메뉴
Programmatic/headless Claude Code usage — CLI flags, stream-json protocol, Agent SDKs, session management. Use before spawning Claude as a subprocess, testing skill or agent behavior, running "claude -p", or building with the Agent SDK.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Send peer-to-peer message and control to Claude Code sessions. Use when coordinating multiple simultaneous Claude sessions, or user says "dm another claude", "list claude sessions", "peek peer claude", "spawn claude in tmux", "monitor remote claude", "notify peer in tmux", "send to peer", "handover to claude", "inspect peer transcript", "orchestrate claude sessions".
Lark/Feishu (飞书) CLI tool. Use when the user asks to do anything on Lark/Feishu — send or read chat messages (IM), read or edit docs/sheets/slides/wiki, work with multi-dimensional tables (Base/bitable), manage calendar/meetings/video-conference, mail, contacts, tasks, approvals, OKR, drive files, minutes, whiteboards, or attendance. Triggers: "lark", "feishu", "send a feishu message", "peek lark group messages", "conclude last lark meeting".
Extract clean, complete markdown from any web page — articles, docs, READMEs, blog/social posts, academic papers. Also use as a fallback when curl returns noisy HTML or WebFetch returns truncated, summarized, or refused results.
Claude has no native audio or video understanding — this skill delegates that to Google Gemini 3.1 Flash Lite (cheap multimodal) on the ofox gateway. Use when the user asks to analyze / transcribe / describe / understand a sound, song, voice memo, or video, or asks what is said, sung, shown, or played in a media file. Triggers: "analyze this audio", "transcribe the song/speech", "what does this voice say", "describe/understand this video/mp4/clip", "what's the music/story in this MV", "listen to", "watch this".
Run long-running tasks under babysit — supervised background runner with cgroup-enforced memory/CPU caps and observability-stall kill. Use BEFORE any long-running task (>2 min), compute-intensive jobs (e.g. builds/benchmarks/renders/training), background work, or when the user says "run in background", "use babysit". This skill defines guardrails and the mandatory workflow, not just a how-to.
Audit agent-facing documentation (CLAUDE.md, SKILL.md, AGENTS.md, prompt markdown, agent reference doc, memory pages) for over-description and propose trims. Use proactively after writing or editing any agent-facing doc, or when the user says "trim this doc", "audit doc bloat", "this is over-explained".
| name | claude-headless |
| description | Programmatic/headless Claude Code usage — CLI flags, stream-json protocol, Agent SDKs, session management. Use before spawning Claude as a subprocess, testing skill or agent behavior, running "claude -p", or building with the Agent SDK. |
Programmatic usage of Claude Code CLI. Three modes available:
One-shot — single prompt, get result, exit:
claude -p "Explain this error" --output-format json
Stream JSON — bidirectional real-time NDJSON over stdin/stdout:
claude -p --output-format stream-json --input-format stream-json --verbose
# Send: {"type":"user","message":{"role":"user","content":"hello"}}
# Recv: {"type":"assistant","message":{...}}
# Recv: {"type":"result","subtype":"success",...}
Resume — continue a previous session:
claude -p "continue the review" --resume <session-id> --output-format json
| Flag | Purpose |
|---|---|
-p / --print | Non-interactive mode |
--output-format stream-json | NDJSON event stream on stdout |
--input-format stream-json | NDJSON messages on stdin (multi-turn) |
--bare | Skip CLAUDE.md, hooks, skills, plugins, MCP, auto-memory, OAuth/keychain (fast CI; see auth.md) |
--allowedTools "Bash,Read" | Pre-approve specific tools |
--max-budget-usd N | Cost cap |
--json-schema '{...}' | Structured output extraction |
For complete flag reference, read references/cli-flags.md.
Load these on demand based on what the user needs:
references/cli-flags.md — Complete CLI flags: headless, permissions, budget, session, system prompt, subcommandsreferences/auth.md — Authentication: subscription OAuth, API key, apiKeyHelper, --bare caveat, token storagereferences/env-vars.md — Complete environment variables: auth, models, thinking, bash/network timeouts, telemetry, TLS, session, plugins, MCP, detectionreferences/stream-json.md — Stream JSON protocol: stdout events, stdin messages, pipe-chainingreferences/agent-view.md — Background sessions & claude agents: --bg, supervisor, shell management commands, peek/attach, worktree isolation, vs claude-dmreferences/permissions.md — Headless permission modes, --allowedTools, --permission-prompt-tool MCPreferences/sdks.md — TypeScript and Python Agent SDKs: API, options, streaming, multi-turnreferences/patterns.md — Real-world patterns: CI/CD, bot bridges, structured extraction, Agent Teams headless