Claude Code Placemat

Verified

New (recent release)

Unverified

BUILDER: Bare Headless claude -p ""

Keys & Shortcuts

General Controls

`Ctrl C` / `D`	Cancel input / Exit session
`Ctrl L`	Clear screen + full redraw
`Ctrl O`	Toggle verbose output
`Ctrl R`	Reverse search history
`Ctrl G`	Open prompt in external editor
`Ctrl B`	Background running task
`Ctrl T`	Toggle task list
`Ctrl V`	Paste image from clipboard
`Ctrl X K`	Kill background agents (chord, x2)
`Esc Esc`	Rewind / undo state

Mode & Input

`Tab`	Cycle permission modes
`\ P`	Switch model
`\ T`	Toggle thinking on/off
`\ Enter`	Newline (quick)
`Ctrl J`	Newline (control seq)

Session Picker Nav

`P` / `R`	Preview / Rename session
`/`	Search sessions
`A` / `B`	Filter All projects / Current branch

Slash Commands (Core)

Session Management

`/clear`	Clear conversation context
`/compact [focus]`	Compact context to free space
`/resume`	Display session picker menu
`/rename [name]`	Name current session
`/branch [name]`	Branch convo (formerly /fork)
`/cost`	Token usage & per-model cost breakdown
`/context`	Visualize context window (grid)
`/diff`	Interactive diff viewer
`/copy`	Copy last response
`/export`	Export conversation

Configuration

`/config`	Open settings interface
`/model [model]`	Switch model manually
`/effort [level]`	Set effort (low/med/high/auto)
`/fast [on/off]`	Toggle Fast mode
`/permissions`	View/update tool permissions
`/color [color]`	Set prompt-bar color
`/keybindings`	Customize keyboard shortcuts
`/terminal-setup`	Configure terminal integration
`/theme`	Change color theme
`/release-notes`	Interactive version picker for release notes

Slash Commands (Tools)

Development Tools

`/init`	Create CLAUDE.md memory
`/memory`	Edit CLAUDE.md files directly
`/mcp`	Manage MCP servers
`/hooks`	Manage event lifecycle hooks
`/skills`	List available active skills
`/agents`	Manage sub-agents
`/chrome`	Chrome browser integration
`/add-dir <path>`	Add working directory to context
`/reload-plugins`	Hot-reload local plugins

Special & Utility

`/btw <query>`	Side question (does not alter context)
`/plan [desc]`	Switch to Plan Mode directly
`/loop [interval]`	Schedule recurring background task
`/schedule`	Cloud scheduled tasks
`/voice`	Push-to-talk voice prompting
`/doctor`	Diagnose installation/env issues
`/pr-comments [PR]`	Fetch GitHub PR comments
`/security-review`	Security analysis of uncommitted code
`/powerup`	Interactive lessons teaching CC features with animated demos
`/stats` / `/insights`	Usage streaks / HTML sessions report
`/desktop`	Continue session in Desktop app
`/remote-control`	Bridge session to claude.ai/code

CLI & Headless Flags

Core Execution

`claude`	Start interactive REPL
`claude -p "q"`	Headless execution (scripting)
`claude -c` / `-r "n"`	Continue last / Resume specific
`claude --from-pr`	Resume session linked to a PR
`claude --fork-session`	Fork existing session on resume

Headless & CI Flags

`--bare`	Minimal headless (no hooks/LSP)
`--channels`	Permission relay / MCP push msg
`--output-format json`	Structured JSON output
`--json-schema`	Strict JSON schema validation
`--dangerously-skip-permissions`	Skip all approval prompts

State & Behavior

`-w` / `--worktree`	Start in isolated git worktree
`--effort`	Set effort level (low/med/high)
`--model`	Override specific model at launch
`--fallback-model`	Fallback if primary is overloaded
`--permission-mode plan`	Start in read-only plan mode
`--max-budget-usd`	Set cost cap for session
`--remote`	Start web-accessible session
`--remote-control-session-name-prefix`	Custom hostname prefix for Remote Control session names

Config & Environment

Files & Priority

`~/.claude/settings.json`	User global defaults
`.claude/settings.json`	Project shared (committed)
`.claude/settings.local.json`	Project local only (gitignored)
`~/.claude.json`	OAuth, MCP, state configuration
`.mcp.json`	Project-specific MCP servers
`managed-settings.d/`	Drop-in policy fragments (alphabetical merge)

Key JSON Settings

`modelOverrides`	Map model picker to custom IDs
`autoMemoryDirectory`	Custom auto-loaded memory dir
`worktree.sparsePaths`	Sparse checkout dirs for agents
`showThinkingSummaries`	Show thinking summaries in interactive sessions (default: false)
`disableSkillShellExecution`	Disable inline shell execution in skills and custom slash commands
`forceRemoteSettingsRefresh`	Block startup until remote managed settings are freshly fetched; fail-closed on fetch failure

Environment Variables

`ANTHROPIC_API_KEY`	Auth override
`ANTHROPIC_MODEL`	Default model override
`CLAUDE_CODE_EFFORT_LEVEL`	Default effort (low/med/high)
`MAX_THINKING_TOKENS`	Cap extended thinking limits
`CLAUDE_CODE_PLUGIN_SEED_DIR`	Multiple plugin seed directories
`IS_DEMO`	Demo mode (hides email/org)
`CLAUDECODE`	Detects if running inside CC shell
`CLAUDE_CODE_SUBPROCESS_ENV_SCRUB`	Strip credentials from subprocesses
`CLAUDE_CODE_MCP_SERVER_NAME` / `CLAUDE_CODE_MCP_SERVER_URL`	Inject server identity into MCP headerHelper scripts
`CLAUDE_CODE_NO_FLICKER=1`	Opt into flicker-free alt-screen rendering with virtualized scrollback
`MCP_CONNECTION_NONBLOCKING=true`	Skip MCP connection wait in headless (-p) mode
`CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE`	Keep marketplace cache when git pull fails (offline envs)

Skills & Agent Frontmatter

Built-in Skills & Locations

`/simplify`	Code review (3 parallel agents)
`/batch`	Large parallel changes (5-30 worktrees)
`/claude-api`	Load API + SDK reference into context
`.claude/skills/<name>/`	Project specific skill directory
`~/.claude/skills/<name>/`	Global personal skill directory
`plugin: bin/`	Plugin executables in bin/ invocable as bare commands from Bash tool

Skill YAML Frontmatter

`description`	Auto-invocation trigger string
`effort`	Override effort level specifically for skill
`allowed-tools`	Skip permission prompts for skill
`context: fork`	Run skill logic in an isolated subagent
`$ARGUMENTS`	User input placeholder replacement
`$FILE_PATH`	File path resolution (hook strings only)
`${CLAUDE_SKILL_DIR}`	Reference the skill's own directory
`! 'cmd'`	Dynamic bash execution context injection

Agent YAML Frontmatter

`permissionMode`	default / acceptEdits / plan / bypass
`isolation: worktree`	Run agent in isolated git worktree
`memory: user\|project`	Persistent memory storage scope
`background: true`	Run entirely as background task
`initialPrompt`	Auto-submit first turn on spawn
`SendMessage`	Auto-resumes stopped agents

Memory, Hooks & MCP

Rules & Auto-Memory

`.claude/rules/*.md`	Project specific structural rules
`~/.claude/rules/*.md`	User specific global rules
`paths:` (frontmatter)	Path-specific rule triggers
`@path/to/file`	Import file directly in CLAUDE.md
`.../memory/MEMORY.md`	Topic files, automatically loaded

Event Hooks

`PreToolUse` / `PostToolUse`	Intercept before/after tool execution
`SubagentStart` / `Stop`	Lifecycle triggers for agent spawning
`SessionEnd`	Run cleanup script when session closes
`CwdChanged` / `FileChanged`	React to directory or file changes
`TaskCreated`	Fires when task created via TaskCreate
`if:` (hook field)	Conditional execution (permission rule syntax)
`PermissionDenied`	Fires after auto mode classifier denials; return {retry:true} to allow retry
`"defer"` (PreToolUse)	Headless sessions pause at tool call; resume with -p --resume to re-evaluate

MCP Servers

`claude mcp list/add/remove`	Standard MCP server management
`claude mcp serve`	Run Claude Code as an MCP server
`--transport http/stdio/sse`	Protocol connection methods
`Elicitation`	Servers can request input mid-task
`_meta["anthropic/maxResultSizeChars"]`	Override max MCP result size per call (up to 500K chars)

Auth Commands

`claude auth login/logout`	Session authentication control
`claude auth status`	Check current authentication validity