Claude Code Cheat Sheet

Claude Code v2.1.81 · Last updated: March 24, 2026 · By Wil Waldon

Install

npm install -g @anthropic-ai/claude-code

Requires Node.js >= 18. Authenticate with claude on first run.

Table of Contents

• Recent Changes
• Keyboard Shortcuts
• Slash Commands
• Memory & Files
• MCP Servers
• Workflows & Tips
• Config & Env
• Skills & Agents
• CLI & Flags
• Permission Modes

---

Recent Changes

• --bare flag — minimal headless mode (no hooks/LSP/plugins)
• --channels — permission relay & MCP push messages (preview)
• effort frontmatter for skills & slash commands
• /fork renamed to /branch (alias kept)
• SendMessage auto-resumes stopped agents

---

⌨️ Keyboard Shortcuts

General Controls

Shortcut	Action
Ctrl C	Cancel input/generation
Ctrl D	Exit session
Ctrl L	Clear screen
Ctrl O	Toggle verbose output
Ctrl R	Reverse search history
Ctrl G	Open prompt in editor
Ctrl B	Background running task
Ctrl T	Toggle task list
Ctrl V	Paste image
Ctrl F	Kill background agents (×2)
Esc Esc	Rewind / undo

Mode Switching

Shortcut	Action
Shift Tab	Cycle permission modes
Alt P	Switch model
Alt T	Toggle thinking

Input

Shortcut	Action
\ Enter	Newline (quick)
Ctrl J	Newline (control seq)

Prefixes

Prefix	Action
/	Slash command
!	Direct bash
@	File mention + autocomplete

Session Picker

Key	Action
↑↓	Navigate
←→	Expand/collapse
P	Preview
R	Rename
/	Search
A	All projects
B	Current branch

---

⚡ Slash Commands

Session

Command	Action
/clear	Clear conversation
/compact [focus]	Compact context
/resume	Resume/switch session
/rename [name]	Name current session
/branch [name]	Branch conversation (/fork alias)
/cost	Token usage stats
/context	Visualize context (grid)
/diff	Interactive diff viewer
/copy	Copy last response
/export	Export conversation

Config

Command	Action
/config	Open settings
/model [model]	Switch model (←→ effort)
/fast [on|off]	Toggle fast mode
/vim	Toggle vim mode
/theme	Change color theme
/permissions	View/update permissions
/effort [level]	Set effort (low/med/high)
/color [color]	Set prompt-bar color
/keybindings	Customize keyboard shortcuts
/terminal-setup	Configure terminal keybindings

Tools

Command	Action
/init	Create CLAUDE.md
/memory	Edit CLAUDE.md files
/mcp	Manage MCP servers
/hooks	Manage hooks
/skills	List available skills
/agents	Manage agents
/chrome	Chrome integration
/reload-plugins	Hot-reload plugins
/add-dir <path>	Add working directory

Special

Command	Action
/btw <question>	Side question (no context)
/plan [desc]	Plan mode (+ auto-start)
/loop [interval]	Schedule recurring task
/voice	Push-to-talk voice (20 langs)
/doctor	Diagnose installation
/rc	Enable remote control
/pr-comments [PR]	Fetch GitHub PR comments
/stats	Usage streaks & prefs
/insights	Analyze sessions report
/desktop	Continue in Desktop app
/remote-control	Bridge terminal to claude.ai/code
/usage	Plan limits & rate status
/schedule	Cloud scheduled tasks
/security-review	Security analysis of changes
/help	Show help + commands
/feedback	Submit feedback (alias: /bug)
/release-notes	View full changelog
/stickers	Order stickers! 🎉

---

📁 Memory & Files

CLAUDE.md Locations

Path	Scope
./CLAUDE.md	Project (team-shared)
~/.claude/CLAUDE.md	Personal (all projects)
/etc/claude-code/	Managed (org-wide)

Rules & Import

Path / Syntax	Description
.claude/rules/*.md	Project rules
~/.claude/rules/*.md	User rules
paths: frontmatter	Path-specific rules
@path/to/file	Import in CLAUDE.md

Auto Memory

~/.claude/projects/<proj>/memory/

Contains MEMORY.md + topic files, auto-loaded per project.

---

🔌 MCP Servers

Add Servers

Flag	Transport
--transport http	Remote HTTP (recommended)
--transport stdio	Local process
--transport sse	Remote SSE

Scopes

Scope	File
Local	.claude.json (per project)
Project	.mcp.json (shared/VCS)
User	~/.claude.json (global)

Manage

Command	Action
/mcp	Interactive UI
claude mcp list	List all servers
claude mcp serve	CC as MCP server
Elicitation	Servers request input mid-task

---

🧠 Workflows & Tips

Plan Mode

Input	Action
Shift Tab	Normal → Auto-Accept → Plan
--permission-mode plan	Start in plan mode

Thinking & Effort

Input	Action
Alt T	Toggle thinking on/off
"ultrathink"	Max effort for turn
Ctrl O	See thinking (verbose)
/effort	○ low · ◐ med · ● high

Git Worktrees

Input	Action
--worktree name	Isolated branch per feature
isolation: worktree	Agent in own worktree
sparsePaths	Checkout only needed dirs
/batch	Auto-creates worktrees

Voice Mode

Input	Action
/voice	Enable push-to-talk
Space (hold)	Record, release to send
20 languages	EN, ES, FR, DE, CZ, PL…

Context Management

Input	Action
/context	Usage + optimization tips
/compact [focus]	Compress with focus
Auto-compact	Triggers at ~95% capacity
1M context	Opus 4.6 (Max/Team/Ent)
CLAUDE.md	Survives compaction

Session Power Moves

Input	Action
claude -c	Continue last conversation
claude -r "name"	Resume by name
/btw question	Side question, no context cost

SDK / Headless

Input	Action
claude -p "query"	Non-interactive
--output-format json	Structured output
--max-budget-usd 5	Cost cap
cat file | claude -p	Pipe input

Scheduling & Remote

Input	Action
/loop 5m msg	Recurring task
/rc	Remote control
--remote	Web session on claude.ai

---

⚙️ Config & Env

Config Files

File	Purpose
~/.claude/settings.json	User settings
.claude/settings.json	Project (shared)
.claude/settings.local.json	Local only
~/.claude.json	OAuth, MCP, state
.mcp.json	Project MCP servers

Key Settings

Setting	Description
modelOverrides	Map model picker → custom IDs
autoMemoryDirectory	Custom memory dir
worktree.sparsePaths	Sparse checkout dirs

Key Environment Variables

Variable	Description
ANTHROPIC_API_KEY	API key
ANTHROPIC_MODEL	Default model
CLAUDE_CODE_EFFORT_LEVEL	low/med/high
MAX_THINKING_TOKENS	0 = off
ANTHROPIC_CUSTOM_MODEL_OPTION	Custom /model entry
CLAUDE_CODE_PLUGIN_SEED_DIR	Multiple plugin seed dirs
CLAUDECODE	Detect CC shell (=1)
IS_DEMO	Demo mode (hide email/org)
CLAUDE_CODE_MAX_OUTPUT_TOKENS	Max output tokens (default 32K)
CLAUDE_CODE_DISABLE_CRON	Disable scheduled tasks

Hooks

Hooks run user-defined commands at specific lifecycle events. Configure in settings or via /hooks.

Event	Fires When
PreToolUse	Before a tool executes
PostToolUse	After a tool executes
Notification	When Claude sends a notification
Stop	When Claude finishes a response
SubagentStop	When a subagent finishes

---

🔧 Skills & Agents

Built-in Skills

Command	Action
/simplify	Code review (3 parallel agents)
/batch	Large parallel changes (5–30 worktrees)
/debug [desc]	Troubleshoot from debug log
/loop [interval]	Recurring scheduled task
/claude-api	Load API + SDK reference

Custom Skill Locations

Path	Scope
.claude/skills/<name>/	Project skills
~/.claude/skills/<name>/	Personal skills

Skill Frontmatter

Key	Description
description	Auto-invocation trigger
allowed-tools	Skip permission prompts
model	Override model for skill
effort	Override effort level
context: fork	Run in subagent
$ARGUMENTS	User input placeholder
${CLAUDE_SKILL_DIR}	Skill's own directory
!`cmd`	Dynamic context injection

Built-in Agents

Agent	Description
Explore	Fast read-only (Haiku)
Plan	Research for plan mode
General	Full tools, complex tasks
Bash	Terminal separate context

Agent Frontmatter

Key	Description
permissionMode	default/acceptEdits/plan/dontAsk/bypass
isolation: worktree	Run in git worktree
memory: user|project	Persistent memory
background: true	Background task
maxTurns	Limit agentic turns
SendMessage	Resume agents (replaces resume)

---

🖥️ CLI & Flags

Core Commands

Command	Action
claude	Interactive
claude "q"	With prompt
claude -p "q"	Headless
claude -c	Continue last
claude -r "n"	Resume
claude update	Update

Key Flags

Flag	Action
--model	Set model
-w	Git worktree
-n / --name	Session name
--add-dir	Add dir
--agent	Use agent
--allowedTools	Pre-approve
--output-format	json/stream
--json-schema	Structured
--max-turns	Limit turns
--max-budget-usd	Cost cap
--console	Auth via Anthropic Console
--verbose	Verbose
--bare	Minimal headless (no hooks/LSP)
--channels	Permission relay / MCP push
--remote	Web session
--effort	low/med/high/max
--permission-mode	plan/default/…
--dangerously-skip-permissions	Skip all prompts ⚠️
--chrome	Chrome

---

Permission Modes

default prompts · acceptEdits auto-accept edits · plan read-only · dontAsk deny unless allowed · bypassPermissions skip all · --dangerously-skip-permissions CLI flag