Every Claude Code Slash Command, Explained

1. Sessions and context management

This is the category you'll reach for most. These commands handle the state of the conversation, the size of your context, and your checkpoints.

/clear — Wipe the conversation clean

Clears your entire current conversation context. Use it when Claude starts mixing up files from an earlier session, or when you're moving to a completely different task.

The difference from its look-alike, /compact, matters. /clear erases all memory and starts from scratch; /compact summarizes that memory to shrink it. New task, /clear; same task that's grown long, /compact.

/compact [instruction] — Save context by summarizing the conversation

Summarizes the conversation to reduce how much context it uses. Use it when you're continuing the same task but the session has gotten long.

Add an instruction afterward to decide what to keep.

  /compact Keep only the API decisions
  /compact Preserve just the error-handling patterns
  /compact Keep only what changed in the code and why

The general rule is to run /compact once context usage passes 80%. Since v2.0.64, compaction completes instantly.

/context — Check current context usage

Shows how your context window is being used. Run it once before /compact to see what's taking up context.

The latest versions even show per-model token estimates per skill, and the plugin name for plugin-sourced skills. It's the command to reach for when you wonder, "Why is my context filling up so fast?"

/rewind — Roll back to a checkpoint

Rolls back to an earlier checkpoint or state. Handy when the conversation is heading the wrong way. Its alias is /undo.

It does the same thing as the Esc + Esc keyboard shortcut, but you can also invoke it explicitly as a command.

/branch [name] — Branch the conversation

Branches your current conversation or workflow. The alias /fork shows up in some references.

When you've been going down path A but want to try path B as well, creating a branch lets you explore the alternative without losing the original.

/goal — Set a completion condition, then run autonomously

Set a completion condition and Claude keeps working across multiple turns until that condition is met. It works in interactive mode, -p mode, and remote control alike.

Use it when a task has a clear finish line and you want Claude to drive itself there. Elapsed time, turn count, and token usage appear in an overlay panel.

/resume [session name] — Resume a previous session

Reopens an earlier session. It supports named sessions and the session titles you set with /rename or --name. Press Ctrl+A to show every project.

/rename [name] — Rename the session

Renames the current session. When you're juggling several tasks at once, give them meaningful names so they're easy to find later.

/status — Check session status

Shows the state of your current session and environment. A good command to run first thing when you start working.

/diff — View changes

Opens an interactive diff viewer. Use it before a code review or a commit to see what changed.

/copy [N] — Copy a response

Copies the most recent response, or one you select, to the clipboard. Handy when you're moving code or generated text somewhere else.

/export [filename] — Export the conversation

Exports the conversation to a file, usually saved as Markdown. Useful for keeping a record of your work or sharing it with teammates.

/cost — Check cost

Opens cost information. Since v2.1.118 it's been folded into /usage, but it still works as a shortcut — it jumps straight to the cost tab of /usage.

2. Settings and environment

These commands configure how Claude Code itself behaves.

/init — Generate CLAUDE.md

Generates CLAUDE.md, your project's instruction file. One of the most important setup commands.

It's the first command to run when you start working a new project with Claude Code. Claude scans your codebase and drafts a CLAUDE.md with your build commands, test setup, code conventions, and more. You can then tweak it yourself.

/config — Open the settings panel

Opens Claude Code's settings. Editor mode (Vim and the like) is managed in here too.

/memory — Edit memory files

Opens or edits Claude's memory files. Includes the CLAUDE.md workflow.

When you send a message that starts with #, it gets added to CLAUDE.md — and /memory lets you view and edit that content directly.

/permissions — Manage permissions

Manages permission modes and recently denied commands. When Claude keeps asking for permission or commands are getting blocked, adjust the policy here.

/model [model name] — Switch models

Switches the active model, balancing speed against depth depending on the nature of the task.

 /model opus    # Hard reasoning, architecture
  /model sonnet  # Everyday coding
  /model haiku   # Simple exploration

Gateway /v1/models discovery is enabled with the environment variable CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1.

/effort [level] — Adjust the reasoning level

Adjusts reasoning effort. The choices are low, medium, high, xhigh, max, and auto.

xhigh works only on Opus 4.7 and later. Run /effort with no argument and an interactive slider appears.

Since March 2026, the default effort level for Opus 4.6 on Max/Team subscriptions changed from high to medium.

/fast [on|off] — Fast mode

Turns fast mode on and off. It isn't a different model — it runs the same Opus 4.6 with API settings tuned for speed.

Ideal for interactive rapid iteration and live debugging. Turn it off when cost matters. Note that turning fast mode on mid-session re-bills your entire prior context at fast-mode rates.

/output-style [style] — Adjust the response format

Changes the response formatting style. Switches between concise and verbose output.

/theme — Change the theme

Changes or creates a theme. It supports "auto-match terminal," named custom themes, JSON themes in ~/.claude/themes/, and plugin-provided themes.

/color [color] — Change the accent color

Changes the session's accent color. If remote control is connected, it even syncs the accent color on claude.ai/code.

/scroll-speed — Adjust scroll speed

Adjusts mouse-wheel scroll speed, with a live preview. Useful when scrolling feels off in VS Code, Cursor, or terminal environments.

/tui — Switch terminal UI mode

Switches the terminal UI mode. /tui fullscreen renders within the same conversation without flicker.

/terminal-setup — Terminal setup guide

Configures terminal integration. It walks you through environment tweaks like mapping the Option key to Meta on a Mac.

/keybindings — Configure keyboard shortcuts

Creates or edits ~/.claude/keybindings.json. Changes take effect immediately, no restart required.

/hooks — Manage hook scripts

Manages hook scripts and hook events. In the latest versions, hooks can call MCP tools with type: "mcp_tool", use the exec form args: string[], and set continueOnBlock on PostToolUse.

/login, /logout — Authentication

Log in and log out. Use it to clear an active auth session.

/doctor — Diagnostics

Runs diagnostics. Useful when something's wrong after an install or upgrade. Press f and Claude fixes the reported problems itself.

/help — Help

Shows help and the available commands. Since the commands change often, it's the safest command when you're unsure.

/exit — Quit

Quits Claude Code.

3. Skills, agents, plugins, and MCP

These commands extend Claude Code.

/agents — Manage subagents

Manages subagents. Running claude agents opens a new agent view that lists every running, blocked, and completed Claude Code session in one place.

/skills — List skills

Lists the available skills. The latest versions let you filter-search by typing and show clearer context for plugin-sourced skills.

Skills are user-defined commands: drop them in the .claude/skills/ directory and they work as project-specific slash commands.

/plugin — Manage plugins

Opens plugin management. Plugin details show a component inventory, hook event names, MCP server names, and the estimated per-session token cost.

/reload-plugins — Hot-reload plugins

Hot-reloads installed plugins. Useful when testing a plugin. The latest versions pull in plugin-provided skills more reliably, and since v2.1.110 it supports remote control.

/mcp — Manage MCP servers

Manages MCP (Model Context Protocol) servers. It also clears dynamic MCP slash commands. On reconnect it picks up .mcp.json edits without a restart.

The MCP slash-command pattern

Commands are generated dynamically from connected MCP servers.

/mcp__[server]__[prompt] [args]

These commands appear only after the relevant MCP server is connected.

/claude-api — Claude API/SDK workflows

Loads the Claude API or SDK helper workflow. Useful for API-related work. The latest versions even cover Managed Agents.

/less-permission-prompts — Automate permissions

Scans your transcript for frequently used read-only Bash and MCP tool calls and proposes a priority allowlist to add to .claude/settings.json. Added in v2.1.111.

When the constant permission prompts get annoying, run this to add your frequently used, safe commands to the allowlist all at once.

4. Coding, review, and planning

The commands you'll use most in actual development work.

/plan [description] — Enter plan mode

Switches to plan mode, where Claude only reads and doesn't edit. Use it when you want to talk through the approach before a big change.

The Shift + Tab keyboard shortcut toggles the same mode.

/ultraplan — Precision planning

Runs a more detailed planning workflow. In the latest versions, the remote-session flow auto-creates a default cloud environment.

/review — Code review

Reviews your current code changes. One of the most-used coding commands.

/simplify — Multi-agent refactoring

A workflow where multiple agents refactor in parallel. Great for structural improvements.

If /review is a single review, /simplify is a parallel review from multiple angles. Use it to examine code quality from several perspectives.

/ultrareview [PR number] — Comprehensive cloud review

Runs a comprehensive cloud code review with parallel multi-agent analysis and critique. With no argument it reviews the current branch; pass a PR number and it reviews that PR.

/security-review — Security review

Runs a security-focused review. Useful before a merge or release.

/debug [description] — Guided debugging

Runs a guided debugging workflow. Great for tracking down a bug step by step.

/batch — Batch changes

Applies the same change across multiple files or worktrees. Useful for repetitive edits spanning a whole project.

/loop [interval] — Recurring workflow

Runs a repeating or scheduled workflow. Useful for periodic checks or automation. Its alias is /proactive.

/btw <question> — Side question

Asks a side question without dragging your whole working context along. For a quick check.

You can ask on the side without interrupting work in progress. The answer isn't added to the conversation history and doesn't change your context window.

/usage — Check usage

Shows your plan limits, quota usage, cost, and stats. Since v2.1.118, /cost and /stats have been folded into tabs inside /usage.

/insights — Usage insights

Shows usage and session insights. Useful for reflecting on your own work patterns.

/focus — Toggle focus view

Toggles focus view on and off. It's no longer tied to Ctrl+O.

/powerup — Interactive feature lessons

Opens interactive feature lessons. Added in 2026, it helps you quickly pick up Claude Code's new features.

/release-notes — Release notes

Opens the release notes. Since Claude Code updates weekly, it's the fastest way to keep up with recent changes.

/feedback — Send feedback

Sends feedback. Use it to file a bug report or feature suggestion directly.

5. Git, PRs, and releases

Commands for branch, commit, pull-request, and release workflows.

/commit — Commit

Generates a commit message and commits. One of the most popular commands the community builds for itself.

/pr — Create a PR

Creates a pull request. A common custom/community command.

/push — Push

Pushes the current branch.

/pr-comments [PR] — Fetch PR comments

Fetches GitHub PR comments. The internal underscore form is /pr_comments.

/install-github-app — Set up the GitHub app

Sets up the GitHub app integration.

/fix-pipeline — Repair the CI pipeline

Attempts to repair a failed CI pipeline. A common custom/community command.

/lint — Run the linter

Runs your linting command. Use it for code-style checks.

/merge-to-main — Merge to the main branch

Handles the main-branch merge workflow.

/vitest — Vitest tests

Runs a Vitest-based test workflow.

6. Integrations, remote, and devices

Commands for working across IDEs, browsers, desktop, mobile, and remote environments.

/ide — IDE integration

Opens or manages IDE integration.

/chrome — Chrome integration

Opens Chrome integration. Availability varies by environment.

/desktop — Desktop app

Hands work off to the desktop app.

/rc or /remote-control — Remote control

Starts remote control. /rc is the short form, /remote-control the full name. Remote-session features keep expanding in the latest versions.

/remote-env — Configure the remote environment

Configures the remote environment. The latest versions' remote-session planning can auto-create a default cloud environment.

/schedule — Cloud scheduling

Manages cloud scheduled jobs.

/teleport — Transfer a session

Transfers or bridges a session.

/voice — Voice mode

Enables push-to-talk voice mode.

/add-dir <path> — Add a directory

Adds another directory to your working scope. Useful for monorepos or adjacent projects.

7. Diagnostics and internal commands

Mostly internal, debug, and experimental commands. Everyday users rarely need them, but they're worth knowing.

/team-onboarding — Team onboarding guide

Generates a ramp-up guide for teammates from your local Claude Code usage history. Added in v2.1.101. When a new teammate joins, it automatically produces a "here's how our team uses Claude Code."

/sandbox — Sandbox controls

Opens sandbox controls.

/stickers — Stickers

A public but non-essential command.

Internal/leak-based commands

The following commands turn up in source references but may not be in standard public builds. Just be aware of them.

• /summary — Session summary
• /session — Session management UI
• /share — Share a session
• /env — Environment settings
• /files — List the files in context
• /issue — Create a GitHub issue
• /passes — Multi-pass workflow
• /bughunter — Bug-hunting workflow
• /advisor — Architecture advice
• /tasks — Manage background tasks
• /onboarding — First-run onboarding

8. The whole set at a glance

The 10 you'll reach for most
/init # First command when starting a new project /clear # Switch to a new task

/compact # Save context in a long session /context # Check current context usage /model # Switch models by task /plan # Plan mode before a big change /review # Code review /btw # Side question /usage # Check cost and usage /help # Safest command when you're unsure

<Recommended combos by workflow>

Starting a new project
/init → Generate CLAUDE.md /permissions → Review the permission policy /add-dir → Add the directories you need

Starting a big task
/plan → Plan mode /ultraplan → More precise planning /effort xhigh → Highest reasoning level

Managing a long session
/context → Check current usage /compact → Compact once you pass 80% /clear → Switch to a new task

Code review
/diff → Check the changes /review → Basic review /simplify → Multi-agent review /security-review → Security review /ultrareview → Comprehensive cloud review

Git work
/commit → Commit /push → Push /pr → Create a PR /pr-comments → Check PR comments

9. A realistic order for learning the commands

Memorizing more than 50 commands at once isn't realistic. This order is the efficient way.

Week 1: five survival commands.
/help, /clear, /compact, /init, /exit. These alone get the basics done.

Week 2: five everyday commands.
/model, /plan, /review, /diff, /context. The work you do daily gets more efficient.

Week 3: five for integration and automation.
/mcp, /agents, /skills, /hooks, /permissions. You weave Claude Code into your work environment.

Week 4: five advanced commands.
/ultraplan, /ultrareview, /security-review, /goal, /btw. You take on big tasks and complex reviews.

Learn 20 this way in a month, and after that you can just look up the rest with /help when you need them. Know the remaining 30 exist and search for them as needed.

10. Building your own commands

Beyond the built-in commands, you can build your own.
Just create a Markdown file in the .claude/commands/ directory.

Personal commands

Create them in ~/.claude/commands/ and you can use them across every project.

Project shared commands

Create them in .claude/commands/ and they're shared with your team through git.

Example: building a /ship command

Save the following to ~/.claude/commands/ship.md.

Review the current diff and run the tests.
  If the tests pass, commit with a clear message and push to main.

Now type /ship and that workflow runs as written. Turning repetitive tasks into commands lets you customize Claude Code to your own working patterns.

Arguments work too. Use $ARGUMENTS in a command definition and whatever you pass when you call it drops into that spot.

Handle issue #$1 at priority $2.

Call it with /fix-issue 123 high and it becomes "Handle issue #123 at priority high."