Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/this-hw/claude-code-kit/auto-devnpx skills add This-HW/claude-code-kit --skill auto-devgit clone --depth 1 https://github.com/This-HW/claude-code-kitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00022 | $0.04598 |
| Opus 5 | $0.00011 | $0.02299 |
| Sonnet 5 | $0.00004 | $0.00920 |
| Haiku 4.5 | $0.00002 | $0.00460 |
Grade A, and why
auto-dev scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
root = subprocess.run(["git","rev-parse","--show-toplevel"], capture_output=True, How it starts
The opening of the file, as written. The whole thing — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Dev 스킬
Work 파일과 Task 시스템을 통합하여 Development → Validation 파이프라인을 자동 실행합니다.
Step 0: Work 컨텍스트 + Task 시스템 초기화 [건너뛰기 금지]
진입 확인 [건너뛰기 금지]
Work ID가 제공된 경우, planning-results.md 존재 여부 확인:
ls docs/works/active/W-XXX-*/planning-results.md 2>/dev/null \
|| ls docs/works/idea/W-XXX-*/planning-results.md 2>/dev/null
- 파일 있음 → 계속
- 파일 없음 → "planning-results.md를 찾을 수 없습니다.
/plan-task W-XXX를 먼저 실행하세요." 출력 후 중단
Work ID 없이 새 요청으로 진입한 경우 (/auto-dev 로그인 기능 추가 형식):
work.sh new로 Work 생성 후 → 즉시/plan-task W-XXX로 위임 (planning-results.md 없이 Step 1 진행 금지)- 이는
brainstorming → plan-task → auto-dev체인 준수를 위함
Fallback 모드(docs/works/ 폴더 자체가 없는 경우)에서는 이 확인을 스킵합니다.
Work ID가 제공된 경우 (예: /auto-dev W-042)
- Work 파일 위치 탐색:
docs/works/idea/또는docs/works/active/ W-XXX-{slug}/W-XXX-{slug}.md와planning-results.md읽기- frontmatter
status,current_phase,phases_completed확인
idea 상태면 자동 전환:
./scripts/work.sh start W-042
# idea/ → active/ 이동, status: active, started_at 기록
current_phase에 따른 시작 위치:
| current_phase | 시작 위치 |
|---|---|
planning |
Step 1부터 전체 |
development |
Step 2부터 재개 |
validation |
Step 3부터 재개 |
Work ID가 없는 경우 (예: /auto-dev 로그인 기능 추가)
docs/works/ 폴더 존재 여부 확인:
- 존재하면 →
work.sh new로 새 Work 생성 후 Step 1부터 진행:./scripts/work.sh new "<요청 제목>" - 없으면 → Step 4 fallback
Task 시스템 초기화 [건너뛰기 금지]
Work ID 확보 후 반드시 실행:
ToolSearch("select:TaskCreate,TaskUpdate,TaskList")— 스키마 fetch
Task 도구가 없으면 멈추지 말고 대체 경로로 간다 —
ToolSearch가 Task 계열을 반환하지 않는 호스트/세션이 있다(F-038). 그때는./scripts/checklist.sh기반 durable checklist로 추적한다. 규율 SSOT:skills/references/task-tools-fallback.md.
TaskList실행 → subject가[W-XXX]로 시작하는 Task 있으면 상태 확인 후 재개 (재생성 스킵, W-XXX는 현재 Work ID)- Task 없으면 → Step 1: Development Tasks 생성으로 이동
Step 1: Development Tasks 생성
planning-results.md의 구현 계획 항목 분석 + 소스코드 직접 탐색:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 388 lines · 22 tokens per session scan A e12eadc181ad
auto-dev is a skill published in the GitHub repository This-HW/claude-code-kit (4 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 4,598 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.