Skip to main content
A 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, a second model, the classifier, reviews actions instead of you; how the classifier evaluates actions lists which actions it reviews and which skip it. On Pro, Max, and Team plans, the built-in starting permission mode is auto mode. 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.

​
Available modes

Each mode makes a different tradeoff between convenience and oversight. The table below shows what Claude can do without a permission prompt in each mode. Manual mode appears under its config value, default. The mode that reviews every action is named Manual in the CLI, in claude --help, in the VS Code and JetBrains extensions, and in the desktop app. Its config value is default, which is what hooks and SDK integrations use. The CLI accepts manual as an alias wherever you type the value, for example claude --permission-mode manual or "defaultMode": "manual". The Manual label and the manual alias require Claude Code v2.1.200 or later. The desktop app’s label doesn’t depend on your CLI version. Writes to protected paths are never auto-approved except in bypassPermissions mode and in plan-mode sessions where bypass permissions are available, meaning sessions started in a way that puts bypassPermissions in the mode cycle. Modes set the baseline. Layer permission rules on top to pre-approve or block specific tools. Deny rules block in every mode, including bypassPermissions. Deny and ask rules don’t apply to EndConversation as long as Claude still has at least one other tool it can call. Allow rules have no effect in bypassPermissions.

​
Actions no mode auto-approves

Claude Code doesn’t auto-approve the following in any mode, including bypassPermissions. Each bullet links to the section that says what happens instead in each mode:

​
Common setups

Permission modes decide whether Claude asks before an action, and the Bash sandbox and outer isolation boundaries decide what an action can reach once it runs. Each row below pairs a goal with the flags or settings that get you there and the isolation it needs, as a starting point. Available modes lists what runs without a prompt in each mode, and the per-mode section each row links carries the full behavior. The Bash sandbox and auto mode work independently and combine, except in plan mode, where auto-allow doesn’t widen approvals. For the full interaction, see How sandboxing relates to permissions and permission modes and How isolation relates to permission modes.

​
Which mode a session starts in

When you start a new session in a terminal, Claude Code takes the permission mode from the first of these that applies:
  1. The --permission-mode flag, or --dangerously-skip-permissions
  2. permissions.defaultMode in a settings file. An "auto" value in .claude/settings.json or .claude/settings.local.json doesn’t take effect, and Claude Code then uses the built-in default rather than a defaultMode from ~/.claude/settings.json. The other values apply from any settings file
  3. The built-in default
Conversations the VS Code extension starts follow the extension’s own list in Switch permission modes. A session you resume keeps the permission mode it was in unless you pass --permission-mode or --dangerously-skip-permissions; what a resumed session restores lists the exceptions. The 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. The 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. In those same two cases, feature-flag fetching off or the first session after an install or upgrade, the VS Code extension ignores every settings file when choosing the starting permission mode and uses default. When 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 a settings file turns it off or the model doesn’t support it. The first time the built-in default starts one of your sessions in auto mode, Claude Code shows a notice that links to this page:
  • In a terminal, once, at the top of the session
  • In the VS Code extension, as a card on the new-conversation screen that stays until you dismiss it
On Pro, Max, and Team plans, if your ~/.claude/settings.json sets a defaultMode other than auto and no other settings file sets one, your sessions keep starting in that mode. Claude Code asks once, in the terminal or in the VS Code extension, whether to change the setting to auto mode. If you decline, your setting stays as it is.

​
Start in a different permission mode

You can set the starting permission mode for one session, or as a default for every session on a machine, in a project, or in an organization. When more than one settings file sets permissions.defaultMode, settings precedence decides, so a project or managed value outranks ~/.claude/settings.json. To change the permission mode of a session that’s already running, see Switch permission modes. This example makes every terminal session on your machine start in Manual mode, whose config value is default. Save it in ~/.claude/settings.json:
The next session you start shows ⏸ manual mode on in the status bar.

​
Switch permission modes

Each interface has its own control for switching permission modes during a session and its own way of choosing the permission mode new sessions start in. Asking Claude in chat to change the permission mode doesn’t work. Select your interface to see its controls.
During a session: press Shift+Tab to cycle permission modes. From auto, the first press switches to default, and the cycle then runs default → acceptEdits → plan → back to default. Optional modes, described below, slot in after plan. The status bar shows the active mode as a gray ⏸ manual mode on for default, or as ⏵⏵ accept edits on, ⏸ plan mode on, ⏵⏵ auto mode on, ⏵⏵ don't ask on, or ⏵⏵ bypass permissions on.Not every mode is in the default cycle:
  • auto: appears when your account meets the auto mode requirements; cycling to it switches permission modes without a confirmation prompt
  • bypassPermissions: appears after you start with --permission-mode bypassPermissions, --dangerously-skip-permissions, --allow-dangerously-skip-permissions, or permissions.defaultMode: "bypassPermissions" in settings; the --allow- variant adds the permission mode to the cycle without activating it
  • dontAsk: never appears in the cycle; set it with --permission-mode dontAsk
Enabled optional modes slot in after plan, with bypassPermissions first and auto last. If you have both enabled, you will cycle through bypassPermissions on the way to auto.At startup: pass the permission mode as a flag.
As a default: set permissions.defaultMode at the scope you want, as described in Start in a different permission mode.The same --permission-mode flag works with -p for non-interactive runs.

​
Auto-approve file edits with acceptEdits mode

acceptEdits mode lets Claude create and edit files in your working directory without prompting. The status bar shows ⏵⏵ accept edits on while this mode is active. In addition to file edits, acceptEdits mode auto-approves common filesystem Bash commands: mkdir, touch, rm, rmdir, mv, cp, and sed. These commands are also auto-approved when prefixed with safe environment variables such as LANG=C or NO_COLOR=1, or process wrappers such as timeout, nice, or nohup. Like file edits, auto-approval applies only to paths inside your working directory or additionalDirectories. Paths outside that scope, writes to protected paths, rm and rmdir removals targeting a critical path, and all other Bash commands except the built-in read-only set still prompt. When the PowerShell tool is enabled, acceptEdits mode also auto-approves Set-Content, Add-Content, Clear-Content, and Remove-Item on in-scope paths, along with their common aliases. The same scope and protected-path rules apply, and Remove-Item gets its own check. A positional argument that contains a quote character, such as the apostrophe in Set-Content .\notes.txt "It's done", still prompts even on in-scope paths, because Claude Code can’t statically validate an argument whose quoted and unquoted readings differ. Pass the content through a named parameter such as -Value to avoid the prompt. Use acceptEdits when you want to review changes in your editor or via git diff after the fact rather than approving each edit inline. Press Shift+Tab once from Manual mode to enter it, or start with it directly:

​
Analyze before you edit with plan mode

Plan 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 sessions with bypass permissions available, edits stay blocked until you approve the plan. When auto mode 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 prompt for approval, including when the sandbox’s auto-allow mode is enabled. In sessions with bypass permissions available, neither the classifier nor a prompt applies to planning commands; 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. Enter plan mode by pressing Shift+Tab or prefixing a single prompt with /plan. You can also start in plan mode from the CLI:
Press Shift+Tab again to leave plan mode without approving a plan.

​
Review and approve a plan

When the plan is ready, Claude presents it and asks how to proceed. From that prompt you can choose:
  • Yes, and use auto mode: approve and start in auto mode. When auto mode is unavailable, this option reads Yes, auto-accept edits. If you started the session with bypass permissions enabled, the option reads Yes, and switch to BYPASS PERMISSIONS (no further prompts) for this session instead.
  • Yes, manually approve edits: approve and review each edit individually.
  • No, keep planning: stay in plan mode and tell Claude what to change.
Approving a plan exits plan mode and switches the session to the permission mode each approve option describes, so Claude starts editing. To plan again, cycle back to plan mode with Shift+Tab, or prefix your next prompt with /plan. Press Ctrl+G to open the proposed plan in your default text editor and edit it directly before Claude proceeds. When showClearContextOnPlanAccept is enabled, the list gains a first option that approves the plan and clears the planning context. Accepting a plan also gives the session a generated title based on the plan, unless you’ve already named the session.

​
Set plan mode as the default

To make plan mode the default for a project’s terminal sessions, set defaultMode in .claude/settings.json. Conversations the VS Code extension starts don’t read project settings for the starting permission mode. There, set claudeCode.initialPermissionMode to plan in your VS Code user settings instead. This example sets the project default:

​
Eliminate permission prompts with auto mode

Auto 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 still force a prompt. On Pro, Max, and Team plans, auto mode is the built-in starting permission mode. The classifier also reviews each message Claude sends to another agent with SendMessage, whether plain text or a structured agent team message, before Claude Code delivers it, both in auto mode and in plan mode while the classifier reviews commands; the send review requires Claude Code v2.1.222 or later. The classifier also reviews and approves or blocks rm and rmdir removals targeting a critical path, such as rm -rf / and rm -rf ~, including when the removal sits inside command or process substitution. Auto 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 instead.
Auto mode reduces permission prompts but does not guarantee safety. Use it for tasks where you trust the general direction, not as a replacement for review on sensitive operations.
Auto mode is available only when your account meets all of these requirements:
  • Plan: All plans.
  • Organization: on Team and Enterprise, auto mode is available by default. Administrators can turn it off for the organization by setting permissions.disableAutoMode to "disable" in managed settings.
  • Model: on the Anthropic API and Claude Platform on AWS, Claude Opus 4.6 or later, Sonnet 4.6 or later, or Fable 5. On Amazon Bedrock, Google Cloud’s Agent Platform, Microsoft Foundry, and signed-in Claude apps gateway sessions, only Claude Sonnet 5, Opus 4.7 or later, and Fable 5. Older models, including Sonnet 4.5, Opus 4.5, Haiku, and claude-3 models, are not supported on any provider.
  • Provider: available by default on the Anthropic API, Claude Platform on AWS, Amazon Bedrock, Google Cloud’s Agent Platform, Microsoft Foundry, and signed-in Claude apps gateway sessions.
If Claude Code reports auto mode as unavailable, one of these requirements is unmet; this is not a transient outage. A separate message that names a model and says auto mode “cannot determine the safety” of an action means a classifier request failed; that failure is usually transient, but on Amazon Bedrock it can repeat until your account can invoke the named model. See the error reference for the causes and what to do. If you set defaultMode: "auto" in settings and a terminal session starts in Manual mode with no error, the setting is likely in .claude/settings.json or .claude/settings.local.json. In Claude Code v2.1.142 and later, auto doesn’t take effect from those files. Move it to ~/.claude/settings.json. For a conversation the VS Code extension started, check the extension’s own list in Switch permission modes instead.

​
Auto mode on Bedrock, Agent Platform, or Foundry

On Amazon Bedrock, Google Cloud’s Agent Platform, Microsoft Foundry, and signed-in 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, which is Manual unless you change it, and conversations in the VS Code extension 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 Fable 5 are supported on these providers. To 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 covers what outranks that pick. The /doctor checkup proposes this user-settings default on these providers the same way it does on the Anthropic API. To prevent developers from using auto mode, set disableAutoMode to "disable" in managed settings. This removes auto from the Shift+Tab cycle, and a session started with --permission-mode auto starts in Manual instead. In 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.

​
What the classifier blocks by default

The classifier trusts your working directory and the remotes that were configured for it when the session started. A remote added or repointed during the session with git remote add or git remote set-url isn’t trusted, and everything else is treated as external until you configure trusted infrastructure. Before v2.1.200, remotes added mid-session were also trusted. Blocked by default:
  • Downloading and executing code, like curl | bash
  • Sending sensitive data to external endpoints
  • Production deploys and migrations
  • Mass deletion on cloud storage
  • Granting IAM or repo permissions
  • Modifying shared infrastructure
  • Irreversibly destroying files that existed before the session
  • Force push
  • Committing or pushing a change that would send secrets or sensitive data outside the repository when it runs, or widen what a deploy exposes. This covers a CI workflow or deploy configuration that hands a secret to a destination that doesn’t already receive it, a script or setup step that reads a secret store and sends the data out, and a config change that widens what a deploy publishes, such as a registry, visibility, artifact, or sourcemap setting. The check applies on any branch, applies even when the repository is public, and fires when the change lands, whether or not that landing triggers the pipeline; clearing it requires naming the execution effect, not only the commit or push. Before v2.1.211, this check was scoped to the default branch instead: a push there was blocked when it carried sensitive content, changes concealed or misdescribed relative to what you asked for, content ported in from outside the repository, or routed around a review you asked for
  • git reset --hard, git checkout -- ., git restore ., git clean -fd, git stash drop, or git stash clear, which the classifier presumes would discard uncommitted changes
  • git commit --amend when the commit at HEAD was not created in this session
  • From v2.1.198, git commit --amend when the commit at HEAD has already been pushed. A message-only reword is not blocked: --amend -m with nothing newly staged, on a commit that Claude created during this session
  • terraform destroy, pulumi destroy, cdk destroy, or terragrunt destroy, and applying a plan that destroys resources
Claude Code v2.1.195 and later block more categories by default. Several depend on environment entries, such as sensitive remote targets and protected IaC scopes, that you can narrow to concrete names.
  • Writing to a secret manager, or changing DNS records or TLS certificates
  • Merging a pull request no human has approved, approving Claude’s own pull request, or disabling CI checks
  • Posting a comment that is itself a command to automation, such as atlantis apply or a bot’s /deploy or /merge
  • Toggling, ramping, or deleting a production feature flag
  • Applying infrastructure changes to a protected IaC scope, or draining and removing cluster nodes
  • Writes to a shared compute cluster that reach beyond the resource you named, such as a label selector or --all that catches other users’ jobs
  • Creating Kubernetes resources that run on every node or intercept cluster traffic, such as DaemonSets and admission webhooks
  • Interactive shells or port-forwards into a sensitive remote target
  • Opening a tunnel or reverse shell that makes a local service reachable from the public internet
  • Printing a live credential or token into the transcript or a file
  • Accessing a location listed as a sensitive data location in your environment, or copying data out of one. As of v2.1.198 this also blocks sending data from one to an audience the entry excludes
  • Routing a package install around your internal package registry to a public registry. As of v2.1.198, this also applies when you’ve told Claude an internal registry or mirror exists in the conversation, not only when one is listed in your environment
  • Running a command with a flag that disarms a safety guard, like --insecure
  • Launching an autonomous agent loop that runs without human approval or a sandbox, such as one started with --dangerously-skip-permissions or --no-sandbox. As of v2.1.198 this also covers running a third-party agent or eval harness with isolation and per-action approval disabled, such as a runner started with --yes-always
  • Claude in Chrome browser actions that could send page content, cookies, or credentials off-origin
Claude Code v2.1.198 and later also block these by default:
  • Deleting files in /tmp, $TMPDIR, or another shared scratch or cache directory by wildcard, glob, or age filter rather than by a specific named path
  • Including sensitive details in content sent, uploaded, published, or written to other people or shared systems, when your own message didn’t authorize those details for that recipient. PR and issue bodies, commit messages, and comments count as this kind of outbound content when the repository is outside the trust boundary or public, including your organization’s own public repositories; internal file paths, code names, live API response data such as emails or account identifiers, and infrastructure identifiers count as sensitive details. The PR, issue, and commit-message scoping requires Claude Code v2.1.200 or later. Live personal data from an API response in a PR or issue body, such as an email address, an account or organization identifier, or a usage metric, requires you to name those details and the recipient regardless of the repository’s visibility or trust boundary. That check requires Claude Code v2.1.203 or later
  • Sending keystrokes to Claude Code’s own tmux pane to drive its own interface, which the classifier treats as Claude changing its own permissions or oversight
Claude Code v2.1.200 and later also block these by default:
  • Commenting out, deleting, or force-passing a test or assertion that guards security behavior, such as auth, access control, input validation, or sandboxing
  • Deleting or tearing down a stateful resource Claude didn’t create in the session, when no more specific deletion rule applies and you didn’t name that resource
  • Repointing an API base URL, proxy endpoint, webhook receiver, or registry mirror at a third-party host that doesn’t fit the task, including in example files like .env.example
  • Changing where pushes go with git remote set-url or git remote add, unless you named the new remote
  • Pushing secrets or personal or entrusted data to a repository known to be public, or pushing confidential material there that isn’t part of that repository’s own work. A dotfiles repository’s own subject matter is the one exception for personal or entrusted data, and content from a private repository reaching any public surface is blocked the same way; both refinements require Claude Code v2.1.203 or later. Before v2.1.203, personal data was grouped with confidential material and blocked only when it wasn’t part of that repository’s own work. When a repository’s visibility isn’t established, the classifier doesn’t block on that alone; it judges the content against the other rules instead
  • Opening a pull request against a different repository or organization, forking with gh repo fork, or pushing to a third-party repository, unless you named that external target
Claude Code v2.1.203 and later also block these by default:
  • Content from a sensitive local store, or from a file whose name, path, or type marks it as sensitive, entering a commit, a push, PR or issue text, a gist or paste, or a package publish, unless you named both the source and the destination. Session transcripts and conversation logs, credential and configuration dot-folders such as SSH keys, cloud credentials, browser profiles, and shell history, and user-data exports all count, and the repository being private doesn’t clear it
Claude Code v2.1.205 and later also block these by default:
  • 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
  • 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
Allowed by default:
  • Local file operations in your working directory
  • Installing dependencies declared in your lock files or manifests
  • Reading .env and sending credentials to their matching API
  • Read-only HTTP requests
  • Pushing to any branch of the repository you’re working in, including the default branch. A non-default branch whose name marks it as a deploy or publication target, such as production or gh-pages, isn’t covered: the classifier judges a push there on its own terms. The push’s content is still checked against the other rules, permissions.deny rules can still block pushes to specific branches outright in every mode, and the remote’s own branch protection still applies. Before v2.1.211, only pushes to the branch you started on, branches Claude created, and routine pushes to the default branch were allowed by default, and before v2.1.203 any direct push to the default branch was blocked
Claude Code v2.1.195 and later also allow these by default:
  • Deleting the exact jobs Claude created earlier in the same session
  • Reading, reviewing, or writing security-related code, configs, and threat models as part of your task
  • Messages between agents working together in the same multi-agent session
  • Sending data to the trusted domains, buckets, and services you list in environment. This covers data flow only, not destructive or credential operations on the same infrastructure
  • Claude in Chrome navigation to a trusted internal domain, localhost, or a URL you named
Sandbox network access requests are routed through the classifier rather than allowed by default. As of v2.1.198, the classifier reuses its verdict for a network host and port instead of re-running on every connection:
  • An allow is reused until new content enters the conversation, at which point that host is checked again
  • Claude Code v2.1.234 and later reuse a deny caused by the conversation outgrowing the classifier’s context window until new content enters the conversation, or until compaction shrinks what the classifier reads. Claude Code then checks the host again
  • A deny that the classifier reached by evaluating the request lasts for the turn in the interactive CLI. In non-interactive mode and Agent SDK sessions, Claude Code reuses that deny for the rest of the run, because those sessions have no turn boundary
  • Changing your permission mode or rules drops all cached verdicts
Run claude auto-mode defaults to print the full rule lists as JSON. If routine actions get blocked, an administrator can add trusted repos, buckets, and services via the autoMode.environment setting: see Configure auto mode. Pushing to any branch of the repository you’re working in and creating a pull request that matches your request run without a prompt, unless the change would send secrets or sensitive data outside the repository or the pull request targets a different repository or organization, the cases the blocked list covers. To require a human checkpoint before these actions while staying in auto mode, add permissions.ask rules: see Common boundaries.

​
Boundaries you state in conversation

The classifier treats boundaries you state in the conversation as a block signal. If you tell Claude “don’t push” or “wait until I review before deploying”, the classifier blocks matching actions even when the default rules would allow them. A boundary stays in force until you lift it in a later message. Claude’s own judgment that a condition was met does not lift it. Boundaries are not stored as rules. The classifier re-reads them from the transcript on each check, so a boundary can be lost if context compaction removes the message that stated it. For a hard guarantee, add a deny rule instead.

​
When auto mode falls back

When auto mode can’t approve your session’s actions, what happens depends on the case:
  • A blocked action: Claude Code shows a notification and lists the action in /permissions under the Recently denied tab, where you can press r to retry it with a manual approval. When the classifier produces no verdict on the action, because a safety check separate from auto mode refused the classifier’s own request or its response didn’t parse, Claude Code denies the action without the notification or the Recently denied entry.
  • Repeated blocks: if the classifier blocks an action 3 times in a row or 20 times total, auto mode pauses and Claude Code resumes prompting. Approving the prompted action resumes auto mode. These thresholds are not configurable. Any allowed action resets the consecutive counter, while the total counter persists for the session and resets only when its own limit triggers a fallback. Claude Code doesn’t count a denial toward either threshold when a safety check separate from auto mode refuses the classifier’s own request; the linked entry covers how Claude Code handles those denials.
  • Sessions that can’t prompt: a non-interactive -p run without a --permission-prompt-tool has no prompt to fall back to. When repeated blocks reach a threshold, the action doesn’t run and Claude keeps working, in the main conversation and in its subagents alike. The same applies when a safety check separate from auto mode refuses the classifier’s request. Claude Code doesn’t stop the run in either case.
  • A mode switch during a check: if you switch permission modes while a classifier check is pending, Claude Code discards a verdict the new mode wouldn’t have requested rather than applying it: you’re prompted for approval instead, or the action is auto-denied in dontAsk mode.
Repeated blocks usually mean the classifier is missing context about your infrastructure. Use /feedback to report false positives, or have an administrator configure trusted infrastructure.
Each action goes through a fixed decision order. The first matching step wins:
  1. Actions matching your allow, ask, or deny rules resolve immediately. Writes to protected paths route to the classifier even when an allow rule matches, and so do rm and rmdir removals targeting a critical path in Claude Code v2.1.218 and later. Connector tools your organization set to ask and MCP tools marked requiresUserInteraction prompt you directly even when an allow rule matches. Ask rules that match on a command’s content, such as Bash(git push *), fall back to a permission prompt
  2. Read-only actions and file edits in your working directory are auto-approved, except writes to protected paths
  3. Everything else goes to the classifier, except the org-set-to-ask connector tools and requiresUserInteraction MCP tools from step 1, which always prompt you directly, so neither an org-required approval nor a consent step is auto-approved
  4. If the classifier blocks, Claude receives the reason and tries an alternative. In most sessions the reason is the fixed text Blocked by classifier rather than a written explanation, in Claude Code v2.1.208 and later; see Review denials
On entering auto mode, broad allow rules that grant arbitrary code execution are dropped:
  • Blanket Bash(*) or PowerShell(*)
  • Wildcarded interpreters like Bash(python*)
  • Package-manager run commands
  • Agent allow rules
  • Monitor allow rules, because Claude Code runs Monitor commands through the shell
Narrow rules like Bash(npm test) stay in effect. Claude Code restores the dropped rules when you leave auto mode. Before v2.1.236, Claude Code left Monitor allow rules in effect in auto mode, so a rule that matched the whole tool approved Monitor commands without classifier review.Claude Code also runs git status itself before a command that would discard uncommitted work, such as git reset --hard or rm -rf, and shows the classifier whether staged, modified, or untracked work is present. Claude Code reports untracked files in that check even when the repository’s git configuration sets status.showUntrackedFiles=no.The classifier sees user messages, tool calls other than read-only lookups such as file reads and searches, and your CLAUDE.md content. Tool results are stripped, so hostile content in a file or web page can’t manipulate it directly. You can annotate a call’s result with a PostToolUse hook’s classifierContext field, which the classifier reads as application-provided context.A separate server-side probe scans incoming tool results and flags suspicious content before Claude reads it. For more on how these layers work together, see the auto mode announcement and the engineering deep dive.
The classifier checks subagent work at three points:
  1. Before a subagent starts, the delegated task description is evaluated, so a dangerous-looking task is blocked at spawn time.
  2. While the subagent runs, each of its actions goes through the classifier with the same rules as the parent session, and any permissionMode in the subagent’s frontmatter is ignored.
  3. When the subagent finishes, the classifier reviews its full action history; if that return check flags a concern, a security warning is prepended to the subagent’s results. When a separate API safety check refuses the review request itself, Claude Code still returns the subagent’s results, prepended with a warning that the work is unreviewed and should be treated as untrusted.
Step 1 requires Claude Code v2.1.178 or later. Earlier versions applied the classifier at steps 2 and 3, but did not evaluate the task description before the subagent started.
The classifier runs on Claude Sonnet 5 by default rather than on your /model selection. A classifier model that Anthropic configures server-side takes precedence over that default. When your session’s model is Claude Sonnet 4.6, or when availableModels excludes Sonnet 5, the classifier runs on the session’s model instead, or on an Opus model when the session runs on Fable 5; on providers other than the Anthropic API, that Opus fallback is the provider’s default Opus model.The session’s first auto-mode request validates the Sonnet 5 default: if the request succeeds, Sonnet 5 stays the session’s classifier model, and if it fails because the model isn’t available, the session uses the fallback instead. After that validation settles, the classifier’s model doesn’t change for the session.On Enterprise plans and on accounts that use the Claude API, Claude Platform on AWS, Amazon Bedrock, Google Cloud’s Agent Platform, or Microsoft Foundry, classifier calls count toward your token usage. Each check sends a portion of the transcript plus the pending action, adding a round-trip before execution. Reads and working-directory edits outside protected paths skip the classifier, so the overhead comes mainly from shell commands and network operations.The classifier reuses a sandbox network verdict for a host and port, so repeated connections to the same host don’t each add a check. What the classifier blocks by default describes how long an allow and a deny last.

​
Allow only pre-approved tools with dontAsk mode

If you set dontAsk mode, Claude Code auto-denies every tool call that would otherwise prompt you. Claude runs only actions matching your permissions.allow rules, read-only Bash commands, and calls approved by a PreToolUse hook. Use this mode for CI pipelines or restricted environments where you pre-define exactly what Claude may do; the session never waits for input. The status bar shows ⏵⏵ don't ask on while this mode is active. Claude Code denies calls matching your explicit ask rules rather than prompting. It also denies the built-in AskUserQuestion tool and connector tools your organization set to ask, even if your allow rules match them. It denies MCP tools marked _meta["anthropic/requiresUserInteraction"] the same way, because their approval card needs an answer this mode never collects; this requires Claude Code v2.1.199 or later. rm and rmdir removals targeting a critical path, such as rm -rf / and rm -rf ~, are denied even when an allow rule matches them or a PreToolUse hook allows them. Cloud sessions on Claude Code on the web ignore defaultMode: "dontAsk"; see bypassPermissions for details. Set it at startup with the flag:

​
Skip all checks with bypassPermissions mode

bypassPermissions mode disables permission prompts and safety checks so tool calls execute immediately, including writes to protected paths. The actions no mode auto-approves still prompt in this mode. Two cross-session messaging safeguards still apply in this mode, and in plan-mode sessions where bypass permissions are available:
  • The isolatePeerMachines approval prompt for messages to your sessions beyond this machine still appears.
  • When no crossSessionInbound value applies, Claude Code holds an inbound message from another of your sessions for your approval, and delivers without asking only when the sending session identifies itself as also bypassing permission prompts. If you leave the permission mode while messages are held, Claude Code re-applies the inbound rules and delivers any held message they now accept.
In sessions with bypass permissions available, Claude Code also doesn’t enforce plan mode’s blocks. Claude is still instructed to plan without editing, but a file edit or shell command it attempts during planning runs without prompting. Explicit ask rules and rm and rmdir removals targeting a critical path still prompt.
Only use this mode in isolated environments like containers, VMs, or dev containers without internet access, where Claude Code cannot damage your host system.
You can’t enter bypassPermissions from a session that was started without it enabled. Enable it at launch with permissions.defaultMode: "bypassPermissions" in settings or with an enabling flag:
The --dangerously-skip-permissions flag is equivalent. The first time you start an interactive session with this mode enabled, Claude Code shows a warning dialog asking you to accept responsibility for actions taken without permission checks. Claude Code saves your acceptance to user settings, so the dialog appears only once. If you decline, Claude Code exits. In non-interactive mode no dialog is shown, and a background session started with --bg is refused until you’ve accepted the dialog in an interactive session. On Linux and macOS, Claude Code refuses to start in this mode when running as root or under sudo:
The check is skipped automatically inside a recognized sandbox. To run autonomously in a container, use the dev container configuration, which runs Claude Code as a non-root user. Claude Code on the web does not honor defaultMode: "bypassPermissions" or "dontAsk" from your settings files, so a repository’s checked-in settings cannot start a cloud session in bypass-permissions mode. The setting is ignored silently and the session starts in the permission mode shown in the mode dropdown instead. See Switch permission modes for which modes cloud sessions offer.
bypassPermissions offers no protection against prompt injection or unintended actions. For background safety checks with far fewer permission prompts, use auto mode instead. Administrators can block this mode by setting permissions.disableBypassPermissionsMode to "disable" in managed settings.

​
Protected paths

Writes to a small set of paths are never auto-approved, except in bypassPermissions mode and in planning sessions with bypass permissions available. This prevents accidental corruption of repository state and Claude’s own configuration. permissions.allow rules in settings files do not pre-approve protected-path writes. The safety check runs before Claude Code evaluates allow rules from settings, so an entry such as Edit(.claude/**) in ~/.claude/settings.json or .claude/settings.json does not change the per-mode outcome in the table above. In modes that prompt, the prompt for a .claude/ write offers Yes, and allow Claude to edit its own settings for this session, which approves later .claude/ writes in that session without prompting again. Protected directories:
  • .git
  • .config/git
  • .vscode
  • .idea
  • .husky
  • .cargo
  • .devcontainer
  • .yarn
  • .mvn
  • .claude, except for .claude/worktrees where Claude stores its own git worktrees
Protected files:
  • .gitconfig, .gitmodules
  • .bashrc, .bash_profile, .bash_login, .bash_aliases, .bash_logout, .zshrc, .zprofile, .zshenv, .zlogin, .zlogout, .profile, .envrc
  • .npmrc, .yarnrc, .yarnrc.yml, .pnp.cjs, .pnp.loader.mjs, .pnpmfile.cjs, bunfig.toml, .bunfig.toml
  • .bazelrc, .bazelversion, .bazeliskrc
  • .pre-commit-config.yaml, lefthook.yml, lefthook.yaml, .lefthook.yml, .lefthook.yaml
  • gradle-wrapper.properties, maven-wrapper.properties
  • .devcontainer.json
  • .ripgreprc, pyrightconfig.json
  • .mcp.json, .claude.json

​
Critical paths

Claude Code never lets a permissions.allow rule or a PreToolUse hook that returns "allow" approve an rm or rmdir command that targets a critical path, even in modes that skip other prompts. This circuit breaker guards against model error. A matching deny rule still blocks the command outright. What happens instead depends on your permission mode: If an explicit ask rule matches the command, Claude Code asks you even in auto mode. In modes that ask, a PermissionRequest hook can answer the prompt the way it answers any other. Claude Code treats an rm or rmdir target as a critical path when it is any of the following:
  • The filesystem root
  • Top-level directories, meaning any direct child of the root, such as /usr, /etc, or /data
  • Your home directory
  • Windows drive roots and their top-level directories, such as C:\ and C:\Windows
  • Your working directory and its parents
  • Your additional working directories and their parents, but only when the removal is a glob under one of them, such as rm -rf <dir>/*. rm -rf <dir> on the directory itself doesn’t trigger this check
Claude Code also treats a glob or trailing slash directly under a shell variable, such as rm -rf "$DIR"/*, as a critical-path removal, because the command becomes a removal from the filesystem root when the variable is empty. Hiding the removal inside command substitution with $(...) or backticks, or process substitution with <(...), doesn’t skip the check. Claude Code finds a critical-path removal whether it sits inside the substitution, as in echo "$(rm -rf ~)", or elsewhere in the same command.

​
Remove-Item in PowerShell

When you enable the PowerShell tool, Claude Code gives Remove-Item its own check, separate from the rm critical-path list. The outcome depends on the target, and the first matching case applies:
  • System paths: the filesystem root and its top-level directories, drive roots and their top-level directories, and your home directory. Claude Code denies the command in every mode, without asking you.
  • Wildcards: a bare *, or any target ending in /* or \*, including a glob under a shell variable such as $dir/*. Claude Code denies the command in every mode, without asking you, before the classifier sees it.
  • Your working directory or one of its parents, with -Recurse: Claude Code treats the command like any other that needs approval in your permission mode, so it asks you in modes that ask, sends it to the classifier in auto mode, and denies it in dontAsk mode. bypassPermissions mode skips this check.

​
See also

  • Permissions: allow, ask, and deny rules; managed policies
  • Configure auto mode: tell the classifier which infrastructure your organization trusts
  • Hooks: custom permission logic via PreToolUse and PermissionRequest hooks
  • Security: safeguards and best practices
  • Sandboxing: filesystem and network isolation for Bash commands
  • Non-interactive mode: run Claude Code with the -p flag