# Claude Code CLI cheat sheet

> Every Claude Code command, permission mode, and config file from Todd Greco’s meetup talk, on one page and kept current.

Source: https://mrballistic.com/claude-code-cli-cheatsheet/ · Author: Todd Greco (https://mrballistic.com) · Updated 2026-10-27

## Install and launch
- `curl -fsSL https://claude.ai/install.sh | bash`: macOS, Linux, WSL
- `brew install --cask claude-code`: Homebrew
- `irm https://claude.ai/install.ps1 | iex`: Windows PowerShell
- `claude`: Start an interactive session
- `claude "fix the failing test"`: Start with a first prompt
- `claude -c`: Continue the most recent conversation
- `claude -r auth-refactor`: Resume a session by name or ID
- `claude -p "explain this repo"`: Print one answer and exit (scripts, CI)
- `cat error.log | claude -p "what broke?"`: Pipe input into a one-shot query
- `claude --version`: Check the installed version

## Slash commands
- `/init`: Write a starter CLAUDE.md from your codebase
- `/help`: List every command
- `/model`: Switch models
- `/effort`: Set how hard the model thinks
- `/context`: See what’s filling the context window
- `/compact`: Summarize the conversation to free up context
- `/clear`: Start fresh in the same session
- `/resume`: Pick up an earlier session
- `/rewind`: Roll back the conversation and file edits to an earlier point
- `/btw`: Ask a side question without adding it to the context
- `/code-review`: Review pending changes (alias /review); add --fix to apply
- `/usage`: Session cost, plan limits, activity (alias /cost)
- `/memory`: Edit the CLAUDE.md files in play
- `/powerup`: Interactive lessons on features you haven’t tried
- `/doctor`: Diagnose your install and settings

## Keyboard shortcuts
- Shift+Tab: Cycle permission modes
- Esc: Interrupt Claude or close a dialog
- Esc Esc: Clear the draft, or open rewind when it’s empty
- Ctrl+R: Search prompt history
- Ctrl+B: Send a running task to the background
- Ctrl+O: Open the full transcript
- Ctrl+G: Edit the prompt in your $EDITOR
- Option+P: Switch model (Alt+P on Windows/Linux)
- Option+T: Toggle extended thinking (Alt+T)
- Option+O: Toggle fast mode (Alt+O)

## Permission modes
- Manual (`--permission-mode default`): Asks before edits and commands. Use when: Learning a codebase, or anything risky.
- Edit automatically (`--permission-mode acceptEdits`): Edits files and runs basic file commands (mkdir, mv, cp) without asking; asks for everything else. Use when: You trust the edits but want to see commands.
- Plan (`--permission-mode plan`): Reads and plans; no edits until you approve the plan. Use when: Before a big change, or to understand code.
- Auto (`--permission-mode auto`): A classifier reviews each action and blocks risky ones; no prompts for the rest. Use when: Well-scoped work with a good CLAUDE.md.
- Don’t ask (`--permission-mode dontAsk`): Runs only pre-approved tools; denies anything that would prompt. Use when: Scripts and CI with an allowlist.
- Bypass permissions (`--dangerously-skip-permissions`): No prompts, no checks. Deny rules still apply.. Use when: Throwaway containers and VMs only.
- `claude --permission-mode auto`: Interactive
- `claude -p "run the tests and fix failures" --permission-mode auto`: Headless

## CLAUDE.md
A markdown file Claude reads at the start of every session: what the project is, how to build it, and what not to touch. Run /init to draft one.
- `./CLAUDE.md`: Project, committed with the repo (or ./.claude/CLAUDE.md)
- `./CLAUDE.local.md`: Project, just for you (gitignored)
- `~/.claude/CLAUDE.md`: You, across every project
- `.claude/rules/*.md`: Topic rules, optionally scoped to paths

## Skills
A folder with a SKILL.md: instructions, and optionally scripts and reference files. Claude loads one when its description matches the task, or you run it as /skill-name.
- `.claude/skills/<name>/SKILL.md`: This project
- `~/.claude/skills/<name>/SKILL.md`: Every project

## Plugins
- Superpowers (https://github.com/obra/superpowers): Makes Claude brainstorm, plan, and test before it writes code, then review before it ships. Install: `/plugin install superpowers@claude-plugins-official`
- Impeccable (https://impeccable.style): Gives Claude a design vocabulary: critique a page, audit it for accessibility, then polish, simplify, or push it bolder. Install: `/plugin marketplace add pbakaus/impeccable`, then `/plugin install impeccable@impeccable`

## MCP servers
- `claude mcp add --transport http my-server https://api.example.com/mcp`: Remote (HTTP)
- `claude mcp add --transport stdio my-server -- npx -y my-mcp-server`: Local process (stdio)
- `claude mcp add-json my-server '{"type":"stdio","command":"npx","args":["-y","my-mcp-server"]}'`: From JSON
- Local scope ((default)): stored in `~/.claude.json`; You, in this project only
- Project scope (--scope project): stored in `.mcp.json`; Everyone on the repo (commit it)
- User scope (--scope user): stored in `~/.claude.json`; You, in every project
- GitHub: `claude mcp add --transport http github https://api.githubcopilot.com/mcp/ --header "Authorization: Bearer YOUR_GITHUB_PAT"`
- Playwright: `claude mcp add playwright -- npx @playwright/mcp@latest`
- Context7: `claude mcp add --transport stdio context7 -- npx -y @upstash/context7-mcp`
- Brave Search: `claude mcp add --transport stdio --env BRAVE_API_KEY=YOUR_KEY brave -- npx -y @brave/brave-search-mcp-server`
- Filesystem: `claude mcp add --transport stdio filesystem -- npx -y @modelcontextprotocol/server-filesystem ~/notes`
- Sequential Thinking: `claude mcp add --transport stdio thinking -- npx -y @modelcontextprotocol/server-sequential-thinking`

## Hooks
Commands that run on Claude Code events, every time, whatever the model decides. Configure them in .claude/settings.json or with /hooks.
- SessionStart: When a session starts or resumes
- UserPromptSubmit: Before Claude sees your prompt
- PreToolUse: Before a tool runs (can block it)
- PermissionRequest: When a permission prompt would appear
- PostToolUse: After a tool succeeds
- Notification: When Claude needs your attention
- Stop: When Claude finishes responding
- PreCompact: Before the context is compacted

## Subagents
Claude can hand work to subagents. Each gets its own context window, tools, and instructions, and returns only a summary, so your main context stays clean.
- Explore: Fast, read-only search across the codebase
- Plan: Research for plan mode
- general-purpose: Multi-step tasks that need every tool

## Links
- [Claude Code docs](https://code.claude.com/docs): Commands, settings, and guides
- [Permission modes](https://code.claude.com/docs/en/permission-modes): Every mode and how auto mode decides
- [Superpowers](https://github.com/obra/superpowers): Jesse Vincent’s methodology plugin
- [Impeccable](https://impeccable.style): Paul Bakaus’s design skill
- [awesome-claude-code](https://github.com/hesreallyhim/awesome-claude-code): Community skills, hooks, and plugins
- [anthropics/skills](https://github.com/anthropics/skills): Official skills from Anthropic
- [Model Context Protocol](https://modelcontextprotocol.io): The spec and SDKs
- [MCP servers](https://github.com/modelcontextprotocol/servers): Reference servers and a directory of others