← Back to Course|Course ToolsClaude Code v2.1.101

⌨️ Claude Code — Cheat Sheet

Keyboard shortcuts · Slash commands · Workflows · MCP · Memory · CLI flags

Setup Guide →
Keyboard shortcuts for:
Blue keys change with OS

⌨️ Keyboard Shortcuts

General Controls
Ctrl C
Cancel input/generation
Ctrl D
Exit session
Ctrl L
Clear prompt input
Ctrl ONEW
Toggle transcript / focus view
Ctrl R
Reverse search history
Ctrl G
Open prompt in editor
Ctrl XCtrl E
Open in editor (alias)
Ctrl B
Background running task
Ctrl T
Toggle task list
Ctrl V
Paste image ([Image #N] chip)
Ctrl XCtrl K
Kill background agents
EscEsc
Rewind or summarize
Mode Switching (Mac)
⇧ Tab
Cycle permission modes
⌥ P
Switch model
⌥ T
Toggle thinking
⌥ O
Toggle fast mode
Input
\Enter
Newline (quick)
Ctrl J
Newline (control seq)
Prefixes
/Slash command
!Direct bash
@File mention + autocomplete
Transcript / Focus View (Ctrl+O)
CtrlE
Toggle show all
Q / Ctrl C / Esc
Exit transcript

⚡ Slash Commands

Session
/clearClear conversation
/compact [focus]Compact context
/resumeResume/switch session
/rename [name]Name current session
/branch [name]Branch conversation (/fork alias)
/costToken usage (per-model + cache)
/contextVisualize context (grid)
/diffInteractive diff viewer
/copy [N]Copy last (or Nth) response
/rewindRewind conv / code checkpoint
/exportExport conversation
Config
/configOpen settings
/model [model]Switch model (←→ effort)
/fast [on|off]Toggle fast mode
/themeChange color theme
/permissionsView/update permissions
/effort [level]Set effort (low/medium/high/max/auto)
/color [color]Set prompt-bar color
/keybindingsCustomize keyboard shortcuts
/terminal-setupConfigure terminal keybindings
Tools
/initCreate CLAUDE.md
/memoryEdit CLAUDE.md, toggle auto memory
/mcpManage MCP servers
/hooksManage hooks
/skillsList available skills
/agentsNEWManage agent configurations
/chromeChrome integration
/reload-pluginsHot-reload plugins
/add-dir <path>Add working directory
Special
/powerupInteractive feature lessons
/btw <question>Side question (no context cost)
/plan [desc]Plan mode (+ auto-start)
/loop [interval]Schedule recurring task
/voiceToggle push-to-talk voice
/doctorDiagnose installation
/statsUsage streaks & prefs
/insightsAnalyze sessions report
/desktopContinue in Desktop app
/remote-controlBridge to claude.ai/code (/rc)
/usagePlan limits & rate status
/scheduleCloud scheduled tasks
/ultraplan <prompt>NEWPlan in browser, execute remotely
/security-reviewSecurity analysis of changes
/helpShow help + commands
/feedbackSubmit feedback (alias: /bug)
/release-notesInteractive version changelog

🧠 Workflows & Tips

Plan Mode
⇧ TabNormal → Auto-Accept → Plan
--permission-mode planStart in plan mode
Thinking & Effort
⌥ T
Toggle thinking on/off
"ultrathink"Max effort for turn
Ctrl O
See thinking (verbose)
/effort○ low · ◐ medium · ● high · ★ max
Auto Mode Denied
/permissions → RecentRetry denied with R
Git Worktrees
--worktree nameIsolated branch per feature
isolation: worktreeAgent in own worktree
sparsePathsCheckout only needed dirs
workspace.git_worktreeNEWStatus line JSON: linked worktree
/batchAuto-creates worktrees
Voice Mode
/voiceEnable push-to-talk
Space (hold)Record, release to send
20 languages:EN, ES, FR, DE, CZ, PL…
Context Management
/contextUsage + optimization tips
/compact [focus]Compress with focus
Auto-compact~95% capacity (thrash detection: 3×)
1M contextOpus 4.6 (Max/Team/Ent)
CLAUDE.mdSurvives compaction!
Session Power Moves
claude -cContinue last conversation
claude -r "name"Resume by name
/btw questionSide Q, no context cost
SDK / Headless
claude -p "query"Non-interactive
--output-format jsonStructured output
--max-budget-usd 5Cost cap
cat file | claude -pPipe input
Scheduling & Remote
/loop 5m msgRecurring task
/rcRemote control (hostname prefix)
--remoteWeb session on claude.ai

🔧 Skills & Agents

Built-in Skills
/simplifyCode review (3 parallel agents)
/batchLarge parallel changes (5–30 worktrees)
/debug [desc]Troubleshoot from debug log
/loop [interval]Recurring scheduled task
/claude-apiLoad API + SDK reference
Custom Skill Locations
.claude/skills/<name>/Project skills
~/.claude/skills/<name>/Personal skills
Skill Frontmatter
descriptionAuto-invocation trigger
allowed-toolsSkip permission prompts
modelOverride model for skill
effortOverride effort level
paths: [globs]Path-specific (YAML list)
context: forkRun in subagent
$ARGUMENTSUser input placeholder
${CLAUDE_SKILL_DIR}Skill's own directory
!`cmd`Dynamic context injection
plugin bin/Ship executables for Bash tool
Built-in Agents
ExploreFast read-only (Haiku)
PlanResearch for plan mode
GeneralFull tools, complex tasks
BashTerminal separate context
Agent Frontmatter
permissionModedefault/acceptEdits/plan/dontAsk/bypass
isolation: worktreeRun in git worktree
memory: user|project|localPersistent memory
background: trueBackground task
maxTurnsLimit agentic turns
initialPromptAuto-submit first turn
SendMessageResume agents (replaces resume)
@agent-nameMention named subagents

🔌 MCP Servers

Add Servers
--transport httpRemote HTTP (recommended)
--transport stdioLocal process
--transport sseRemote SSE
Scopes
Local~/.claude.json (you only)
Project.mcp.json (shared/VCS)
User~/.claude.json (global)
Manage
/mcpInteractive UI
claude mcp listList all servers
claude mcp serveRun CC as stdio MCP server
maxResultSizeCharsRaise per-tool limit (up to 500K chars)

📁 Memory & Files

CLAUDE.md Locations
./CLAUDE.mdProject (team-shared)
./CLAUDE.local.mdLocal personal (gitignored)
~/.claude/CLAUDE.mdPersonal (all projects)
/etc/claude-code/CLAUDE.mdManaged policy (org-wide)
Rules & Import
.claude/rules/*.mdProject rules
~/.claude/rules/*.mdUser rules
paths: frontmatterPath-specific rules
@path/to/fileImport in CLAUDE.md
Auto Memory
~/.claude/projects/<proj>/memory/Memory directory
MEMORY.md auto-loads at startup (first 25KB or 200 lines). Topic files load on demand.

⚙️ Config & ENV

Config Files
~/.claude/settings.jsonUser settings
.claude/settings.jsonProject (shared)
.claude/settings.local.jsonLocal only
~/.claude.jsonOAuth, MCP, state
.mcp.jsonProject MCP servers
managed-settings.d/Drop-in policy fragments
Key Settings
modelOverridesMap model picker → custom IDs
autoMemoryDirectoryCustom memory dir
worktree.sparsePathsSparse checkout dirs
sandbox.failIfUnavailableExit if sandbox fails
hooks: ifConditional hooks
Monitor toolNEWStream events from bg scripts
showThinkingSummariesOpt-in (off by default)
refreshIntervalNEWRe-run status line every N sec
Key Env Vars
ANTHROPIC_API_KEYYour Anthropic API key
ANTHROPIC_MODELDefault model override
CLAUDE_CODE_EFFORT_LEVELlow/medium/high/max/auto
MAX_THINKING_TOKENS0 = off
CLAUDE_CODE_SUBPROCESS_ENV_SCRUBNEWStrip creds from subprocesses
CLAUDE_CODE_SCRIPT_CAPSNEWJSON caps for script invocations
CLAUDE_STREAM_IDLE_TIMEOUT_MSStreaming watchdog (def 90s)
CLAUDE_CODE_NO_FLICKERAlt-screen rendering (=1)
CLAUDE_CODE_USE_MANTLENEWUse Mantle for Bedrock (=1)
CLAUDECODEDetect CC shell (=1)

🖥 CLI & Flags

Core Commands
claudeInteractive
claude "q"With prompt
claude -p "q"Headless
claude -cContinue last
claude -r "n"Resume by name
claude updateUpdate Claude Code
Key Flags
--modelSet model
-wGit worktree
-n / --nameSession name
--add-dirAdd directory
--agentUse agent
--allowedToolsPre-approve tools
--output-formattext / json / stream-json
--json-schemaStructured output schema
--max-turnsLimit turns
--max-budget-usdCost cap
--verboseVerbose output
--bareMinimal (skip hooks/skills/MCP)
--channelsPermission relay / MCP push
--remoteCreate web session on claude.ai
--effortlow / medium / high / max
--permission-modeplan / default / acceptEdits / …
--dangerously-skip-permissionsSkip all prompts ⚠️
Permission Modes
defaultPrompts for permissions
acceptEditsAuto-accept file edits
planRead-only (no writes)
dontAskDeny unless pre-allowed
bypassPermissionsSkip all ⚠️
Related:⌨️ Claude Code CLI Setup📚 Lesson 10 — Claude Code Deep Dive🔮 Lesson 23 — Claude Code Superuser📚 Prompt Library