Claude Code Cheat Sheet

Claude Code v2.1.101 Last updated: April 11, 2026
📋 Recent Changes ✕
⌨️ Keyboard Shortcuts
General Controls
CtrlC Cancel input/generation
CtrlD Exit session
CtrlL Clear prompt input
CtrlO Toggle transcript viewer / focus viewNEW
CtrlR Reverse search history
CtrlG Open prompt in editor
CtrlX CtrlE Open in editor (alias)
CtrlB Background running task
CtrlT Toggle task list
CtrlV Paste image ([Image #N] chip)
CtrlX CtrlK Kill background agents
EscEsc Rewind or summarize
Mode Switching
ShiftTab Cycle permission modes
AltP Switch model
AltT Toggle thinking
AltO Toggle fast modeNEW
Input
\Enter Newline (quick)
CtrlJ Newline (control seq)
Prefixes
/ Slash command
! Direct bash
@ File mention + autocomplete
Transcript / Focus View (Ctrl+O)
CtrlE Toggle show all
Q / CtrlC / Esc Exit transcript
🔌 MCP Servers
Add Servers
--transport http Remote HTTP (recommended)
--transport stdio Local process
--transport sse Remote SSE
Scopes
Local ~/.claude.json (you only)
Project .mcp.json (shared/VCS)
User ~/.claude.json (global)
Manage
/mcp Interactive UI
claude mcp list List all servers
claude mcp serve Run Claude Code itself as a stdio MCP server
Elicitation Servers can request user input mid-task
2KB each Tool descriptions and server instructions are each truncated at 2KB
maxResultSizeChars _meta["anthropic/maxResultSizeChars"] raises per-tool text threshold (up to 500K chars)NEW
⚡ 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 (per-model + cache breakdown)NEW
/context Visualize context (grid)
/diff Interactive diff viewer
/copy [N] Copy last (or Nth) response
/rewind Rewind conv / code checkpoint
/export Export conversation
Config
/config Open settings
/model [model] Switch model (←→ effort)
/fast [on|off] Toggle fast mode
/theme Change color theme
/permissions View/update permissions
/effort [level] Set effort (low/medium/high/max/auto)
/color [color] Set prompt-bar color
/keybindings Customize keyboard shortcuts
/terminal-setup Configure terminal keybindings
Tools
/init Create CLAUDE.md
/memory Edit CLAUDE.md files, toggle auto memory, view entries
/mcp Manage MCP servers
/hooks Manage hooks
/skills List available skills
/agents Manage agent configurationsNEW
/chrome Chrome integration
/reload-plugins Hot-reload plugins
/add-dir <path> Add working directory
Special
/powerup Interactive feature lessonsNEW
/btw <question> Ask a side question without adding to the conversation
/plan [desc] Plan mode (+ auto-start)
/loop [interval] Schedule recurring task
/voice Toggle push-to-talk voice dictation
/doctor Diagnose installation
/stats Usage streaks & prefs
/insights Analyze sessions report
/desktop Continue in Desktop app
/remote-control Bridge to claude.ai/code (/rc)
/usage Plan limits & rate status
/schedule Cloud scheduled tasks
/ultraplan <prompt> Draft a plan in a browser session, then execute remotely or send it back to terminalNEW
/security-review Security analysis of changes
/help Show help + commands
/feedback Submit feedback (alias: /bug)
/release-notes Interactive version changelogNEW
/stickers Order stickers! 🎉
📁 Memory & Files
CLAUDE.md Locations
./CLAUDE.md or ./.claude/CLAUDE.md Project (team-shared)
./CLAUDE.local.md Local personal project notes (gitignored)
~/.claude/CLAUDE.md Personal (all projects)
/etc/claude-code/CLAUDE.md Managed policy (Linux/WSL, 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 auto-loads at startup (first 25KB or 200 lines); topic files load on demand
🧠 Workflows & Tips
Plan Mode
ShiftTab Normal → Auto-Accept → 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 · ◐ medium · ● high · ★ max
Auto Mode Denied
/permissions → Recent Retry denied with RNEW
Git Worktrees
--worktree name Isolated branch per feature
isolation: worktree Agent in own worktree
sparsePaths Checkout only needed dirs
workspace.git_worktree Status line JSON: linked worktree pathNEW
/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 (thrash detection: 3x)NEW
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 (hostname prefix default)NEW
/ultraplan Draft plan in browser, then execute remotely or send back to terminalNEW
--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
managed-settings.d/ Drop-in policy fragments
Key Settings
modelOverrides Map model picker → custom IDs
autoMemoryDirectory Custom memory dir
worktree.sparsePaths Sparse checkout dirs
sandbox.failIfUnavailable Exit if sandbox fails
hooks: if Conditional hooks (permission rule syntax)
Monitor tool Stream events from background scriptsNEW
PermissionDenied Hook: auto-mode denialNEW
showThinkingSummaries Opt-in (off by default now)NEW
allowedChannelPlugins Admin channel plugin allowlist
hooks: "defer" Pause headless → resume later
disableSkillShellExec Block !`cmd` in skills/pluginsNEW
forceRemoteSettingsRefresh Fail-closed: block startup until freshNEW
refreshInterval Re-run custom status line every N secNEW
Key Env Vars
ANTHROPIC_API_KEY
ANTHROPIC_MODEL
CLAUDE_CODE_EFFORT_LEVEL low/medium/high/max/auto
MAX_THINKING_TOKENS 0=off
ANTHROPIC_CUSTOM_MODEL_OPTION Custom /model entry
CLAUDE_CODE_SUBPROCESS_ENV_SCRUB Strip Anthropic/cloud creds from Bash, hooks, and MCP stdio subprocesses; Linux also isolates PID namespaceNEW
CLAUDE_CODE_SCRIPT_CAPS JSON caps for specific script invocations when env scrubbing is enabledNEW
CLAUDE_CODE_PERFORCE_MODE Enable Perforce-aware write protection with p4 edit hintNEW
CLAUDE_STREAM_IDLE_TIMEOUT_MS Streaming watchdog (def 90s)
CLAUDE_CODE_NO_FLICKER Alt-screen rendering (=1)NEW
MCP_CONNECTION_NONBLOCKING Skip MCP wait in -pNEW
CLAUDE_CODE_USE_MANTLE Use Mantle for Bedrock (=1)NEW
CLAUDE_CODE_CERT_STORE Comma-separated TLS CA sources: bundled, system (default: both)NEW
CLAUDECODE Detect CC shell (=1)
🔧 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 level
paths: [globs] Path-specific (YAML list)NEW
context: fork Run in subagent
$ARGUMENTS User input placeholder
${CLAUDE_SKILL_DIR} Skill's own directory
!`cmd` Dynamic context injection
plugin bin/ Ship executables for Bash toolNEW
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/plan/dontAsk/bypassPermissions
isolation: worktree Run in git worktree
memory: user|project|local Persistent memory
background: true Background task
maxTurns Limit agentic turns
initialPrompt Auto-submit first turn
SendMessage Resume agents (replaces resume)
@agent-name Mention named subagentsNEW
🖥️ 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
--allow-dangerously-skip-permissions Add bypassPermissions to Shift+Tab cycle
--output-format text/json/stream-json
--json-schema Structured
--max-turns Limit turns
--max-budget-usd Cost cap
--exclude-dynamic-system-prompt-sections Print mode: improve cross-user prompt cachingNEW
--verbose Verbose
--bare Minimal mode (skips hooks/skills/plugins/MCP/auto-memory/CLAUDE.md)
--channels Permission relay / MCP push
--remote Create web session on claude.ai
--remote-control / --rc Interactive session with Remote Control enabled
--effort low/medium/high/max
--permission-mode plan/default/…
--dangerously-skip-permissions Skip all prompts ⚠️
--chrome Chrome
nter="https://stats.storyfox.cz/count" async src="https://stats.storyfox.cz/count.js">