All 118 Claude Code commands, and when to use each

Q: How do I see every Claude Code command?

Type / at the prompt and the menu opens with all of them. Keep typing to filter. /help also lists them with what each one does, and the full list is on this page .

Q: Which command should I learn first?

Learn /context first. It is the one that tells you why the session stopped working, and almost nobody runs it. It is also in the 17 most people never find .

Q: What is the difference between /clear and /compact?

/clear starts a new conversation with an empty context window. /compact keeps the conversation and summarises it to free space. Use /clear when you move to a different task. Use /compact when you are still on the same one and it has just gone long.

Q: How do I go back after Claude changed the wrong thing?

Use /rewind. It rolls the conversation and the code back to an earlier checkpoint. Its aliases are /checkpoint and /undo, which is what most people search for first and why they never find it. More like it are in hidden commands .

Claude Code has 118 slash commands and most people use about a dozen. Here is every one of them, plus the 26 that map to how a session actually runs.

by Navid Moazzez·Updated 2 oct 2026·13 min read·

Claude Code commands are the slash commands you type into the prompt to change what the session is doing. Type / and the menu appears. If you haven't used Claude Code yet, start with what it is.

There are 118 of them. Most people meet about a dozen, usually by accident, and never find the ones that would have saved them the most time.

So this is all of them, grouped by the point in the work where you would actually reach for one.

In this guide, I'll show you:

What a Claude Code command is, and how the menu matches what you type
Why the right command at the right moment costs you less than a better prompt
The 26 that map to a normal session, grouped by when you use them
All 118 in one table you can search
The 6 worth setting up before your next session

And every one of them was read from Anthropic's own command reference on September 30, 2026.

key_takeaways.md

TL;DR

Key takeaways

Claude Code commands are instructions to the tool rather than to the model. Type / and the menu opens.

There are 118: core commands built into Claude Code, plus bundled skills you type the same way.

Most of what people try to fix with a better prompt is fixed by a command. /context shows what is filling the window, and /clear gives it back.

Anthropic groups them by when you use them: your first session, during a task, in parallel, before you ship, between sessions, and when something is wrong.

Set up 6 before your next session, starting with /permissions.

What is a Claude Code command?

A Claude Code command is an instruction to the tool rather than to the model. /clear does not ask Claude to forget: it empties the context window.

You type / and a menu opens. Keep typing and it filters.

Some are core commands built into Claude Code. Others are bundled skills, which behave the same way at the prompt but are loaded rather than built in.

Why Claude Code commands matter

Most of what people try to fix with a better prompt is not a prompting problem.

A session that has gone vague usually has a full context window. A run that keeps stalling on approvals usually has no permission rules. Neither gets better by rewording the request.

For example, an hour into a session the answers get worse. The prompt is not the problem. /context shows you what is filling the window and /clear gives it back, and that takes 2 seconds.

So the commands are the controls. Prompting is what you do once the controls are set.

Your first session in a repo

Run these once and the project is set up for every session after it. This is also where your AI OS starts.

Command	What it does
`/init`	Initialize project with a `CLAUDE.md` guide.
`/memory`	Edit `CLAUDE.md` files, enable or disable auto memory, and view auto memory entries
`/mcp [reconnect <server>\|enable\|disable [<server>\|all]]`	Manage MCP server connections and OAuth authentication.
`/permissions`	Manage allow, ask, and deny rules for tool permissions.

During a task

These are the 6 you will use every day, and 3 of them decide what the session costs you.

Command	What it does
`/plan [description]`	Enter plan mode directly from the prompt.
`/model [model]`	Switch the AI model and save it as your default for new sessions.
`/effort [level\|auto\|status\|ultracode [on\|off]]`	Set the effort level: `low` to `xhigh`, `max`, or `auto`; `status` prints it.
`/context [all]`	Visualize current context usage as a colored grid.
`/compact [instructions]`	Free up context by summarizing the conversation so far.
`/btw [question]`	Ask a side question about the current session without adding to the conversation.

Running work in parallel

Use these when 1 task is really several, or when you want your terminal back.

Command	What it does
`/tasks`	View and manage background work in the current session, including subagents that have finished.
`/background [prompt]`	Detach the current session to run as a background agent and free this terminal.
`/batch <instruction>`	Orchestrate large-scale changes across a codebase in parallel.

Before you ship

Read what changed before anyone else has to.

Command	What it does
`/diff`	Review the changes in your working tree, including the edits Claude has made so far.
`/code-review [low\|medium\|high\|xhigh\|max\|ultra] [--fix] [--comment] [pr#\|branch\|path]`	Review the current diff, or a PR number, branch, or path you pass, for correctness bugs.
`/security-review`	Analyze the changes on your current branch for security vulnerabilities.

Between sessions

Work does not end when you close the terminal, and last week's conversation is still there.

Command	What it does
`/clear [name]`	Start a new conversation with empty context.
`/resume [session]`	Resume a conversation by ID or name, or open the session picker.
`/branch [name]`	Create a branch of the current conversation at this point, so you can try a different direction without losing the conversation as it stands.
`/fork [prompt]`	Copy the current conversation into a new background session and keep working here.
`/teleport`	Pull a cloud session into this terminal.
`/remote-control`	Make this session available for Remote Control from claude.ai.

When something is wrong

Reach for these before you restart from scratch, which is what most people do instead.

Command	What it does
`/rewind`	Rewind the conversation and/or code to a previous point, or summarize from a selected message.
`/doctor [prompt-audit [path]]`	Run a setup checkup that diagnoses issues and can fix them.
`/debug [description]`	Enable debug logging for the current session and troubleshoot issues by reading the session debug log.
`/feedback [report]`	Send product feedback about Claude Code.

/mcp is where you manage the MCP servers Claude Code connects to. I've published 23 open source MCP servers you can connect, and my AI OS guide shows what to set up in your first session.

All 118 Claude Code commands

Here is the full Claude Code command list, in alphabetical order.

/add-dir <path>

What it does: Add a working directory for file access during the current session.
Type: Built in

/advisor [model|off]

What it does: Enable or disable the advisor tool, which consults a second model for guidance at key moments during a task.
Type: Built in

/agents

What it does: As of v2.1.198, running /agents prints a reminder to ask Claude to create or manage subagents, or to edit .claude/agents/ or ~/.claude/agents/ directly.
Type: Built in

/artifact-capabilities

What it does: Load the reference for the runtime capabilities a published artifact can use, such as calling your connectors or offering a file download, including which ones your account has.
Type: Bundled skill

/artifact-diagramming

What it does: Load diagramming guidance for Claude to follow in artifacts: when a diagram helps, what to draw, and how to write inline SVG that stays legible in light and dark themes.
Type: Bundled skill

/artifacts

What it does: List the artifacts you own or that are shared with you, then attach one to the session, open it in your browser, or copy its link.
Type: Built in

/auto-mode-setup

What it does: Draft autoMode.environment entries from your project and recent sessions, then review the draft and save it to your user settings.
Type: Built in

/autocompact [auto|<tokens>]

What it does: Set the auto-compact window: how full the context window gets before Claude Code compacts automatically.
Type: Built in

/autofix-pr [prompt]

What it does: Spawn a cloud session that watches the current branch's PR and pushes fixes when CI fails or reviewers leave comments.
Type: Built in

/background [prompt]

What it does: Detach the current session to run as a background agent and free this terminal.
Type: Built in

/batch <instruction>

What it does: Orchestrate large-scale changes across a codebase in parallel.
Type: Bundled skill

/branch [name]

What it does: Create a branch of the current conversation at this point, so you can try a different direction without losing the conversation as it stands.
Type: Built in

/btw [question]

What it does: Ask a side question about the current session without adding to the conversation.
Type: Built in

/bug [report]

What it does: Report a bug or share your conversation.
Type: Built in

/cd <path>

What it does: Move this session to a new working directory, keeping the conversation.
Type: Built in

/chrome

What it does: Configure Claude in Chrome settings
Type: Built in

/claude-api [migrate|upgrade|managed-agents-onboard|prompt-audit|cost-optimize|build-eval|hillclimb|preserved-thinking-migration]

What it does: Load Claude API and Managed Agents reference material for your project's language.
Type: Bundled skill

/claude-in-chrome [task]

What it does: Have Claude carry out a task in your browser, such as testing a page, filling a form, or reading console logs, through Claude in Chrome.
Type: Bundled skill

/clear [name]

What it does: Start a new conversation with empty context.
Type: Built in

What it does: Review the current diff, or a PR number, branch, or path you pass, for correctness bugs.
Type: Bundled skill

/color [color|default]

What it does: Set the prompt bar color for the current session.
Type: Built in

/compact [instructions]

What it does: Free up context by summarizing the conversation so far.
Type: Built in

/config [key=value ...]

What it does: Open the Settings interface to adjust theme, model, output style, and other preferences.
Type: Built in

/context [all]

What it does: Visualize current context usage as a colored grid.
Type: Built in

/copy [N]

What it does: Copy the last assistant response to clipboard.
Type: Built in

/cost

What it does: Alias for /usage
Type: Built in

/dataviz [request]

What it does: Design guidance for charts, graphs, and dashboards.
Type: Bundled skill

/debug [description]

What it does: Enable debug logging for the current session and troubleshoot issues by reading the session debug log.
Type: Bundled skill

/deep-research <question>

What it does: Workflow. Fan out web searches on a question, fetch and cross-check sources, and synthesize a cited report
Type: Built in

/design [brief]

What it does: Draft UI mockups, screen flows, landing pages, or posters as artboards on one canvas, published as a Claude Design artifact, for example /design a settings screen for a mobile banking app.
Type: Bundled skill

/design-login

What it does: Authorize design-system access for /design-sync with your claude.ai account
Type: Built in

/design-sync [hint]

What it does: Convert your repo's React design system and upload it to Claude Design, so designs it produces use your real components.
Type: Bundled skill

/desktop

What it does: Continue the current session in the Claude Code Desktop app.
Type: Built in

/diff

What it does: Review the changes in your working tree, including the edits Claude has made so far.
Type: Built in

/doctor [prompt-audit [path]]

What it does: Run a setup checkup that diagnoses issues and can fix them.
Type: Bundled skill

/effort [level|auto|status|ultracode [on|off]]

What it does: Set the effort level: low to xhigh, max, or auto; status prints it.
Type: Built in

/exit

What it does: Exit the CLI.
Type: Built in

/export [filename]

What it does: Export the current conversation as plain text.
Type: Built in

/fast [on|off]

What it does: Toggle fast mode on or off.
Type: Built in

/feedback [report]

What it does: Send product feedback about Claude Code.
Type: Built in

/fewer-permission-prompts

What it does: Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project .claude/settings.json to reduce permission prompts
Type: Bundled skill

/focus

What it does: Toggle the focus view, which shows only your last prompt, a one-line tool-call summary with edit diffstats, and the final response.
Type: Built in

/fork [prompt]

What it does: Copy the current conversation into a new background session and keep working here.
Type: Built in

/goal [condition|clear]

What it does: Set a goal: Claude keeps working across turns until the condition is met or the goal clears for another reason.
Type: Built in

/heapdump

What it does: Write a JavaScript heap snapshot and a memory breakdown to ~/Desktop, or your home directory on Linux without a Desktop folder, for diagnosing high memory usage.
Type: Built in

/help

What it does: Show help and available commands
Type: Built in

/hooks

What it does: View hook configurations for tool events
Type: Built in

/ide

What it does: Manage IDE integrations and show status
Type: Built in

/import [codex|gemini|cursor] [--dry-run] [--yes]

What it does: Bring configuration from OpenAI Codex, Google Gemini CLI, or Cursor on your machine into Claude Code, including instruction files, MCP servers, commands, subagents, and skills.
Type: Built in

/init

What it does: Initialize project with a CLAUDE.md guide.
Type: Built in

/insights

What it does: Generate an HTML report analyzing your recent sessions on this machine: which projects you work in, how you use Claude Code, where things go wrong, and features to try.
Type: Built in

/install-github-app

What it does: Install the Claude GitHub App for a repository, with an optional step to set up GitHub Actions workflows and secrets.
Type: Built in

/install-slack-app

What it does: Install the Claude Slack app.
Type: Built in

/keybindings

What it does: Open your keyboard shortcuts file
Type: Built in

/list-agents

What it does: List the subagents, agent team teammates, and other Claude Code sessions Claude can message, with the name to use for each.
Type: Built in

/login

What it does: Sign in to your Anthropic account
Type: Built in

/logout

What it does: Sign out from your Anthropic account
Type: Built in

/loop [interval] [prompt]

What it does: Run a prompt repeatedly while the session stays open.
Type: Bundled skill

/mcp [reconnect <server>|enable|disable [<server>|all]]

What it does: Manage MCP server connections and OAuth authentication.
Type: Built in

/memory

What it does: Edit CLAUDE.md files, enable or disable auto memory, and view auto memory entries
Type: Built in

/mobile

What it does: Show QR code to download the Claude mobile app.
Type: Built in

/model [model]

What it does: Switch the AI model and save it as your default for new sessions.
Type: Built in

/output-style [style]

What it does: List output styles or switch to one, for example /output-style concise.
Type: Built in

/passes

What it does: Share a free week of Claude Code with friends.
Type: Built in

/permissions

What it does: Manage allow, ask, and deny rules for tool permissions.
Type: Built in

/plan [description]

What it does: Enter plan mode directly from the prompt.
Type: Built in

/plugin [subcommand]

What it does: Manage Claude Code plugins.
Type: Built in

/powerup

What it does: Discover Claude Code features through quick interactive lessons with animated demos
Type: Built in

/pr-comments [PR]

What it does: Removed in v2.1.91.
Type: Built in

/privacy-settings

What it does: View and update your privacy settings.
Type: Built in

/radio

What it does: Open Claude FM lo-fi radio in your browser.
Type: Built in

/rate-limit-options

What it does: Show ways to keep working when a claude.ai usage limit blocks a request: wait and continue automatically when the limit resets, add usage credits, or upgrade your plan.
Type: Built in

/recap

What it does: Generate a one-line summary of the current session on demand.
Type: Built in

/release-notes

What it does: View the changelog in an interactive version picker.
Type: Built in

/reload-plugins [--force]

What it does: Reload all active plugins to apply pending changes without restarting.
Type: Built in

/reload-skills

What it does: Re-scan skill and command directories so skills added or changed on disk during the session become available without restarting.
Type: Built in

/remote-control

What it does: Make this session available for Remote Control from claude.ai.
Type: Built in

/remote-env

What it does: Choose the default cloud environment for cloud sessions you start from the CLI
Type: Built in

/rename [name]

What it does: Rename the current session and show the name on the prompt bar.
Type: Built in

/resume [session]

What it does: Resume a conversation by ID or name, or open the session picker.
Type: Built in

What it does: Alias of /code-review: reviews the current diff, or a PR number, branch, or path you pass, such as /review 1234, and takes the same effort levels and flags.
Type: Built in

/rewind

What it does: Rewind the conversation and/or code to a previous point, or summarize from a selected message.
Type: Built in

/run

What it does: Launch and drive your project's app to see a change working, not only passing tests.
Type: Bundled skill

/run-skill-generator

What it does: Teach /run and /verify how to build, launch, and drive your project's app from a clean environment by writing a per-project skill
Type: Bundled skill

/sandbox

What it does: Toggle sandbox mode.
Type: Built in

/schedule [description]

What it does: Create, update, list, or run routines, which execute in the cloud.
Type: Built in

/scroll-speed

What it does: Adjust mouse wheel scroll speed interactively, with a ruler you can scroll while the dialog is open to preview the change.
Type: Built in

/security-review

What it does: Analyze the changes on your current branch for security vulnerabilities.
Type: Built in

/setup-bedrock

What it does: Configure Amazon Bedrock authentication, region, and model pins through an interactive wizard.
Type: Built in

/setup-vertex

What it does: Configure Google Cloud's Agent Platform authentication, project, region, and model pins through an interactive wizard.
Type: Built in

/simplify [target]

What it does: Review the changed code for cleanup opportunities and apply the fixes.
Type: Bundled skill

/skill-doctor

What it does: Show what each of your skills costs in context and how often it gets used, so you can find skills to turn off.
Type: Built in

/skills

What it does: List available skills.
Type: Built in

/slides [brief]

What it does: Make a new presentation as a Claude Slides artifact filled from your brief, for example /slides a quarterly review of the platform team.
Type: Bundled skill

/stats

What it does: Alias for /usage.
Type: Built in

/status

What it does: Open the Settings interface on the Status tab, showing version, model, account, and connectivity.
Type: Built in

/statusline

What it does: Configure Claude Code's status line.
Type: Built in

/stickers

What it does: Order Claude Code stickers
Type: Built in

/stop

What it does: Stop the current background session.
Type: Built in

/subtask <task>

What it does: Spawn a forked subagent: a background subagent that inherits the full conversation and works on the task while you keep working.
Type: Built in

/tasks

What it does: View and manage background work in the current session, including subagents that have finished.
Type: Built in

/team-onboarding

What it does: Generate a team onboarding guide from your Claude Code usage history.
Type: Built in

/teleport

What it does: Pull a cloud session into this terminal.
Type: Built in

/terminal-setup

What it does: Install a Shift+Enter keybinding for newlines in VS Code, Cursor, Devin Desktop, Alacritty, or Zed.
Type: Built in

/theme

What it does: Change the color theme.
Type: Built in

/tui [default|fullscreen]

What it does: Set the terminal UI renderer and relaunch into it with your conversation intact.
Type: Built in

/ultraplan <prompt>

What it does: Removed.
Type: Built in

/ultrareview [PR or branch]

What it does: Run a deep, multi-agent code review in a cloud sandbox with ultrareview.
Type: Built in

/update-config [request]

What it does: Describe a settings change, such as allowing a command, setting an environment variable, or adding a hook, and Claude edits the matching settings.json file.
Type: Bundled skill

/upgrade

What it does: Open the upgrade page in your browser to switch to a higher plan tier.
Type: Built in

/usage

What it does: Show session cost, plan usage limits, and activity stats.
Type: Built in

/usage-credits

What it does: Configure usage credits, or request them from your admin, when you hit a limit.
Type: Built in

/verify

What it does: Confirm a code change does what it should by building your project's app, running it, and observing the result, rather than relying on tests or type checks.
Type: Bundled skill

/vim

What it does: Removed in v2.1.92.
Type: Built in

/voice [hold|tap|off]

What it does: Toggle voice dictation, or enable it in a specific mode.
Type: Built in

/web-setup

What it does: Connect your GitHub account for cloud sessions using your local gh CLI credentials
Type: Built in

/workflow-authoring

What it does: Load the reference for writing dynamic workflow scripts: the script API, resume behavior, quality patterns, and worked examples.
Type: Bundled skill

/workflows

What it does: Open the workflow progress view to watch, pause, resume, or save running and completed workflows
Type: Built in

Command	What it does	Type
`/add-dir <path>`	Add a working directory for file access during the current session.	Built in
`/advisor [model\|off]`	Enable or disable the advisor tool, which consults a second model for guidance at key moments during a task.	Built in
`/agents`	As of v2.1.198, running `/agents` prints a reminder to ask Claude to create or manage subagents, or to edit `.claude/agents/` or `~/.claude/agents/` directly.	Built in
`/artifact-capabilities`	Load the reference for the runtime capabilities a published artifact can use, such as calling your connectors or offering a file download, including which ones your account has.	Bundled skill
`/artifact-diagramming`	Load diagramming guidance for Claude to follow in artifacts: when a diagram helps, what to draw, and how to write inline SVG that stays legible in light and dark themes.	Bundled skill
`/artifacts`	List the artifacts you own or that are shared with you, then attach one to the session, open it in your browser, or copy its link.	Built in
`/auto-mode-setup`	Draft `autoMode.environment` entries from your project and recent sessions, then review the draft and save it to your user settings.	Built in
`/autocompact [auto\|<tokens>]`	Set the auto-compact window: how full the context window gets before Claude Code compacts automatically.	Built in
`/autofix-pr [prompt]`	Spawn a cloud session that watches the current branch's PR and pushes fixes when CI fails or reviewers leave comments.	Built in
`/background [prompt]`	Detach the current session to run as a background agent and free this terminal.	Built in
`/batch <instruction>`	Orchestrate large-scale changes across a codebase in parallel.	Bundled skill
`/branch [name]`	Create a branch of the current conversation at this point, so you can try a different direction without losing the conversation as it stands.	Built in
`/btw [question]`	Ask a side question about the current session without adding to the conversation.	Built in
`/bug [report]`	Report a bug or share your conversation.	Built in
`/cd <path>`	Move this session to a new working directory, keeping the conversation.	Built in
`/chrome`	Configure Claude in Chrome settings	Built in
`/claude-api [migrate\|upgrade\|managed-agents-onboard\|prompt-audit\|cost-optimize\|build-eval\|hillclimb\|preserved-thinking-migration]`	Load Claude API and Managed Agents reference material for your project's language.	Bundled skill
`/claude-in-chrome [task]`	Have Claude carry out a task in your browser, such as testing a page, filling a form, or reading console logs, through Claude in Chrome.	Bundled skill
`/clear [name]`	Start a new conversation with empty context.	Built in
`/code-review [low\|medium\|high\|xhigh\|max\|ultra] [--fix] [--comment] [pr#\|branch\|path]`	Review the current diff, or a PR number, branch, or path you pass, for correctness bugs.	Bundled skill
`/color [color\|default]`	Set the prompt bar color for the current session.	Built in
`/compact [instructions]`	Free up context by summarizing the conversation so far.	Built in
`/config [key=value ...]`	Open the Settings interface to adjust theme, model, output style, and other preferences.	Built in
`/context [all]`	Visualize current context usage as a colored grid.	Built in
`/copy [N]`	Copy the last assistant response to clipboard.	Built in
`/cost`	Alias for `/usage`	Built in
`/dataviz [request]`	Design guidance for charts, graphs, and dashboards.	Bundled skill
`/debug [description]`	Enable debug logging for the current session and troubleshoot issues by reading the session debug log.	Bundled skill
`/deep-research <question>`	Workflow. Fan out web searches on a question, fetch and cross-check sources, and synthesize a cited report	Built in
`/design [brief]`	Draft UI mockups, screen flows, landing pages, or posters as artboards on one canvas, published as a Claude Design artifact, for example `/design a settings screen for a mobile banking app`.	Bundled skill
`/design-login`	Authorize design-system access for `/design-sync` with your claude.ai account	Built in
`/design-sync [hint]`	Convert your repo's React design system and upload it to Claude Design, so designs it produces use your real components.	Bundled skill
`/desktop`	Continue the current session in the Claude Code Desktop app.	Built in
`/diff`	Review the changes in your working tree, including the edits Claude has made so far.	Built in
`/doctor [prompt-audit [path]]`	Run a setup checkup that diagnoses issues and can fix them.	Bundled skill
`/effort [level\|auto\|status\|ultracode [on\|off]]`	Set the effort level: `low` to `xhigh`, `max`, or `auto`; `status` prints it.	Built in
`/exit`	Exit the CLI.	Built in
`/export [filename]`	Export the current conversation as plain text.	Built in
`/fast [on\|off]`	Toggle fast mode on or off.	Built in
`/feedback [report]`	Send product feedback about Claude Code.	Built in
`/fewer-permission-prompts`	Scan your transcripts for common read-only Bash and MCP tool calls, then add a prioritized allowlist to project `.claude/settings.json` to reduce permission prompts	Bundled skill
`/focus`	Toggle the focus view, which shows only your last prompt, a one-line tool-call summary with edit diffstats, and the final response.	Built in
`/fork [prompt]`	Copy the current conversation into a new background session and keep working here.	Built in
`/goal [condition\|clear]`	Set a goal: Claude keeps working across turns until the condition is met or the goal clears for another reason.	Built in
`/heapdump`	Write a JavaScript heap snapshot and a memory breakdown to `~/Desktop`, or your home directory on Linux without a Desktop folder, for diagnosing high memory usage.	Built in
`/help`	Show help and available commands	Built in
`/hooks`	View hook configurations for tool events	Built in
`/ide`	Manage IDE integrations and show status	Built in
`/import [codex\|gemini\|cursor] [--dry-run] [--yes]`	Bring configuration from OpenAI Codex, Google Gemini CLI, or Cursor on your machine into Claude Code, including instruction files, MCP servers, commands, subagents, and skills.	Built in
`/init`	Initialize project with a `CLAUDE.md` guide.	Built in
`/insights`	Generate an HTML report analyzing your recent sessions on this machine: which projects you work in, how you use Claude Code, where things go wrong, and features to try.	Built in
`/install-github-app`	Install the Claude GitHub App for a repository, with an optional step to set up GitHub Actions workflows and secrets.	Built in
`/install-slack-app`	Install the Claude Slack app.	Built in
`/keybindings`	Open your keyboard shortcuts file	Built in
`/list-agents`	List the subagents, agent team teammates, and other Claude Code sessions Claude can message, with the name to use for each.	Built in
`/login`	Sign in to your Anthropic account	Built in
`/logout`	Sign out from your Anthropic account	Built in
`/loop [interval] [prompt]`	Run a prompt repeatedly while the session stays open.	Bundled skill
`/mcp [reconnect <server>\|enable\|disable [<server>\|all]]`	Manage MCP server connections and OAuth authentication.	Built in
`/memory`	Edit `CLAUDE.md` files, enable or disable auto memory, and view auto memory entries	Built in
`/mobile`	Show QR code to download the Claude mobile app.	Built in
`/model [model]`	Switch the AI model and save it as your default for new sessions.	Built in
`/output-style [style]`	List output styles or switch to one, for example `/output-style concise`.	Built in
`/passes`	Share a free week of Claude Code with friends.	Built in
`/permissions`	Manage allow, ask, and deny rules for tool permissions.	Built in
`/plan [description]`	Enter plan mode directly from the prompt.	Built in
`/plugin [subcommand]`	Manage Claude Code plugins.	Built in
`/powerup`	Discover Claude Code features through quick interactive lessons with animated demos	Built in
`/pr-comments [PR]`	Removed in v2.1.91.	Built in
`/privacy-settings`	View and update your privacy settings.	Built in
`/radio`	Open Claude FM lo-fi radio in your browser.	Built in
`/rate-limit-options`	Show ways to keep working when a claude.ai usage limit blocks a request: wait and continue automatically when the limit resets, add usage credits, or upgrade your plan.	Built in
`/recap`	Generate a one-line summary of the current session on demand.	Built in
`/release-notes`	View the changelog in an interactive version picker.	Built in
`/reload-plugins [--force]`	Reload all active plugins to apply pending changes without restarting.	Built in
`/reload-skills`	Re-scan skill and command directories so skills added or changed on disk during the session become available without restarting.	Built in
`/remote-control`	Make this session available for Remote Control from claude.ai.	Built in
`/remote-env`	Choose the default cloud environment for cloud sessions you start from the CLI	Built in
`/rename [name]`	Rename the current session and show the name on the prompt bar.	Built in
`/resume [session]`	Resume a conversation by ID or name, or open the session picker.	Built in
`/review [low\|medium\|high\|xhigh\|max\|ultra] [--fix] [--comment] [pr#\|branch\|path]`	Alias of `/code-review`: reviews the current diff, or a PR number, branch, or path you pass, such as `/review 1234`, and takes the same effort levels and flags.	Built in
`/rewind`	Rewind the conversation and/or code to a previous point, or summarize from a selected message.	Built in
`/run`	Launch and drive your project's app to see a change working, not only passing tests.	Bundled skill
`/run-skill-generator`	Teach `/run` and `/verify` how to build, launch, and drive your project's app from a clean environment by writing a per-project skill	Bundled skill
`/sandbox`	Toggle sandbox mode.	Built in
`/schedule [description]`	Create, update, list, or run routines, which execute in the cloud.	Built in
`/scroll-speed`	Adjust mouse wheel scroll speed interactively, with a ruler you can scroll while the dialog is open to preview the change.	Built in
`/security-review`	Analyze the changes on your current branch for security vulnerabilities.	Built in
`/setup-bedrock`	Configure Amazon Bedrock authentication, region, and model pins through an interactive wizard.	Built in
`/setup-vertex`	Configure Google Cloud's Agent Platform authentication, project, region, and model pins through an interactive wizard.	Built in
`/simplify [target]`	Review the changed code for cleanup opportunities and apply the fixes.	Bundled skill
`/skill-doctor`	Show what each of your skills costs in context and how often it gets used, so you can find skills to turn off.	Built in
`/skills`	List available skills.	Built in
`/slides [brief]`	Make a new presentation as a Claude Slides artifact filled from your brief, for example `/slides a quarterly review of the platform team`.	Bundled skill
`/stats`	Alias for `/usage`.	Built in
`/status`	Open the Settings interface on the Status tab, showing version, model, account, and connectivity.	Built in
`/statusline`	Configure Claude Code's status line.	Built in
`/stickers`	Order Claude Code stickers	Built in
`/stop`	Stop the current background session.	Built in
`/subtask <task>`	Spawn a forked subagent: a background subagent that inherits the full conversation and works on the task while you keep working.	Built in
`/tasks`	View and manage background work in the current session, including subagents that have finished.	Built in
`/team-onboarding`	Generate a team onboarding guide from your Claude Code usage history.	Built in
`/teleport`	Pull a cloud session into this terminal.	Built in
`/terminal-setup`	Install a Shift+Enter keybinding for newlines in VS Code, Cursor, Devin Desktop, Alacritty, or Zed.	Built in
`/theme`	Change the color theme.	Built in
`/tui [default\|fullscreen]`	Set the terminal UI renderer and relaunch into it with your conversation intact.	Built in
`/ultraplan <prompt>`	Removed.	Built in
`/ultrareview [PR or branch]`	Run a deep, multi-agent code review in a cloud sandbox with ultrareview.	Built in
`/update-config [request]`	Describe a settings change, such as allowing a command, setting an environment variable, or adding a hook, and Claude edits the matching `settings.json` file.	Bundled skill
`/upgrade`	Open the upgrade page in your browser to switch to a higher plan tier.	Built in
`/usage`	Show session cost, plan usage limits, and activity stats.	Built in
`/usage-credits`	Configure usage credits, or request them from your admin, when you hit a limit.	Built in
`/verify`	Confirm a code change does what it should by building your project's app, running it, and observing the result, rather than relying on tests or type checks.	Bundled skill
`/vim`	Removed in v2.1.92.	Built in
`/voice [hold\|tap\|off]`	Toggle voice dictation, or enable it in a specific mode.	Built in
`/web-setup`	Connect your GitHub account for cloud sessions using your local `gh` CLI credentials	Built in
`/workflow-authoring`	Load the reference for writing dynamic workflow scripts: the script API, resume behavior, quality patterns, and worked examples.	Bundled skill
`/workflows`	Open the workflow progress view to watch, pause, resume, or save running and completed workflows	Built in

The 6 Claude Code commands to set up first

0/6

1Run /permissions once, so approvals stop interrupting every run

2Put /context on a habit: check it before you blame the prompt

3Set /effort down for work that does not need the reasoning

4Use /btw instead of stopping a run to ask something small

5Name sessions with /rename so /resume is usable next week

6Run /doctor once now, before the day you actually need it

More AI coding tools I've reviewed

Claude Code is the one I use every day, and these are the others I've reviewed:

Claude Code

Paid

AI coding agent that also writes, researches, and runs full business workflows from plain English.

Code assistantsAI agentsLLMProductivity

Codex

Paid

OpenAI's agentic coding assistant that writes, edits, and ships code from natural-language instructions.

Code assistantsAI agentsProductivity

Cursor

Freemium

Code editor with AI pair-programming and intelligent autocomplete.

Code assistantsProductivity

GitHub Copilot

Freemium

AI pair programmer that suggests and completes code in your editor.

Code assistants

FAQs about Claude Code commands

Have questions about Claude Code commands? Find answers to the most common ones below.

What is a Claude Code command?

A Claude Code command is an instruction to the tool rather than to the model.

You type `/` at the prompt and a menu opens.

Some are core commands built into Claude Code.

Others are bundled skills, which you type exactly the same way.

How do I see every Claude Code command?

Type `/` at the prompt and the menu opens with all of them.

Keep typing to filter.

`/help` also lists them with what each one does, and the full list is on this page.

How many commands does Claude Code have?

Claude Code has 118, counting the bundled skills.

That count moves as versions ship, which is why this page is dated and the table is read from the reference rather than typed out by hand.

What is the difference between a command and a skill?

At the prompt there is no difference, because you type both the same way.

Underneath, core commands are built into Claude Code and bundled skills are loaded.

The table on this page marks which is which.

Which command should I learn first?

Learn `/context` first.

It is the one that tells you why the session stopped working, and almost nobody runs it.

It is also in the 17 most people never find.

What is the difference between /clear and /compact?

`/clear` starts a new conversation with an empty context window.

`/compact` keeps the conversation and summarises it to free space.

Use `/clear` when you move to a different task.

Use `/compact` when you are still on the same one and it has just gone long.

Can I make my own commands?

You can.

Skills and plugins add their own, and they appear in the same menu.

That is also how a command becomes part of your AI OS rather than something you retype.

Do commands work everywhere Claude Code runs?

Most do, but not all of them.

Some are tied to where the session lives.

`/teleport` pulls a cloud session into your terminal, and `/remote-control` exposes a local one to another device.

Neither makes sense in a surface that is already the other kind.

Why does a command I read about not exist?

Commands are added and removed between versions, and most lists of them are never checked again.

Run `claude --version`, then check the current reference.

A command from an article 6 months old may simply be gone.

How do I go back after Claude changed the wrong thing?

Use `/rewind`.

It rolls the conversation and the code back to an earlier checkpoint.

Its aliases are `/checkpoint` and `/undo`, which is what most people search for first and why they never find it.

More like it are in hidden commands.

What does /btw actually do?

It answers a side question without adding it to the conversation.

So you can ask something small while a long run continues, instead of cancelling the run to ask and losing the work.

Do these commands read my AI OS?

They operate on the same session your AI OS is loaded into, so they do in the sense that matters.

`/memory` edits the files directly, and `/context` shows you whether they loaded at all, which is the first thing to check when Claude seems to be ignoring them.

Is there a command to check my setup is healthy?

Run `/doctor`.

It runs a setup checkup, reports installation and configuration problems, and can fix some of them.

It's worth running once while nothing is wrong, so you know what its output looks like normally.

Final thoughts on Claude Code commands

The commands are the controls. Prompting is what you do once the controls are set.

And when a good prompt is what you need, my Claude Code prompt generator writes one with the files, a check Claude can run, and what done looks like.

Keep reading:

Hidden Claude Code commands – the 17 worth learning next
Claude Code permission modes – what /permissions and Shift+Tab actually change
How to install Claude Code – every route, and which ones update themselves
What is Claude Code? – what it does, and whether it is for you

Then run /context in your next session, before you blame the prompt.

Navid Moazzez

AI business strategist & AI OS builder

Navid Moazzez helps creators and founders master AI and build their own AI Operating System (AI OS) to automate their business and life.

Navid.me is reader-supported. When you buy through links on this site, I may earn an affiliate commission. Learn more.