Skip to content

parcadei/Continuous-Claude-v3 / .claude/skills/cli-reference

cli-reference

Unverified

Claude Code CLI commands, flags, headless mode, and automation patterns

CLI Reference

Complete reference for Claude Code command-line interface.

When to Use

  • "What CLI flags are available?"
  • "How do I use headless mode?"
  • "Claude in automation/CI/CD"
  • "Output format options"
  • "System prompt via CLI"
  • "How do I spawn agents properly?"

Core Commands

CommandDescriptionExample
claudeStart interactive REPLclaude
claude "query"REPL with initial promptclaude "explain this project"
claude -p "query"Headless mode (SDK)claude -p "explain function"
cat file | claude -pProcess piped contentcat logs.txt | claude -p "explain"
claude -cContinue most recentclaude -c
claude -c -p "query"Continue via SDKclaude -c -p "check types"
claude -r "id" "query"Resume sessionclaude -r "auth" "finish PR"
claude updateUpdate versionclaude update
claude mcpConfigure MCP serversSee MCP docs

Session Control

FlagDescriptionExample
--continue, -cLoad most recent conversationclaude --continue
--resume, -rResume session by ID/nameclaude --resume auth-refactor
--session-idUse specific UUIDclaude --session-id "550e8400-..."
--fork-sessionCreate new session on resumeclaude --resume abc --fork-session

Headless Mode (Critical for Agents)

FlagDescriptionExample
--print, -pNon-interactive, exit afterclaude -p "query"
--output-formattext, json, stream-jsonclaude -p --output-format json
--max-turnsLimit agentic turnsclaude -p --max-turns 100 "query"
--verboseFull turn-by-turn outputclaude --verbose
--dangerously-skip-permissionsSkip permission promptsclaude -p --dangerously-skip-permissions
--include-partial-messagesInclude streaming eventsclaude -p --output-format stream-json --include-partial-messages
--input-formatInput format (text/stream-json)claude -p --input-format stream-json

Tool Control

FlagDescriptionExample
--allowedToolsAuto-approve these tools"Bash(git log:*)" "Read"
--disallowedToolsBlock these tools"Bash(rm:*)" "Edit"
--toolsOnly allow these tools--tools "Bash,Edit,Read"

Subagent Definition (--agents flag)

Define custom subagents inline via JSON:

claude --agents '{
  "code-reviewer": {
    "description": "Expert code reviewer. Use proactively after code changes.",
    "prompt": "You are a senior code reviewer. Focus on code quality and security.",
    "tools": ["Read", "Grep", "Glob", "Bash"],
    "model": "sonnet"
  },
  "debugger": {
    "description": "Debugging specialist for errors and test failures.",
    "prompt": "You are an expert debugger. Analyze errors and provide fixes."
  }
}'

Agent Fields

FieldRequiredDescription
descriptionYesWhen to invoke this agent
promptYesSystem prompt for behavior
toolsNoAllowed tools (inherits all if omitted)
modelNosonnet, haiku, or claude-opus-4-5-20251101

Key Insight

When Lead uses Task tool, it auto-spawns from these definitions. No manual spawn needed.

System Prompt Customization

FlagBehaviorModes
--system-promptReplace entire promptInteractive + Print
--system-prompt-fileReplace from filePrint only
--append-system-promptAppend to default (recommended)Interactive + Print

Use --append-system-prompt for most cases - preserves Claude Code capabilities.

Model Selection

FlagDescriptionExample
--modelSet model for session--model claude-sonnet-4-5
--fallback-modelFallback if default overloaded--fallback-model sonnet

Aliases: sonnet, opus, haiku

MCP Configuration

FlagDescriptionExample
--mcp-configLoad MCP servers from JSON--mcp-config ./mcp.json
--strict-mcp-configOnly use these MCP servers--strict-mcp-config --mcp-config ./mcp.json

Advanced Flags

FlagDescriptionExample
--add-dirAdd working directories--add-dir ../apps ../lib
--agentSpecify agent for session--agent my-custom-agent
--permission-modeStart in permission mode--permission-mode plan
--permission-prompt-toolMCP tool for permissions--permission-prompt-tool mcp_auth
--plugin-dirLoad plugins from directory--plugin-dir ./my-plugins
--settingsLoad settings from file/JSON--settings ./settings.json
--setting-sourcesWhich settings to load--setting-sources user,project
--betasBeta API headers--betas interleaved-thinking
--debugEnable debug mode--debug "api,hooks"
--ideAuto-connect to IDE--ide
--chromeEnable Chrome integration--chrome
--no-chromeDisable Chrome for session--no-chrome
--enable-lsp-loggingVerbose LSP debugging--enable-lsp-logging
--version, -vOutput versionclaude -v

Output Formats

JSON (for parsing)

claude -p "query" --output-format json
# {"result": "...", "session_id": "...", "usage": {...}}

Streaming (for real-time monitoring)

claude -p "query" --output-format stream-json
# Newline-delimited JSON events

Structured Output (schema validation)

claude -p "Extract data" \
  --output-format json \
  --json-schema '{"type":"object","properties":{...}}'

Headless Agent Pattern (CRITICAL)

Proper headless agent spawn:

claude -p "$TASK_PROMPT" \
  --session-id "$UUID" \
  --dangerously-skip-permissions \
  --max-turns 100 \
  --output-format stream-json \
  --agents '{...}' \
  --append-system-prompt "Context: ..."

Missing any of these causes hangs:

  • --session-id - Track the session
  • --dangerously-skip-permissions - Headless requires this
  • --max-turns - Prevents infinite loops

Common Patterns

CI/CD Automation

claude -p "Run tests and fix failures" \
  --dangerously-skip-permissions \
  --max-turns 50 \
  --output-format json | jq '.result'

Piped Input

cat error.log | claude -p "Find root cause"
gh pr diff | claude -p "Review for security"

Multi-turn Session

id=$(claude -p "Start task" --output-format json | jq -r '.session_id')
claude -p "Continue" --resume "$id"

Stream Monitoring

claude -p "Long task" \
  --output-format stream-json \
  --include-partial-messages | while read -r line; do
    echo "$line" | jq '.type'
done

Keyboard Shortcuts (Interactive)

ShortcutAction
Ctrl+CCancel current
Ctrl+DExit
Ctrl+RReverse search history
Esc EscRewind changes
Shift+TabToggle permission mode

Quick Commands

PrefixAction
/Slash command
!Bash mode
#Add to memory
@File mention
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
discernment-nudgeanthropics/skillsAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.Stars: 195kUpdated Claude CodeCodexVerifiedInstall
internal-commsanthropics/skillsA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).Stars: 195kUpdated Claude CodeCodexVerifiedInstall