Code with Claude#

Use this skill when the user asks about Claude Code CLI features, configuration, workflows, or best practices.

Claude Code Feature Map#

FeatureWhat It DoesReferenceCLI flagsLaunch-time options for sessions, models, permissions, prompts./references/cli-reference.mdCommandsIn-session / commands for model switching, permissions, context, workflows./references/commands.mdInteractive modeKeyboard shortcuts, Vim mode, multiline input, voice, task list./references/interactive-mode.mdHooksShell commands, HTTP endpoints, or LLM prompts at lifecycle events./references/hooks.mdPluginsExtend Claude Code with skills, agents, hooks, MCP/LSP servers./references/plugins.mdChannelsMCP servers that push external events into a session./references/channels.mdCheckpointingAutomatic file edit tracking with rewind and summarize./references/checkpointing.mdToolsBuilt-in tools: Bash, Edit, Read, Write, Agent, WebFetch, etc../references/tools.mdEnvironment variablesControl behavior via env vars or settings.json``./references/env-vars.md

Quick Reference: Essential CLI Flags#

FlagPurposeExample--modelSet model (alias or full name)claude --model opus``--continue, -cResume most recent conversationclaude -c``--resume, -rResume by session ID or nameclaude -r "auth-refactor"``--print, -pNon-interactive print mode (SDK)claude -p "query"``--permission-modeStart in a specific permission modeclaude --permission-mode plan``--worktree, -wIsolated git worktree sessionclaude -w feature-auth``--bareMinimal mode, skip auto-discoveryclaude --bare -p "query"``--append-system-promptAdd to default system promptclaude --append-system-prompt "Use TS"``--effortSet effort level for sessionclaude --effort high

Quick Reference: Essential Commands#

CommandPurpose/model [model]Switch model mid-session/compact [instructions]Compact conversation, free context/clearClear conversation history/rewindRewind to a checkpoint (Esc+Esc)/permissionsManage tool allow/deny rules/plan [description]Enter plan mode/batch <instruction>Parallel large-scale changes/hooksView hook configurations/memoryEdit CLAUDE.md memory files/diffInteractive diff viewer/costShow token usage statistics/effort [level]Set effort (low/medium/high/max)

Quick Reference: Key Shortcuts#

ShortcutActionCtrl+CCancel current generationEsc+EscRewind / checkpoint menuShift+TabCycle permission modesCtrl+OToggle transcript viewerCtrl+BBackground running tasksCtrl+TToggle task listAlt+PSwitch modelAlt+TToggle extended thinking!commandRun bash directly in session@pathFile path autocomplete

Quick Reference: Permission Modes#

ModeBehaviordefaultAsk for each tool useacceptEditsAuto-approve file edits, ask for bashplanRead-only exploration, no writesautoAI classifier approves safe operationsbypassPermissionsSkip all permission prompts

Cycle modes with Shift+Tab. Start in a specific mode: claude --permission-mode plan.

Quick Reference: Core Tools#

ToolDescriptionPermissionBashExecute shell commandsYesReadRead file contentsNoEditTargeted file editsYesWriteCreate or overwrite filesYesAgentSpawn subagent with own contextNoGlobFind files by patternNoGrepSearch file contentsNoWebFetchFetch URL contentYesWebSearchWeb searchYesMonitorBackground watch + reactYes

Gotchas#

• Env vars don't persist across Bash tool commands. Use CLAUDE_ENV_FILE or a SessionStart hook.
• Checkpoints don't track bash changes — only direct file edits via Edit/Write tools are tracked.
• applyTo: "**" burns context — always-on instructions load on every interaction. Use specific globs.
• macOS Alt shortcuts require Option-as-Meta in your terminal (iTerm2: Profiles → Keys → "Esc+").
• --bare disables everything — hooks, skills, plugins, MCP, auto-memory, CLAUDE.md. Use for fast scripted calls.
• Hook if patterns use tool permission syntax: Bash(rm *) matches bash commands starting with rm.
• Plugin agents can't use hooks, mcpServers, or permissionMode frontmatter for security reasons.

When to Load References#

Load the appropriate reference when the user needs detailed information:

• CLI flags, system prompt customization, launch options → Read ./references/cli-reference.md
• In-session commands, slash commands, skills list → Read ./references/commands.md
• Keyboard shortcuts, Vim mode, multiline, voice, task list → Read ./references/interactive-mode.md
• Hooks lifecycle, events, matchers, configuration → Read ./references/hooks.md
• Plugins structure, manifest, MCP/LSP, distribution → Read ./references/plugins.md
• Channels, webhook receivers, two-way chat bridges → Read ./references/channels.md
• Checkpointing, rewind, restore, summarize → Read ./references/checkpointing.md
• Built-in tools, Bash behavior, LSP, Monitor, PowerShell → Read ./references/tools.md
• Environment variables, timeouts, model config, proxy → Read ./references/env-vars.md