Claude Code Cheat Sheet

Claude Code Cheat Sheet

Claude Code v2.1.81
Last updated: March 23, 2026

📋 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
CtrlC Cancel input/generation
CtrlD Exit session
CtrlL Clear screen
CtrlO Toggle verbose output
CtrlR Reverse search history
CtrlG Open prompt in editor
CtrlB Background running task
CtrlT Toggle task list
CtrlV Paste image
CtrlF Kill background agents (×2)
EscEsc Rewind / undo
Mode Switching
ShiftTab Cycle permission modes
AltP Switch model
AltT Toggle thinking
Input
\Enter Newline (quick)
CtrlJ Newline (control seq)
Prefixes
/ Slash command
! Direct bash
@ File mention + autocomplete
Session Picker
↑↓ Navigate
←→ Expand/collapse
P Preview
R Rename
/ Search
A All projects
B Current branch

🔌 MCP Servers

Add Servers
--transport http Remote HTTP (recommended)
--transport stdio Local process
--transport sse Remote SSE
Scopes
Local ~/.claude.json (per project)
Project .mcp.json (shared/VCS)
User ~/.claude.json (global)
Manage
/mcp Interactive UI
claude mcp list List all servers
claude mcp serve CC as MCP server
Elicitation Servers request input mid-taskNEW

⚡ Slash Commands

Session
/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
/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)NEW
/color [color] Set prompt-bar color
Tools
/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
Special
/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/codeNEW
/stickers Order stickers! 🎉

📁 Memory & Files

CLAUDE.md Locations
./CLAUDE.md Project (team-shared)
~/.claude/CLAUDE.md Personal (all projects)
/etc/claude-code/ Managed (org-wide)
Rules & Import
.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/
MEMORY.md + topic files, auto-loaded

🧠 Workflows & Tips

Plan Mode
ShiftTab Normal → Auto → Plan
--permission-mode plan Start in plan mode
Thinking & Effort
AltT Toggle thinking on/off
"ultrathink" Max effort for turn
CtrlO See thinking (verbose)
/effort ○ low · ◐ med · ● highNEW
Git Worktrees
--worktree name Isolated branch per feature
isolation: worktree Agent in own worktree
sparsePaths Checkout only needed dirsNEW
/batch Auto-creates worktrees
Voice Mode
/voice Enable push-to-talk
Space (hold) Record, release to send
20 languages EN, ES, FR, DE, CZ, PL…
Context Management
/context Usage + optimization tips
/compact [focus] Compress with focus
Auto-compact ~95% capacity
1M context Opus 4.6 (Max/Team/Ent)
CLAUDE.md Survives compaction!
Session Power Moves
claude -c Continue last conv
claude -r "name" Resume by name
/btw question Side Q, no context cost
SDK / Headless
claude -p "query" Non-interactive
--output-format json Structured output
--max-budget-usd 5 Cost cap
cat file | claude -p Pipe input
Scheduling & Remote
/loop 5m msg Recurring task
/rc Remote control
--remote Web session on claude.ai

⚙️ Config & Env

Config Files
~/.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
modelOverrides Map model picker → custom IDs
autoMemoryDirectory Custom memory dir
worktree.sparsePaths Sparse checkout dirsNEW
Key Env Vars
ANTHROPIC_API_KEY
ANTHROPIC_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

🔧 Skills & Agents

Built-in Skills
/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
.claude/skills/<name>/ Project skills
~/.claude/skills/<name>/ Personal skills
Skill Frontmatter
description Auto-invocation trigger
allowed-tools Skip permission prompts
model Override model for skill
effort Override effort levelNEW
context: fork Run in subagent
$ARGUMENTS User input placeholder
${CLAUDE_SKILL_DIR} Skill's own directory
!`cmd` Dynamic context injection
Built-in Agents
Explore Fast read-only (Haiku)
Plan Research for plan mode
General Full tools, complex tasks
Bash Terminal separate context
Agent Frontmatter
permissionMode default/acceptEdits/dontAsk/plan
isolation: worktree Run in git worktree
memory: user|project Persistent memory
background: true Background task
maxTurns Limit agentic turns
SendMessage Resume agents (replaces resume)NEW

🖥️ CLI & Flags

Core Commands
claude Interactive
claude "q" With prompt
claude -p "q" Headless
claude -c Continue last
claude -r "n" Resume
claude update Update
Key Flags
--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)NEW
--channels Permission relay / MCP pushNEW
--remote Web session
--chrome Chrome

Permission Modes:
default prompts
·
acceptEdits auto-accept edits
·
plan read-only
·
dontAsk deny unless allowed
·
bypassPermissions skip all

Key Env Vars:
ANTHROPIC_API_KEY
·
ANTHROPIC_MODEL
·
CLAUDE_CODE_EFFORT_LEVEL (low/med/high)
·
MAX_THINKING_TOKENS (0=off)
·
CLAUDE_CODE_MAX_OUTPUT_TOKENS (def 32K)
·
CLAUDE_CODE_DISABLE_CRON

Claude Code v2.1.81 represents a significant evolution in the code assistant, introducing several key advancements aimed at enhancing developer productivity and workflow management. The update focuses heavily on improved memory management, enhanced control over agent behavior, and streamlined integration with MCP (Mission Control Platform) servers. A major shift is the introduction of the `--bare` flag, offering a minimal headless mode without hooks, LSP, or plugins, catering to advanced users requiring a lightweight environment.

Several interface changes are worth noting, including the renaming of `/fork` to `/branch`, maintaining the existing alias for convenience. The auto-resumption of SendMessage agents has been disabled, prompting the user to actively manage agent states. Furthermore, the addition of “effort frontmatter” within skills and slash commands allows for granular control over the agent's intensity, configurable through the `/effort` command. The introduction of channels and MCP push messages via permission relay represents a preview feature enabling advanced scenarios.

Memory management has been improved with the addition of auto-memory and rules/import functionalities which allow for the storage and management of project data within a structured CLAUDE.md format. This system integrates local, project, and organization-wide settings, facilitating efficient knowledge sharing and contextual awareness. The worktree feature adds isolation and sparse paths capabilities, allowing developers to manage parallel branches and files efficiently—benefiting significantly from the “batch” command.

The slash command system has been expanded, adding features like /copy, /export, /stats, /insights, and desktop continuation. New commands such as /btw, /plan, /loop, /voice, /doctor, /rc, and /pr-comments have been introduced, creating more interactive and dynamic control.

Configuration options include model selection via `/model`, theme customization with `/color`, and permission management via `/permissions`. Furthermore, several key environment variables such as `ANTHROPIC_API_KEY`, `CLAUDE_CODE_EFFORT_LEVEL`, and `MAX_THINKING_TOKENS` can be adjusted.

The update includes a robust set of built-in skills, including /simplify (code review), /batch (large parallel changes), /debug (troubleshooting), and /loop (recurring tasks). These are supported by a range of agents, including explore, plan, and general, each designed to address specific development tasks. The SDK and headless capabilities continue to be supported, enabling integration with various development tools and environments. The CLI and flags provide flexible control over the assistant's behavior, with options for setting models, managing worktrees, input methods, and output formats.

Permission Modes continue to be a cornerstone of the assistant’s functionality, offering distinct behavioral settings based on the individual's needs and the specific task at hand. Key environment variables, like `ANTHROPIC_API_KEY` and model overrides, contribute to a highly customizable and adaptable development environment.