Claude Code CLI Reference: Every Command & Flag

/

121 of 121 items

Commands

Start interactive session

Commands

Start interactive session with initial prompt

claude "explain this project"

claude -p "query"

Commands

Query via SDK, then exit

claude -p "explain this function"

cat file | claude -p "query"

Commands

Process piped content

cat logs.txt | claude -p "explain"

claude -c

Commands

Continue most recent conversation in current directory

claude -c -p "query"

Commands

Continue via SDK

claude -c -p "Check for type errors"

claude -r "<session>" "query"

Commands

Resume session by ID or name

claude -r "auth-refactor" "Finish this PR"

claude update

Commands

Update to latest version

claude gateway

Commands

Start the self-hosted Claude apps gateway server, for administrators deploying SSO and policy in front of Claude Code on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry. Requires --config pointing at a gateway.yaml.

claude gateway --config gateway.yaml

claude install [version]

Commands

Install or reinstall the native binary. Accepts a version like 2.1.118, or stable or latest. See Install a specific version

claude install stable

claude auth logout

Commands

Log out from your Anthropic account

claude auth status

Commands

Show authentication status as JSON. Use --text for human-readable output. Exits with code 0 if logged in, 1 if not. The JSON includes a configDirectory field naming the configuration directory the CLI uses. The field requires Claude Code v2.1.268 or later. The JSON's authMethod field is one of none, claude.ai, oauth_token, api_key, api_key_helper, or third_party

claude agents

Commands

Open agent view to monitor and dispatch parallel background sessions. Use --cwd <path> to show only sessions started under that directory, or --json to print active sessions as a JSON array for scripting (--json --all also includes completed background sessions). Pass --permission-mode, --model, --effort, or --agent to set defaults for dispatched sessions. Accepts --settings, --add-dir, --plugin-dir, and --mcp-config like the top-level claude command. Opening agent view requires an interactive terminal

claude agents --json

claude attach <id|name>

Commands

Attach to a background session in this terminal. Passing part of a running session's name in place of the ID requires Claude Code v2.1.290 or later

claude attach 7c5dcf5d

claude auto-mode defaults

Commands

Print the built-in auto mode classifier rules as JSON. Use claude auto-mode config to see your effective config with settings applied. --label <prefix> prints only the rules whose label starts with that prefix, matched case-insensitively. Requires Claude Code v2.1.208 or later

claude auto-mode defaults --label 'Git Destructive'

claude auto-mode reset

Commands

Restore the default auto mode configuration by removing the autoMode section from your user settings file. Prompts for confirmation before writing; pass -y/--yes to skip the prompt. Rules from managed settings or the --settings flag still apply. Requires Claude Code v2.1.212 or later. See Inspect the defaults and your effective config

claude auto-mode reset --yes

claude daemon logs

Commands

Follow the background-session supervisor's log file, ~/.claude/daemon.log, printing new lines as they arrive until you press Ctrl+C

claude daemon run

Commands

Run the background-session supervisor in the foreground of this terminal, printing its log

claude daemon status

Commands

Print the background-session supervisor's state, version, socket directory, and worker count for diagnostics. Exits 1 if the supervisor isn't running

claude daemon stop --any

Commands

Stop the background-session supervisor and the sessions it hosts. Pass --keep-workers to leave background sessions running for the next supervisor to reconnect to. --any confirms stopping an on-demand supervisor, which is the default. Use this to recover from an unresponsive supervisor

claude daemon stop --any --keep-workers

claude doctor

Commands

Print read-only installation and settings diagnostics from the terminal without starting a session, including install health, settings-file validation errors, and Remote Control eligibility. For the in-session setup checkup that can also apply fixes, run /doctor

claude import [source]

Commands

Start an interactive session that runs /import to bring configuration from other coding agents into Claude Code. Accepts the same --dry-run and --yes options as the command. Not available on Amazon Bedrock, Google Cloud's Agent Platform, Microsoft Foundry, or Claude Platform on AWS. Also unavailable when you turn off feature-flag fetching. Requires Claude Code v2.1.213 or later

claude import codex --dry-run

claude logs <id|name>

Commands

Print recent output from a background session. Passing part of a session's name in place of the ID requires Claude Code v2.1.290 or later

claude logs 7c5dcf5d

claude mcp

Commands

Configure Model Context Protocol (MCP) servers

See the [Claude Code MCP documentation](https://code.claude.com/docs/en/mcp).

claude mcp login <name>

Commands

Run a configured MCP server's OAuth flow without opening the interactive /mcp panel. Works for HTTP, SSE, and claude.ai connector servers. Add --no-browser over SSH to print the authorization URL instead of opening a browser. For an HTTP or SSE server, paste the redirect URL back at the prompt. For a claude.ai connector, see Authorize a connector again from your shell. See Authenticate from the command line

claude mcp login sentry

claude mcp logout <name>

Commands

Clear stored OAuth credentials for an MCP server

claude mcp logout sentry

claude plugin

Commands

Manage Claude Code plugins. Alias: claude plugins. See plugin reference for subcommands

claude plugin install code-review@claude-plugins-official

claude purge [path]

Commands

Delete all local Claude Code state for a project: transcripts, task lists, debug logs, file-edit history, prompt history lines, and the project's entry in ~/.claude.json. Omit [path] to pick from an interactive list. Flags: --dry-run to preview, -y/--yes to skip confirmation, -i/--interactive to confirm each item, --all for every project. See Clear local data

claude purge ~/work/repo --dry-run

claude remote-control

Commands

Start a Remote Control server to control Claude Code from Claude.ai or the Claude app. Runs in server mode (no local interactive session). See Server mode flags. After you stop the server, you can bring back the sessions it was serving. See Resume sessions after stopping the server

claude remote-control --name "My Project"

claude respawn <id>

Commands

Restart a background session, running or stopped, with its conversation intact. Use --all to restart every running session, e.g. to pick up an updated Claude Code binary

claude respawn 7c5dcf5d

claude rm <id>

Commands

Remove a background session from the list. When the removal is refused over the session's worktree and a second claude rm can resolve it, the refusal prints the exact flag and value to pass: --discard-unpushed <commit>@<worktree-id> discards a worktree that has unpushed commits along with those commits, and --force-remove-worktree <worktree-id> deletes a worktree directory that git or the WorktreeRemove hook couldn't remove. --discard-unpushed requires Claude Code v2.1.260 or later, and --force-remove-worktree requires v2.1.268 or later. The conversation transcript stays on your local machine, available through claude --resume

claude rm 7c5dcf5d

claude self-hosted-runner

Commands

Start a runner process that registers this machine or container with a self-hosted environment and hosts Claude Code cloud sessions on your infrastructure. Run claude self-hosted-runner setup for a guided operator walkthrough, claude self-hosted-runner doctor to diagnose a deployed runner, and claude self-hosted-runner orchestrator to spawn on-demand runners. Requires Claude Code v2.1.224 or later

claude self-hosted-runner setup

claude setup-token

Commands

Generate a long-lived OAuth token for CI and scripts. Prints the token to the terminal without saving it. Requires a Claude subscription. See Generate a long-lived token

claude stop <id>

Commands

Stop a background session. Also accepts claude kill

claude stop 7c5dcf5d

claude ultrareview [target]

Commands

Run ultrareview non-interactively. Prints findings to stdout and exits 0 on success or 1 on failure. Use --json for the raw payload and --timeout <minutes> to override the 45-minute default. Use --post on a github.com pull request target to post the finished findings to the PR as one plain comment from your GitHub account. --no-post is the default. --post and --no-post require Claude Code v2.1.227 or later. See Post findings to the pull request

claude ultrareview 1234 --json

--add-dir

Flags

Add additional working directories for Claude to read and edit files. Grants file access; Claude Code doesn't discover most .claude/ configuration from these directories. Validates that each path exists as a directory. You can't add most network paths, such as \\server\share. To persist these directories across sessions, set permissions.additionalDirectories in settings

claude --add-dir ../apps ../lib

--advisor <model>

Flags

Enable the server-side advisor tool for this session with a model alias, fable, opus, or sonnet, or a full model ID. Takes precedence over the advisorModel setting for the session. fable requires Fable access

claude --advisor opus

--agent

Flags

Specify an agent for the current session (overrides the agent setting)

claude --agent my-custom-agent

--agents

Flags

Define custom subagents dynamically via JSON. Accepts the fields listed for CLI-defined subagents. With --print, the value can instead be the path to a JSON file holding the object; the file form requires Claude Code v2.1.281 or later. Claude Code validates the value at startup and exits on an invalid one; see Invalid --agents configuration for the message and for the flags and environment variable that skip the validation. Validation requires Claude Code v2.1.242 or later

claude --agents '{"reviewer":{"description":"Reviews code","prompt":"You are a code reviewer"}}'

--allow-dangerously-skip-permissions

Flags

Add bypassPermissions to the Shift+Tab mode cycle without starting in it. Lets you begin in a different mode like plan and switch to bypassPermissions later. See permission modes

claude --permission-mode plan --allow-dangerously-skip-permissions

--allowedTools, --allowed-tools

Flags

Tools that execute without prompting for permission, apart from reads from network paths. See permission rule syntax for pattern matching. To restrict which tools are available, use --tools instead. If you name one of the task-tracking tools here, Claude Code also opts the session in

"Bash(git log *)" "Bash(git diff *)" "Read"

--append-subagent-system-prompt

Flags

Append custom text to the end of every subagent's system prompt, nested subagents included, apart from a forked subagent, which reuses the conversation's own prompt. Only applies in non-interactive mode with -p. Requires Claude Code v2.1.205 or later

claude -p --append-subagent-system-prompt "Cite file paths in every answer" "query"

--append-subagent-system-prompt-file

Flags

Load text from a file and append it to subagent system prompts. An alternative to --append-subagent-system-prompt for text too long to pass on the command line. The two flags can't be combined. Only applies in non-interactive mode with -p. Requires Claude Code v2.1.261 or later

claude -p --append-subagent-system-prompt-file ./subagent-rules.txt "query"

--append-system-prompt

Flags

Append custom text to the end of the default system prompt

claude --append-system-prompt "Always use TypeScript"

--append-system-prompt-file

Flags

Load additional system prompt text from a file and append to the default prompt

claude --append-system-prompt-file ./extra-rules.txt

--autocompact <auto|tokens>

Flags

Set the auto-compact window for this session without changing your saved settings. Accepts the same values as /autocompact; that section covers the value forms and what overrides the flag. Requires Claude Code v2.1.221 or later

claude --autocompact 500k

--bare

Flags

Minimal mode: skip auto-discovery of hooks, skills, custom commands, subagents, installed plugins, MCP servers, auto memory, and CLAUDE.md so scripted calls start faster. Skills in a directory you pass with --add-dir still load. Claude has access to Bash, file read, and file edit tools. Sets CLAUDE_CODE_SIMPLE. See bare mode

claude --bare -p "query"

--betas

Flags

Beta headers to include in API requests (API key users only)

claude --betas interleaved-thinking

--bg, --background

Flags

Start the session as a background agent and return immediately. Prints the session ID and management commands. Combine with --exec to run a shell command as a background job instead of a Claude session, or with --agent to run a specific subagent. Checks workspace trust for the directory before it starts. Can't be combined with -p/--print; see the error reference

claude --bg "investigate the flaky test"

--channels

Flags

(Research preview) MCP servers whose channel notifications Claude should listen for in this session. Space-separated list of plugin:<name>@<marketplace> entries. Requires Anthropic authentication through claude.ai or a Console API key

claude --channels plugin:my-notifier@my-marketplace

--chrome

Flags

Enable Chrome browser integration for web automation and testing

claude --chrome

--cloud

Flags

With a task description, create a new cloud session. With a session ID (session_... or cse_...) or a claude.ai/code URL, queue a message into that existing session instead, with -p. See send a follow-up message.

claude --cloud "Fix the login bug"

--continue, -c

Flags

Load the most recent conversation in the current directory, including a background session that has finished; opening finished background sessions requires Claude Code v2.1.257 or later. Skips sessions created with claude -p or the Agent SDK, and sessions whose first prompt was /loop. claude -p --continue includes -p, SDK, and /loop sessions. Includes sessions that added this directory with /add-dir

claude --continue

--dangerously-load-development-channels

Flags

Enable channels that are not on the approved allowlist, for local development. Accepts plugin:<name>@<marketplace> and server:<name> entries. Prompts for confirmation, so it takes effect in interactive sessions. With -p, Claude Code ignores the flag

claude --dangerously-load-development-channels server:webhook

--dangerously-skip-permissions

Flags

Skip permission prompts. Equivalent to --permission-mode bypassPermissions. See permission modes for what this does and does not skip. For sessions started with --bg, the mode persists when the supervisor restarts the session

claude --dangerously-skip-permissions

--debug

Flags

Enable debug mode with optional category filtering, such as --debug='mcp,startup' or --debug='!mcp'. The filter binds only in the = form; a space-separated filter enables debug mode without filtering

claude --debug='mcp,startup'

--debug-file <path>

Flags

Write debug logs to a specific file path. Implicitly enables debug mode. Takes precedence over CLAUDE_CODE_DEBUG_LOGS_DIR

claude --debug-file /tmp/claude-debug.log

--desktop

Flags

Open the Claude Desktop app on the current directory and exit without starting a session in the terminal. Add --continue, or --resume with a session ID, to open that session in Desktop instead. --resume here takes only a session ID, not a name or transcript path. Takes no prompt and no other flags except --verbose and the --debug flags, since the app starts the session itself. Available on macOS and x64 Windows when you're signed in with a Claude subscription. Requires Claude Code v2.1.285 or later

claude --desktop

--disable-slash-commands

Flags

Disable all skills and commands for this session

claude --disable-slash-commands

--disallowedTools, --disallowed-tools

Flags

Deny rules. A bare tool name removes the matching tools from Claude's context: "Edit" removes Edit, "*" removes every tool, and "mcp__*" removes every MCP tool. A scoped rule such as Bash(rm *) leaves the tool available and denies only calls that match as written. A rule naming EndConversation can't remove it while any other tool remains

"Bash(git log *)" "Bash(git diff *)" "Edit"

--effort

Flags

Set the effort level for the current session. Options: low, medium, high, xhigh, max, or ultracode. Available levels depend on the model. ultracode requests xhigh effort with ultracode turned on, and requires Claude Code v2.1.203 or later. On the main conversation's model, overrides the modelSettings and effortLevel settings for this session and doesn't persist

claude --effort high

--enable-auto-mode

Flags

Removed in v2.1.111. Auto mode is now in the Shift+Tab cycle by default; use --permission-mode auto to start in it

claude --permission-mode auto

--environment <environment-id>

Flags

Create a new cloud session that runs on the self-hosted environment with the given ID. Environment IDs start with ccpool_. See --environment dispatch behavior for dispatch behavior and the flag combinations it rejects. Requires Claude Code v2.1.224 or later

claude -p "Fix the login bug" --environment ccpool_abc123

--exclude-dynamic-system-prompt-sections

Flags

Move per-user context, such as the auto memory location, out of the system prompt and into the first user message. Improves prompt-cache reuse across different users and machines running the same task. Only applies with the default system prompt; ignored when --system-prompt or --system-prompt-file is set. Use with -p for scripted, multi-user workloads

claude -p --exclude-dynamic-system-prompt-sections "query"

--exec

Flags

Run a shell command as a PTY-backed background job instead of starting a Claude session. Use with --bg to launch from the shell

claude --bg --exec 'pytest -x'

--fallback-model

Flags

Enable automatic fallback to the specified model(s) when the primary model is overloaded or not available, for example a retired model. Accepts a comma-separated list tried in order. See Fallback model chains. To persist a chain across sessions, use the fallbackModel setting, which this flag overrides

claude --fallback-model sonnet,haiku

--fork-session

Flags

When resuming, create a new session ID instead of reusing the original (use with --resume or --continue)

claude --resume abc123 --fork-session

--forward-subagent-text

Flags

Emit subagent text and thinking blocks in the output stream as assistant and user messages with parent_tool_use_id set, so you can reconstruct each subagent's transcript. Without this flag, Claude Code omits the text and thinking blocks of a subagent that runs in the foreground. Requires --print and --output-format stream-json. For nested subagents, forked skills, and the version each needs, see Follow subagent messages. The CLAUDE_CODE_FORWARD_SUBAGENT_TEXT environment variable enables the same behavior. Requires Claude Code v2.1.211 or later

claude -p --output-format stream-json --verbose --forward-subagent-text "query"

--from-pr

Flags

Open the session picker filtered to sessions linked to a specific pull request. Accepts a PR number, a GitHub or GitHub Enterprise PR URL, a GitLab merge request URL, or a Bitbucket pull request URL. Sessions are linked automatically when Claude creates the pull request

claude --from-pr 123

--ide

Flags

Automatically connect to IDE on startup if exactly one valid IDE is available

claude --ide

--init

Flags

Run Setup hooks with the init matcher before the session (print mode only)

claude -p --init "query"

--init-only

Flags

Run Setup and SessionStart hooks, then exit without starting a conversation

claude --init-only

--include-hook-events

Flags

Include hook lifecycle events in the output stream. SessionStart and Setup hook events are always included and don't need this flag. Some hook events, such as Notification, SessionEnd, PreCompact, and PostCompact, never produce a hook_started event, even with this flag. For those events, Claude Code still emits hook_progress while a command hook that runs for more than a second produces output, and emits hook_response only when a hook that runs in the background finishes. Requires --output-format stream-json

claude -p --output-format stream-json --verbose --include-hook-events "query"

--include-partial-messages

Flags

Include partial streaming events in output. Requires --print and --output-format stream-json

claude -p --output-format stream-json --verbose --include-partial-messages "query"

--input-format

Flags

Specify input format for print mode (options: text, stream-json)

claude -p --input-format stream-json --output-format stream-json --verbose

--json-schema

Flags

Get validated JSON output matching a JSON Schema after the agent completes its workflow (print mode only). See structured outputs. Claude Code exits with an error on an invalid schema and accepts the format keyword as an annotation without client-side validation

claude -p --json-schema '{"type":"object","properties":{...}}' "query"

--maintenance

Flags

Run Setup hooks with the maintenance matcher before the session (print mode only)

claude -p --maintenance "query"

--max-budget-usd

Flags

Stop the run once estimated spend on API calls reaches this amount (print mode only). Claude Code checks the cap against its client-side cost estimate, which can differ from your bill. Spend from subagents counts toward the cap. Spend can pass the cap, so leave headroom. When you return to a conversation with --continue or --resume, totals restored from earlier runs don't count toward it. Once spend reaches the cap, spawning another subagent fails with Budget limit reached, and Claude Code stops background subagents that are still running; the cap-enforcement behaviors require Claude Code v2.1.217 or later

claude -p --max-budget-usd 5.00 "query"

--max-turns

Flags

Limit the number of agentic turns (print mode only). No limit by default. With --input-format stream-json, a message still queued when the limit ends a turn stays queued and starts a new turn with its own limit

claude -p --max-turns 3 "query"

--mcp-config

Flags

Load MCP servers from JSON files or strings (space-separated). When you pass this flag with -p, Claude Code waits for still-pending servers to connect before running the first turn, up to the MCP_TIMEOUT startup timeout, 30 seconds by default; a server with a cached tool list skips the wait and connects on first use. In a self-hosted environment, a shorter wait applies instead. The wait requires Claude Code v2.1.221 or later

claude --mcp-config ./mcp.json

--model

Flags

Sets the model for the current session with a model alias such as sonnet, opus, haiku, or fable, or a model's full name. Overrides the model setting and ANTHROPIC_MODEL

claude --model claude-sonnet-5

--name, -n

Flags

Set a display name for the session, shown in /resume and the terminal title. You can resume a named session with claude --resume <name>. /rename changes the name mid-session and also shows it on the prompt bar

claude -n "my-feature-work"

--no-chrome

Flags

Disable Chrome browser integration for this session

claude --no-chrome

--no-session-persistence

Flags

Disable session persistence so sessions are not saved to disk and cannot be resumed. Print mode only. The CLAUDE_CODE_SKIP_PROMPT_HISTORY environment variable does the same in any mode

claude -p --no-session-persistence "query"

--output-format

Flags

Specify output format for print mode (options: text, json, stream-json)

claude -p "query" --output-format json

--permission-mode

Flags

Begin in a specified permission mode. Accepts default, acceptEdits, plan, auto, dontAsk, bypassPermissions, or manual as an alias for default. The manual alias selects the permission mode the UI labels Manual and requires Claude Code v2.1.200 or later; claude --help lists it in place of default, and both values work. Overrides defaultMode from settings files. Without this flag or --dangerously-skip-permissions, a new session starts in the permission mode described in which permission mode a session starts in, which also covers what a -p run starts in

claude --permission-mode plan

--permission-prompt-tool

Flags

Specify an MCP tool to handle permission prompts in non-interactive mode. Pass the full name, such as mcp__<server>__<tool>, of a tool on an MCP server that the run loads. Claude Code waits for that tool's MCP server to connect before running the first turn, up to the MCP_TIMEOUT startup timeout, 30 seconds by default. The prompt tool can't approve an MCP tool marked as requiring user interaction: Claude Code converts an allow result for one to a deny. This restriction requires Claude Code v2.1.199 or later

claude -p --mcp-config ./mcp.json --permission-prompt-tool mcp__permissions__approve "query"

--permission-prompts

Flags

Set who answers permission prompts in print mode. With the default host, Claude Code sends them to the Agent SDK host or the --permission-prompt-tool tool. Pass none when nobody can answer, and Claude Code denies them instead. See Turn off permission prompts in unattended runs. Requires Claude Code v2.1.259 or later

claude -p --permission-prompts none "query"

--plugin-dir

Flags

Load a plugin from a directory or .zip archive, or several from a folder of plugins, for this session only. Each flag takes one path. Repeat the flag for more paths: --plugin-dir A --plugin-dir B.zip. Passing a folder of plugins requires Claude Code v2.1.265 or later

claude --plugin-dir ./my-plugin

--plugin-url

Flags

Fetch a plugin .zip archive from a URL for this session only. Repeat the flag for multiple plugins, or pass space-separated URLs in a single quoted value

claude --plugin-url https://example.com/plugin.zip

--print, -p

Flags

Print response without interactive mode (see Agent SDK documentation for programmatic usage details). For --resume on a background session that is still running, see Resume a running background session

claude -p "query"

--prompt-suggestions

Flags

Emit a prompt_suggestion message with a predicted next user prompt after each turn that generates one; very short conversations can produce none. Requires --print, --output-format stream-json, and --verbose. See Prompt suggestions

claude -p --prompt-suggestions --output-format stream-json --verbose "query"

--ref <branch>

Flags

With --environment, base the new session's checkout on a named ref instead of local HEAD

claude -p "Run the smoke test" --environment ccpool_abc123 --ref main

--remote

Flags

Deprecated alias for --cloud, including the existing-session form

claude --remote "Fix the login bug"

--remote-control, --rc

Flags

Start an interactive session with Remote Control enabled so you can also control it from claude.ai or the Claude app. Optionally pass a name for the session

claude --remote-control "My Project"

--remote-control-session-name-prefix <prefix>

Flags

Prefix for auto-generated Remote Control session names when no explicit name is set. Defaults to your machine's hostname, producing names like myhost-graceful-unicorn. Set CLAUDE_REMOTE_CONTROL_SESSION_NAME_PREFIX for the same effect

claude remote-control --remote-control-session-name-prefix dev-box

--replay-user-messages

Flags

Re-emit user messages from stdin back on stdout for acknowledgment. Requires --input-format stream-json and --output-format stream-json

claude -p --input-format stream-json --output-format stream-json --verbose --replay-user-messages

--restricted

Flags

Start in restricted mode. Use it when an evaluation harness drives claude on a shared machine and Claude Code must not run commands or read that machine's user and project settings. Claude Code removes the built-in tools that run commands or code, and WebFetch, unless you name them individually in --tools, not through the default preset. It also confines the built-in file tools to the working directories, loads only managed settings and --settings, refuses bypassPermissions, and refuses to create cloud sessions. Requires Claude Code v2.1.248 or later

claude --restricted -p "query"

--resume, -r

Flags

Resume a specific session by ID or name, or show an interactive picker to choose a session. In place of an ID, you can pass the absolute path to a session's .jsonl transcript file. The picker and name search include sessions that added this directory with /add-dir. When you pass a session ID, Claude Code searches the current project directory and its git worktrees, then every other project on this machine. Before v2.1.223, the ID search covered only the current project directory and its git worktrees. Background sessions appear in the picker marked with bg. Resuming one that is still running opens that session in this terminal through claude attach, and a prompt you pass on the command line goes to it as its next turn. Before v2.1.285, Claude Code refused and printed the claude attach command to run instead

claude --resume auth-refactor

--safe-mode

Flags

Start with all customizations disabled to troubleshoot a broken configuration: CLAUDE.md, skills, plugins, hooks, MCP servers, custom commands and agents, output styles, workflows, custom themes, custom keybindings, status line and file-suggestion commands, LSP servers, and auto memory do not load. Authentication, model selection, built-in tools, and permissions work normally, which differs from --bare. Managed settings policy still applies, including policy-configured hooks, status line, and file-suggestion commands; managed plugins, managed skills, managed CLAUDE.md, and policy-configured MCP servers do not. Useful for checking whether a customization is what triggers automatic model fallback. Sets CLAUDE_CODE_SAFE_MODE

claude --safe-mode

--session-id

Flags

Use a specific session ID for the conversation (must be a valid UUID)

claude --session-id "550e8400-e29b-41d4-a716-446655440000"

--setting-sources

Flags

Comma-separated list of setting sources to load (user, project, local). See agent view and agent teams for the sessions you start from this one that inherit the list

claude --setting-sources user,project

--settings

Flags

Path to a settings JSON file or an inline JSON string. Values you set here override the same keys in your settings.json files for this session. Keys you omit keep their file-based values. The file must be a regular file no larger than 2 MiB. See settings precedence

claude --settings ./settings.json

--strict-mcp-config

Flags

Only use MCP servers from --mcp-config, ignoring all other MCP configurations. See Exclusive control with managed-mcp.json for what the flag does under a managed MCP file

claude --strict-mcp-config --mcp-config ./mcp.json

--system-prompt

Flags

Replace the entire system prompt with custom text

claude --system-prompt "You are a Python expert"

--system-prompt-file

Flags

Load system prompt from a file, replacing the default prompt

claude --system-prompt-file ./custom-prompt.txt

--system-prompt-snapshot

Flags

Pass off to rebuild the system prompt on every request instead of reusing the prompt recorded on the conversation's first request, for example while you iterate on --append-system-prompt text across --continue runs. Requires Claude Code v2.1.257 or later

claude --system-prompt-snapshot off

--teleport

Flags

Resume a cloud session in your local terminal

claude --teleport

--teammate-mode

Flags

Set how agent team teammates display: in-process (default), auto, tmux, or iterm2. Overrides the teammateMode setting for this session. See Choose a display mode

claude --teammate-mode auto

--tmux

Flags

Create a tmux session for the worktree. Requires --worktree. Uses iTerm2 native panes when available; pass --tmux=classic for traditional tmux

claude -w feature-auth --tmux

--tools

Flags

Restrict which built-in tools Claude can use. Use "" to disable all, "default" for the default set, or tool names like "Bash,Edit,Read". On macOS, Linux, and WSL, the default set leaves out Glob and Grep, as described under Glob tool behavior. If you name one of the task-tracking tools here, Claude Code also opts the session in. The flag doesn't affect MCP tools; to deny those too, use --disallowedTools "mcp__*". A list that omits EndConversation doesn't remove it; "" removes it only when no MCP tools remain

claude --tools "Bash,Edit,Read"

--verbose

Flags

Enable verbose logging, shows full turn-by-turn output. Overrides the viewMode setting for this session

claude --verbose

--version, -v

Flags

Output the version number

claude -v

--worktree, -w

Flags

Start Claude in an isolated git worktree at <repo>/.claude/worktrees/<name>. If you don't give a name, Claude Code generates one. Pass #<number>, a GitHub pull request URL, or a GitLab merge request URL to fetch that PR or MR from origin and branch the worktree from it. Branching from a GitLab merge request requires Claude Code v2.1.233 or later

claude -w feature-auth

--system-prompt

System prompt flags

Replaces the entire default prompt

claude --system-prompt "You are a Python expert"

--system-prompt-file

System prompt flags

Replaces with file contents

claude --system-prompt-file ./prompts/review.txt

--append-system-prompt

System prompt flags

Appends to the default prompt

claude --append-system-prompt "Always use TypeScript"

--append-system-prompt-file

System prompt flags

Appends file contents to the default prompt

claude --append-system-prompt-file ./style-rules.txt

--system-prompt-snapshot

System prompt flags

With off, rebuilds the prompt on every request. With on, the default, reuses a recorded prompt where recording applies

claude --append-system-prompt "Draft rules" --system-prompt-snapshot off

Most-used flags

-p / --print: run once and print the answer. The basis of every script and CI job.
-c / --continue and -r / --resume: pick up where you left off.
--model: choose the model for this session.
--permission-mode, --allowedTools, --disallowedTools: control what runs without asking. Test rules with the permission rule tester.
--append-system-prompt: add instructions without replacing Claude Code's own system prompt.

Frequently asked questions

How do I run Claude Code non-interactively?

Use print mode: claude -p "your prompt". It runs the task, prints the result and exits, which suits scripts and CI. Add --output-format json or stream-json for machine-readable output, and --allowedTools to pre-approve the tools it needs.

How do I resume a previous Claude Code session?

claude -c (or --continue) reopens the most recent conversation in the current directory. claude -r (or --resume) opens a picker, or takes a session ID or name to resume a specific one.

What does --dangerously-skip-permissions do?

It starts Claude Code in bypassPermissions mode, which skips permission prompts except for a few protected actions. Only use it in an isolated container or VM, never on a machine with credentials or data you care about.

How do I pick a model from the command line?

Pass --model with an alias (opus, sonnet, haiku, fable) or a full model ID such as claude-opus-5-5. You can also set ANTHROPIC_MODEL or the model key in settings.json.

Sources: Claude Code CLI reference. Claude Code Agents is an independent site, not affiliated with Anthropic.

More free Claude Code tools

All tools →

Claude Code cheat sheetThe commands, shortcuts, flags and files you use every day, on one printable page.Environment variablesEvery environment variable Claude Code reads, searchable by name or purpose.Slash commandsEvery built-in Claude Code slash command and bundled skill, searchable.Permission rule testerPaste allow, ask and deny rules and see whether a Bash command, file path or URL would run or prompt.