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.
git clone --depth 1 https://github.com/sangrokjung/claude-forgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/sangrokjung/claude-forge/web-checklist)<a href="https://agentmods.dev/commands/sangrokjung/claude-forge/web-checklist"><img src="https://agentmods.dev/badge/commands/sangrokjung/claude-forge/web-checklist.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00016 | $0.02163 |
| Opus 5 | $0.00008 | $0.01081 |
| Sonnet 5 | $0.00003 | $0.00433 |
| Haiku 4.5 | $0.00002 | $0.00216 |
Grade A, and why
web-checklist 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 8d ago.
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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task
0단계: 컨텍스트 수집
git log --oneline -3
git diff HEAD~1 --name-only
git diff HEAD~1 --stat
git branch --show-current
다음 파일 읽기 (있는 것만):
.claude/handoff.md- 개발 의도, 테스트 필요 사항spec.md- 기능 요구사항prompt_plan.md- Task 상세.claude/web-checklist-state.json- 기존 체크리스트 상태
0.5단계: 플래그 분기
--status 플래그 → 상태 조회 모드:
.claude/web-checklist-state.json 읽기:
파일 있으면:
════════════════════════════════════════════════════════════════
📋 Web Checklist Status (v6)
════════════════════════════════════════════════════════════════
📅 생성: [created timestamp]
📌 커밋: [commit hash]
🌿 브랜치: [branch name]
진행률: [completion]% ([done]/[total])
## 미완료 항목
- [ ] [ID: N] [category] [text]
- [ ] [ID: N] [category] [text]
...
## 완료 항목
- [x] [ID: N] [category] [text]
- [x] [ID: N] [category] [text]
...
완료 처리: /web-checklist --complete [ID]
════════════════════════════════════════════════════════════════
→ 종료
파일 없으면:
ℹ️ 저장된 체크리스트가 없습니다.
생성: /web-checklist --save
→ 종료
--complete ID 플래그 → 항목 완료 모드:
.claude/web-checklist-state.json 읽기:
해당 ID 찾으면:
items[ID].done→true로 변경completion재계산- 파일 저장
✅ 체크리스트 항목 완료
[ID]: [text] → ✅ Done
진행률: [new completion]% ([done]/[total])
남은 항목: [remaining count]개
전체 완료 시: /sync-docs
→ 종료
해당 ID 없으면:
❌ ID [N]을 찾을 수 없습니다.
유효한 ID: [사용 가능한 ID 목록]
상태 확인: /web-checklist --status
→ 종료
1단계: 변경 영역 분석
변경된 파일 카테고리별 분류:
| 카테고리 | 파일 패턴 | 테스트 영역 |
|---|---|---|
| UI/화면 | *.tsx, *.jsx, components/* |
화면 표시, 반응형, 인터랙션 |
| API/서버 | api/*, server/*, *.ts |
엔드포인트, 응답 |
| 인증 | auth/*, login/*, session/* |
로그인, 로그아웃, 권한 |
| 결제 | payment/*, billing/* |
결제 플로우, 금액 |
| 데이터 | *.sql, supabase/*, db/* |
데이터 정합성 |
| 스타일 | *.css, *.scss, tailwind.* |
레이아웃, 디자인 |
2단계: 테스트 체크리스트 생성
handoff.md의 "테스트 필요 사항" 참조해서 구체화.
UI 변경 시:
- 화면이 정상적으로 렌더링되는지
- 반응형 (모바일/태블릿/데스크톱) 확인
- 로딩 상태 표시 확인
- 에러 상태 표시 확인
- 빈 상태(empty state) 표시 확인
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.
- 8d ago First seen · 294 lines · 16 tokens per session scan A 9f1ae2221bf5
web-checklist is a command published in the GitHub repository sangrokjung/claude-forge (825 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 2,163 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 2026-08-30.
Other commands, from other repositories
test-suite
Run comprehensive test suite with coverage analysis.
create-smoke-test.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
ui-test.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
ui-smoke.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
testing
Comprehensive testing through distributed execution.