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/debugnpx skills add This-HW/claude-code-kit --skill debuggit 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 | $0.00024 | $0.00912 |
| Opus 5 | $0.00012 | $0.00456 |
| Sonnet 5 | $0.00005 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
debug 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
디버깅 실행
4-Phase Debugging (Superpowers 패턴) Reproduce → Isolate → Fix → Verify
즉시 실행하세요. 설명하지 말고 바로 실행합니다.
에러 정보: $ARGUMENTS
파이프라인 구조
┌──────────────┐ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐
│ Phase 1 │ → │ Phase 2 │ → │ Phase 3 │ → │ Phase 4 │
│ Reproduce │ │ Isolate │ │ Fix │ │ Verify │
│ (재현) │ │ (격리) │ │ (수정) │ │ (검증) │
└──────────────┘ └──────────────┘ └──────────────┘ └──────────────┘
│ │ │ │
└──── diagnose ──────┘ fix-bugs ─┘ verify-code ┘
(opus) (sonnet) (haiku)
Phase 1-2: 재현 및 격리 (Reproduce + Isolate)
Task tool 사용:
subagent_type: diagnose
model: opus
prompt: |
다음 에러를 진단해주세요:
$ARGUMENTS
### Phase 1: Reproduce (재현)
- 에러를 재현하는 최소 단계 식별
- 재현 조건 및 환경 확인
- 에러 발생 빈도 (항상/간헐적)
### Phase 2: Isolate (격리)
- 에러 유형 (문법/타입/런타임/빌드/외부API)
- 파일 위치 및 라인 번호
- 스택 트레이스 분석
- 루트 원인 파악
- 영향 범위 (단일 함수/모듈/시스템 전체)
### 수정 방안 제안
- 옵션 A: [빠른 수정]
- 옵션 B: [근본 해결]
Phase 3: 수정 (Fix)
Task tool 사용:
subagent_type: fix-bugs
model: sonnet
prompt: |
[diagnose 결과 포함]
진단 결과를 바탕으로 버그를 수정해주세요.
수정 원칙:
- 최소 변경 원칙
- exc_info=True 포함 (Python 로깅)
- 에러 핸들링 추가 (필요시)
- 같은 패턴의 버그가 다른 곳에 없는지 확인
Phase 4: 검증 (Verify)
Task tool 사용:
subagent_type: verify-code
model: haiku
prompt: |
수정된 코드를 검증해주세요:
[변경된 파일 목록]
검증 항목:
1. 에러 재현 → 해결 확인
2. 빌드/컴파일 성공
3. 타입 체크 통과
4. 관련 테스트 통과
5. 엣지 케이스 확인
출력 형식
Phase 1-2: 재현 및 격리
| 항목 | 내용 |
|---|---|
| 유형 | [타입/런타임/빌드/외부API] |
| 위치 | [파일:라인] |
| 재현 조건 | [최소 재현 단계] |
| 루트 원인 | [원인 설명] |
| 영향 범위 | [함수/모듈/시스템] |
Phase 3: 수정
[변경사항 diff 또는 설명]
Phase 4: 검증
[테스트/빌드 통과 여부]
예방 권장
[재발 방지를 위한 제안]
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 · 130 lines · 24 tokens per session scan A 34fbb7f9c294
debug is a skill published in the GitHub repository This-HW/claude-code-kit (4 stars, last pushed 4d ago), licensed MIT. It adds 24 tokens to every session and 912 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.