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/plan-tasknpx skills add This-HW/claude-code-kit --skill plan-taskgit 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 | $0.00029 | $0.01868 |
| Opus 5 | $0.00015 | $0.00934 |
| Sonnet 5 | $0.00006 | $0.00374 |
| Haiku 4.5 | $0.00003 | $0.00187 |
Grade A, and why
plan-task scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan-Task 스킬
사용법
/plan-task W-001 # 기존 Work ID로 재개
/plan-task 로그인 기능 추가 # 새 요청 (Work 자동 생성)
/plan-task fix the auth bug # 새 요청 (description 형식)
Phase Gate
이 스킬은 brainstorming 이후에 실행되어야 합니다.
docs/specs/에 관련 스펙 파일이 없으면:
- 새 기능이라면 → 먼저
brainstorming스킬을 invoke하세요 - 버그 수정/소규모 작업이라면 → 계속 진행 가능 (단, 이 사실을 명시)
Work 파일과 Task 시스템을 통합하여 구조화된 Planning을 진행합니다.
Step 0: Work ID 확보 [건너뛰기 금지]
체크리스트 초기화 [최우선]
Step 0 진입 즉시, Work ID 확보 전에 스킬 자체 진행을 추적할 Tasks를 생성합니다:
ToolSearch("select:TaskCreate,TaskUpdate,TaskList")실행
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.
- 다음 Tasks 생성 (이미
[Planning]Task 있으면 스킵):
TaskCreate: [Planning] Work ID 확보 및 초기화
TaskCreate: [Planning] 요구사항 명확화
TaskCreate: [Planning] 구현 계획 수립
TaskCreate: [Planning] Planning 완료 처리
의존성 설정: 각 Task는 이전 Task가 완료되어야 시작 가능 (addBlockedBy).
Work ID가 제공된 경우 (예: /plan-task W-043)
docs/works/idea/디렉토리에서 해당 Work 폴더 탐색W-XXX-{slug}/W-XXX-{slug}.md파일 읽기progress.md로 현재 진행 상황 확인 — 중단된 지점부터 재개- frontmatter
status,current_phase확인
Work ID가 없는 경우 (새 요청)
docs/works/ 폴더가 존재하면:
work.sh new로 Work 파일 생성:
→./scripts/work.sh new "<요청 제목>"docs/works/idea/W-XXX-{slug}/폴더와 파일 자동 생성 → 출력된 Work ID(예: W-001)를 이후 단계에서 사용
docs/works/ 폴더 자체가 없으면 → Fallback으로 이동
Work ID 확보 완료 후에만 Step 1로 진행.
Step 1: Task 시스템 초기화 [건너뛰기 금지]
-
ToolSearch("select:TaskCreate,TaskUpdate,TaskList")— 스키마 fetch (deferred tool이므로 필수) -
TaskList실행 → 이미 생성된 동일 Work Task 있으면 이 Step 스킵 (중복 방지) -
Task 없으면 아래 두 Tasks 생성:
T1: [W-XXX][Planning] 요구사항 명확화 T2: [W-XXX][Planning] 구현 계획 수립 ← blockedBy T1TaskCreate 시 모든 Task에 metadata 포함:
{ "work_id": "W-XXX", "phase": "planning" }T2 생성 직후
TaskUpdate(T2, addBlockedBy=[T1])설정.
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 · 202 lines · 29 tokens per session scan A dcfe47b4e9c8
plan-task is a skill published in the GitHub repository This-HW/claude-code-kit (4 stars, last pushed 4d ago), licensed MIT. It adds 29 tokens to every session and 1,868 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. 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.