs/en/remote-control#requirements). See [Message sessions on other machines](/docs/en/cross-session-messaging#message-sessions-on-other-machines).
glossary Changed · +1 / -1 lines
from line 50
5050
5151### Auto mode
5252
53A [permission mode](#permission-mode) where a separate classifier model reviews actions instead of you, so Claude Code runs most of them without asking you. Claude Code still asks you before actions your explicit ask rules match. On Pro, Max, and Team plans, auto mode is the [built-in starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) for interactive terminal and VS Code sessions. The classifier blocks scope escalation, untrusted infrastructure, and [prompt injection](#prompt-injection). Tool results are stripped from what it sees, so hostile content in a file or web page can't manipulate it directly.
53A [permission mode](#permission-mode) where a separate classifier model reviews actions instead of you, so Claude Code runs most of them without asking you. Claude Code still asks you before actions your explicit ask rules match. With Claude Code v2.1.283 or later, auto mode is the [built-in starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) for interactive terminal and VS Code sessions, and on earlier versions only on Pro, Max, and Team plans. The classifier blocks scope escalation, untrusted infrastructure, and [prompt injection](#prompt-injection). Tool results are stripped from what it sees, so hostile content in a file or web page can't manipulate it directly.
5454
5555Learn more: [Eliminate prompts with auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)
5656
how-claude-code-works Changed · +1 / -1 lines
from line 152
152152
153153Choose a permission mode to set what Claude can do without asking you. Press `Shift+Tab` to cycle through the permission modes:
154154
155* **Auto**: a classifier reviews most actions in the background and blocks the risky ones instead of asking you. On Pro, Max, and Team plans, it's the [built-in starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) for interactive terminal and VS Code sessions
155* **Auto**: a classifier reviews most actions in the background and blocks the risky ones instead of asking you. With Claude Code v2.1.283 or later, it's the [built-in starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) for interactive terminal and VS Code sessions, and on earlier versions only on Pro, Max, and Team plans
156156* **Manual**: Claude asks before file edits and shell commands
157157* **Accept edits**: Claude edits files and runs common filesystem commands like `mkdir` and `mv` without asking, still asks for other commands
158158* **Plan**: Claude explores and proposes a plan without editing your source files
remote-control Changed · +1 / -1 lines
from line 299
299299
300300Remote Control and [cloud sessions](/docs/en/claude-code-on-the-web) both use the claude.ai/code interface. The key difference is where the session runs: Remote Control executes on your machine, so your local MCP servers, tools, and project configuration stay available. A cloud session executes on cloud infrastructure, Anthropic-managed by default.
301301
302Use Remote Control when you're in the middle of local work and want to keep going from another device. Use a cloud session when you want to start a task without any local setup, work on a repo you don't have cloned, or run multiple tasks in parallel.
302Use Remote Control when you're in the middle of local work and want to keep going from another device. Use a cloud session when you want to start a task without any local setup, work on a repo you don't have cloned, or run multiple tasks in parallel. A [project](/docs/en/claude-projects) combines the two: its threads run in the cloud, and it uses Remote Control to [run a thread on your computer](/docs/en/claude-projects#run-a-thread-on-your-own-computer) when you ask for one there.
303303
304304## Mobile push notifications
305305
sub-agents Changed · +1 / -1 lines
from line 559
559559
560560#### Permission modes
561561
562Set `permissionMode` to choose the permission mode a subagent runs in. Use the modes' config values, so Manual mode is `default`. If you leave it unset, the subagent inherits the main conversation's mode, which starts as [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) on Pro, Max, and Team plans unless your settings or your organization change it.
562Set `permissionMode` to choose the permission mode a subagent runs in. Use the modes' config values, so Manual mode is `default`. If you leave it unset, the subagent inherits the main conversation's [permission mode](/docs/en/permission-modes).
563563
564564The main conversation's permission mode decides whether Claude Code uses the value you set:
565565
tools-reference Changed · +1 / -1 lines
from line 9
99To add custom tools, connect an [MCP server](/docs/en/mcp). To extend Claude with reusable prompt-based workflows, write a [skill](/docs/en/skills), which runs through the existing `Skill` tool rather than adding a new tool entry.
1010
1111<Info>
12 On Pro, Max, and Team plans, Claude Code starts sessions in [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), where a classifier decides most of these prompts instead of you. The `Permission required` column shows whether the tool prompts in [Manual mode](/docs/en/permission-modes) for paths inside the working directory. File-access tools marked No, including `Read`, `Grep`, and `Glob`, still prompt for paths outside the [working directory and additional directories](/docs/en/permissions#working-directories). `Bash` is marked Yes but runs a built-in set of [read-only commands](/docs/en/permissions#read-only-commands) without prompting.
12 In [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode), a classifier decides most permission prompts instead of you. The `Permission required` column shows whether the tool prompts in [Manual mode](/docs/en/permission-modes) for paths inside the working directory. File-access tools marked No, including `Read`, `Grep`, and `Glob`, still prompt for paths outside the [working directory and additional directories](/docs/en/permissions#working-directories). `Bash` is marked Yes but runs a built-in set of [read-only commands](/docs/en/permissions#read-only-commands) without prompting.
1313</Info>
1414
1515| Tool | Description | Permission required |
vs-code Changed · +2 / -2 lines
from line 97
9797
9898The prompt box supports several features:
9999
100* **Permission modes**: click the mode indicator at the bottom of the prompt box to switch permission modes. On Pro, Max, and Team plans, Auto is the built-in starting permission mode. See [how the extension chooses the starting permission mode](/docs/en/permission-modes#switch-permission-modes) for what changes that, and every permission mode the indicator offers.
100* **Permission modes**: click the mode indicator at the bottom of the prompt box to switch permission modes. With Claude Code v2.1.283 or later, Auto is the built-in starting permission mode, and on earlier versions only on Pro, Max, and Team plans. See [how the extension chooses the starting permission mode](/docs/en/permission-modes#switch-permission-modes) for what changes that, and every permission mode the indicator offers.
101101 * **Auto**: a classifier reviews most actions instead of asking you. See [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for what it reviews and blocks.
102102 * **Manual**: Claude asks permission before file edits and most shell commands.
103103 * **Plan**: Claude describes what it will do and waits for approval before making changes. VS Code automatically opens the plan as a full Markdown document where you can add inline comments to give feedback before Claude begins.
from line 464
464464The extension has two types of settings:
465465
466466* **Extension settings** in VS Code: control the extension's behavior within VS Code. Open with `Cmd+,` (Mac) or `Ctrl+,` (Windows/Linux), then go to Extensions → Claude Code. You can also type `/` and select **General config…** to open settings.
467* **Claude Code settings** in `~/.claude/settings.json`: shared between the extension and CLI. Use it for allowed commands, environment variables, hooks, and MCP servers. On Pro, Max, and Team plans, it's also one input to the permission mode conversations start in. [Switch permission modes](/docs/en/permission-modes#switch-permission-modes) lists the order. See [Settings](/docs/en/settings) for details.
467* **Claude Code settings** in `~/.claude/settings.json`: shared between the extension and CLI. Use it for allowed commands, environment variables, hooks, and MCP servers. With Claude Code v2.1.283 or later, it's also one input to the permission mode conversations start in, and on earlier versions only on Pro, Max, and Team plans. [Switch permission modes](/docs/en/permission-modes#switch-permission-modes) lists the order. See [Settings](/docs/en/settings) for details.
468468
469469<Tip>
470470 Add `"$schema": "https://json.schemastore.org/claude-code-settings.json"` to your `settings.json` to get autocomplete and inline validation for all available settings directly in VS Code.