Launch price: 120+ Claude Code agents for $49 one-time · lifetime updatesGet access →
Coding·Updated ·8 min read

Claude Code Slash Commands: The Full List and How to Make Your Own

Type / in Claude Code and you'll see dozens of commands. Most people use three of them. This guide groups the ones worth knowing by what you're trying to do, then shows how to build your own.

Commands change between versions, so treat this as a map and type / to see exactly what your version offers.

Managing your session

  • /clear — start a new conversation with empty context (use it between unrelated tasks)
  • /compact [instructions] — summarise the conversation so far to free up context
  • /context — see what's using your context window
  • /resume — pick up a previous conversation
  • /rewind — roll the conversation and/or code back to an earlier point
  • /branch — fork the conversation to try a different direction
  • /btw — ask a quick side question without derailing the main task
  • /plan — enter plan mode so Claude researches and proposes before editing

Setting up your project

  • /init — generate a CLAUDE.md for the project
  • /memory — edit CLAUDE.md files and manage auto memory
  • /model — switch models
  • /effort — set how hard Claude thinks (low to xhigh)
  • /permissions — manage allow, ask and deny rules for tools
  • /hooks — view your hook configuration
  • /mcp — manage MCP server connections
  • /agents and /list-agents — manage and list subagents
  • /import codex | gemini | cursor — bring configuration over from another tool
  • /doctor — check your installation and settings

Reviewing and shipping code

  • /diff — review the changes in your working tree
  • /code-review (alias /review) — review the current diff, a branch or a pull request
  • /security-review — check your branch's changes for vulnerabilities
  • /simplify — look for cleanup and simplification opportunities
  • /install-github-app — set up Claude in GitHub Actions

Account and usage

  • /usage (alias /cost) — session cost, plan limits and activity
  • /status — version, model, account and connectivity
  • /login and /logout — switch accounts
  • /help — list commands

How custom commands work now

Custom commands have been merged into skills. A file at .claude/commands/deploy.md and a skill at .claude/skills/deploy/SKILL.md both create /deploy and behave the same way. Old command files keep working, but skills are recommended for new work because they can include supporting files and Claude can load them on its own when relevant.

  • Project: .claude/skills/<name>/SKILL.md
  • Personal (all projects): ~/.claude/skills/<name>/SKILL.md

Example: a command with arguments

.claude/skills/migrate-component/SKILL.md
---
name: migrate-component
description: Migrate a component from one language or framework to another
argument-hint: <component> <from> <to>
---

Migrate the $0 component from $1 to $2.
Preserve all existing behavior and tests.
Run the tests when you're done and report the result.

Run it as /migrate-component SearchBar JavaScript TypeScript. $ARGUMENTS holds everything you typed, and $0, $1, $2 pick out individual arguments. Quote multi-word arguments.

Useful frontmatter options

  • description — what it does; Claude uses this to decide when to load it
  • disable-model-invocation: true — only you can run it (good for /deploy)
  • allowed-tools — tools it may use without asking during that turn
  • argument-hint — shown in autocomplete
  • context: fork — run the skill in a forked subagent

Commands worth building first

  • /ship — run lint, tests and build, then write a commit message
  • /seo-audit — check titles, descriptions, canonicals and schema
  • /release-notes — summarise commits since the last tag
  • /new-page — scaffold a page with metadata and tests

claudeagents includes 54 ready-made slash commands like /seo-audit and /launch-kit, wired to its 120+ subagents.

Frequently asked questions

How do I see all Claude Code slash commands?

Type / at the prompt. You'll see built-in commands, bundled skills and your own custom ones, and you can type letters to filter.

How do I create a custom slash command?

Create .claude/skills/<name>/SKILL.md with a description in its frontmatter. It becomes /<name>. Older files in .claude/commands/ still work.

How do I pass arguments to a custom command?

Use $ARGUMENTS for everything typed after the command, or $0, $1, $2 for individual arguments.

What's the difference between /clear and /compact?

/clear starts a fresh conversation with empty context. /compact keeps going but replaces the history with a summary to free up space.

Skip the setup: get 120+ ready-made agents

Coding, SEO and marketing kits for Claude Code, with 54 skills and 54 slash commands. $49 one-time, lifetime updates.

See what's included →

Keep reading