Install Claude Code natively on macOS, Linux, or WSL with automatic background updates.
Install Claude Code with the native installer from Windows PowerShell with automatic background updates.
Install Claude Code with the native installer from Windows CMD with automatic background updates.
Install Claude Code with Homebrew.
Homebrew installations do not auto-update. Run this command to get the latest features and security fixes.
Install Claude Code with WinGet on Windows.
WinGet installations do not auto-update. Run this command to get the latest features and security fixes.
Start an interactive Claude Code session in the current project.
Show the installed Claude Code version.
Manually update Claude Code to the latest version.
Run initialization hooks and start interactive mode.
Log in to your Claude account from the terminal. Use --email to pre-fill email or --sso to force SSO authentication.
Show authentication status as JSON. Use --text for human-readable output. Exits with code 0 if logged in, 1 if not.
Run a one-time task and get a response without starting an interactive session.
Create a Git commit with Claude Code writing the commit message.
Initialize project guidance files for the current project.
Open Claude memory management from inside the session.
Sign in to your Anthropic account.
Sign out from your Anthropic account.
Show QR code to download the Claude mobile app.
Bring configuration from OpenAI Codex, Google Gemini CLI, or Cursor into Claude Code, including instruction files, MCP servers, commands, subagents, and skills.
Run Claude once in print mode and exit with a single response.
Open the current prompt in your default text editor.
Ask a side question without adding it to the main conversation history. Can run while Claude is working.
Delete from the cursor to the end of the line.
Delete the entire current line.
Paste text deleted with readline kill commands.
Cycle through earlier kill-ring entries after pasting.
Move the cursor back by one word.
Move the cursor forward by one word.
Paste an image from the clipboard.
Insert a newline for multiline input.
Open the slash command picker from the start of the prompt.
Enter bash mode from the start of the prompt.
Trigger file path autocomplete.
Accept a prompt suggestion for editing.
Accept a prompt suggestion and submit it immediately.
Exit bash mode when the prompt is empty.
Toggle push-to-talk voice dictation.
Dismiss a /btw side-question overlay and return to the main prompt.
Set a goal: Claude keeps working across turns until the condition is met. Pass clear to remove an active goal early.
Run a prompt repeatedly while the session stays open, with an interval such as 5m, or let Claude self-pace. Alias: /proactive.
Create, update, list, or run routines, which execute in the cloud on a schedule. Alias: /routines.
Fan out web searches on a question, fetch and cross-check sources, and synthesize a cited report.
Stash the current prompt for later. With text in the input, stashes it and clears the prompt; pressed again on an empty prompt, restores the stashed text.
Move the cursor to the start of the current line. In multiline input, moves to the start of the current logical line.
Move the cursor to the end of the current line. In multiline input, moves to the end of the current logical line.
Delete back to the previous whitespace. One press removes a whole path or --flag=value.
Delete to the end of the current word, or to the end of the next word when the cursor is between words.
Undo the last input edit, restoring the previous input text and cursor position.
Send your queued messages, and your draft with them, right away while Claude is still working.
Get JSON output from print mode for scripts and automation.
Enable automatic fallback to a specified model when the default model is overloaded (print mode only).
Limit agentic turns or set a spending cap for print mode runs.
Continue most recent conversation in current directory.
Resume a specific session by ID or name, or show an interactive picker to choose a session.
Clear the current session and start a fresh conversation.
Compact the current conversation to keep only the important context.
Resume another conversation from inside the current session.
Rename the current conversation.
Copy the current conversation into a new background session and keep working here. Pass a prompt to start the copy on it immediately. To switch into a branch yourself, use /branch; to hand a task to a subagent that reports back, use /subtask.
Show how much context is currently in use.
Enter plan mode, optionally passing a task description to start planning immediately.
Open the task list for the current session.
Copy the last assistant response to the clipboard. Pass a number N to copy the Nth-latest response, or pick individual code blocks from the interactive picker.
Export the current response to a file.
Transfer a terminal session to the desktop app or web for visual diff review and continued work.
Add a new working directory to the current session.
Create a branch of the current conversation at this point.
Enable remote control of the current session from claude.ai.
Rewind or summarize from the keyboard.
Detach the current session to run as a background agent and free your terminal. Pass a prompt to send one more instruction before detaching. Alias: /bg.
Spawn a forked subagent that inherits the full conversation and works on the task while you keep working. Its result returns to this conversation when it finishes.
Move the session to a new working directory while keeping the conversation.
Generate a one-line summary of the current session on demand.
Pull a cloud session from claude.ai into this terminal. Opens a picker, then fetches the branch and conversation. Alias: /tp.
Set the auto-compact window: how full the context window gets before Claude Code compacts automatically. Pass a size such as 500k, or auto for the model-tuned default.
Start Claude in an isolated git worktree at .claude/worktrees/<name> so parallel sessions do not conflict. If no name is given, one is auto-generated.
Set a display name for the session, shown in /resume and the terminal title. Resume it later with claude --resume <name>.
When resuming, create a new session ID instead of reusing the original, keeping the original conversation untouched.
Resume sessions linked to a specific GitHub PR (auto-linked when created via gh pr create).
Resume a web session from claude.ai in your local terminal.
Create a new web session on claude.ai with the provided task description.
Start an interactive session with Remote Control enabled so you can also control it from claude.ai or the Claude app.
Cancel the current input or generation.
Kill all background agents.
Exit the Claude Code session.
Exit Claude Code from the command prompt.
Clear the terminal screen while keeping conversation history.
Toggle verbose output for tool execution details.
Background running tasks. Tmux users press Ctrl+B twice.
Show or hide the task list.
Cycle through tabs in dialogs and menus.
Navigate command history.
Suspend Claude Code to your shell (Unix only). Run fg to resume.
Show the current diff inside Claude.
Rewind the conversation to an earlier checkpoint.
Run a setup checkup that diagnoses installation, settings, extension, and CLAUDE.md problems and proposes fixes Claude applies after you confirm.
Show current Claude session and account status.
Show detailed conversation and usage statistics including session history and streaks.
Generate a report analyzing Claude Code sessions, interaction patterns, and friction points.
Show current usage information.
Show current spend and cost information.
Review the current branch for security issues.
Open the linked pull request from the footer.
Review the current diff, or a PR number, branch, or path, for correctness bugs. Pass --fix to apply findings, --comment to post them on the PR, or ultra for a deep multi-agent cloud review. Alias: /review.
Review the changed code for cleanup opportunities and apply the fixes. Four agents run in parallel covering reuse, simplification, efficiency, and abstraction level. Does not look for correctness bugs; use /code-review for those.
Confirm a code change does what it should by building the app, running it, and observing the result, rather than relying on tests or type checks.
Enable debug logging for the current session and troubleshoot issues by reading the session debug log. Optionally describe the issue to focus the analysis.
Start reverse search through command history or cycle through older matches.
Accept the current reverse-search match for editing.
Accept the current reverse-search match and execute it.
Exit reverse search when the query is empty.
Cancel reverse search and restore your original input.
Open the Settings interface, or pass key=value pairs to set a setting directly, such as /config thinking=false or /config model=sonnet.
Open the theme picker.
Set the interface color theme.
Open keybinding configuration.
Install terminal-specific bindings such as Shift+Enter support.
Switch models from inside the current session.
Change the current reasoning effort level.
Toggle fast mode in the current session.
Open permission settings.
Open sandbox settings.
Manage MCP server integrations.
Manage plugins from inside the session.
Reload installed plugins.
Connect Claude Code to your IDE.
Open agent and teammate options.
View hook configurations for tool events and automations.
Toggle between Vim and Normal editing modes from the Settings interface. Removed as the /vim command in v2.1.92.
Configure Claude Code's status line display in your shell prompt.
Toggle permission modes.
Switch models without clearing the current prompt.
Toggle extended thinking mode.
Toggle syntax highlighting inside the theme picker.
Configure usage credits, or request them from your admin, when you hit a rate limit. Previously /extra-usage.
List output styles or switch to one.
Describe a settings change, such as allowing a command or adding a hook, and Claude edits the matching settings.json file. For theme and model, use /config instead.
Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project settings to reduce permission prompts.
Show what each of your skills costs in context and how often it gets used, so you can find skills to turn off.
List the subagents, agent team teammates, and other Claude Code sessions Claude can message, with the name to use for each. Alias: /peers.
Toggle fast mode on or off.
Define custom subagents dynamically at launch via JSON, using the same fields as subagent frontmatter plus a prompt field.
Restrict which built-in tools Claude can use. Use "" to disable all, "default" for all, or list tool names.
Set the effort level for the session at launch: low, medium, high, or max (Opus only, session-scoped).
Add additional working directories for Claude to access at launch.
Begin the session in a specified permission mode, such as plan.
Load MCP servers from JSON files or strings, optionally ignoring all other MCP configuration.
Open the built-in slash command help.
Open the available skills list.
View the full changelog with recent version updates.
Submit feedback or report bugs about Claude Code.
Open the shortcut legend for your current environment.