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/LeeYudok/agents-scaffoldWrote 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/leeyudok/agents-scaffold/sdlc-cycle)<a href="https://agentmods.dev/commands/leeyudok/agents-scaffold/sdlc-cycle"><img src="https://agentmods.dev/badge/commands/leeyudok/agents-scaffold/sdlc-cycle.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 | $0.00041 | $0.00906 |
| Opus 5 | $0.00020 | $0.00453 |
| Sonnet 5 | $0.00008 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00091 |
Grade A, and why
sdlc-cycle 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 6d 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.
What it actually says
SDLC 한 사이클
$ARGUMENTS 로 이슈번호 또는 기획서 경로를 받아, 이슈 → 개발 → 테스트 → 검증 → PR/MR 한 사이클을 돈다.
각 단계는 게이트: 실패하면 멈추거나 앞 단계로 되돌린다.
옵션: --no-mr(PR/MR 생략), --no-issue(이슈 생성 생략).
시작 전 체크: 인자가 파일경로면 Read로 읽는다. 없으면 중단 + 경로 요청. 글로벌 규칙 준수: 이슈-우선, 커밋 직전 브랜치 재확인, 이슈 클로즈 규약(
.claude/rules/forge.md). forge 별 구체 명령(gh/glab)은 forge 프리셋이 이 파일을 덮어쓴다.
Phase 0 — 인입 & 이슈
- 이슈번호면 forge CLI 로 내용 파악(GitHub
gh issue view $N/ GitLabglab issue view $N). 기획서면 Read. - (
--no-issue아니면) 이슈 생성 (forge CLI —gh issue create/glab issue create). → 이슈번호 N 확보. - 브랜치 생성 (현재 main이면):
git checkout -b feature/issue-N-<slug>
Phase 1 — 개발 → 서브에이전트 sdlc-developer
이슈/기획서 내용을 주고 최소 스코프 구현 위임. 산출물(변경 파일 목록·충족 요구사항·미구현 항목) 수령.
Phase 2 — 테스트 → 서브에이전트 sdlc-tester
AC/TC 기준 테스트 코드 작성 위임. 실행 X — 작성까지.
Phase 3 — 검증 → 서브에이전트 sdlc-verifier
빌드+테스트 파이프라인 실행 + 결과 보고.
- PASS: Phase 4 로
- FAIL: 실패 단계·원인 가설 수령 → Phase 1(또는 2)로 되돌려 수정 + 재검증. 최대 2회 재시도. 2회 후 실패 → 정지 + Phase 4 실패 보고.
Phase 4 — PR/MR (--no-mr 면 생략)
# 커밋 직전 브랜치 재확인
git branch --show-current
git add -p # 또는 git add <files>
git commit -m "feat(#N): <기능명>"
git push -u origin feature/issue-N-<slug>
# forge CLI 로 PR/MR 생성 (본문에 Closes #N) — 구체 명령은 .claude/rules/forge.md 참조
# GitHub: gh pr create --fill --body "Closes #N"
# GitLab: glab mr create -t "feat(#N): <기능명>" -d "Closes #N" --fill -y
Phase 5 — 보고
| 항목 | 값 |
|---|---|
| 이슈 | #N |
| 브랜치 | feature/N-slug |
| 변경 파일 | n개 |
| 검증 | lint/build/test PASS·FAIL, 통과 수, 재시도 횟수 |
| PR/MR | URL 또는 생략 사유 |
다음 액션(머지·추가 수정·배포)을 제안.
단계별 단독 실행
- 개발만:
Agent sdlc-developer에 이슈 내용 전달 - 테스트만:
Agent sdlc-tester - 검증만:
Agent sdlc-verifier
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.
- 6d ago First seen · 75 lines · 41 tokens per session scan A 002c219fc8d7
sdlc-cycle is a command published in the GitHub repository LeeYudok/agents-scaffold (25 stars, last pushed 8d ago), licensed MIT. It adds 41 tokens to every session and 906 once invoked, about $0.0002 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
release-update
(dev-only) release-update maintainer harness — Claude Code upstream change tracker (release-notes version-delta sweep + docs sync). NOT distributed to user projects.
github
(dev-only) github maintainer harness — GitHub issue-fix and PR-review via gh CLI. NOT distributed to user projects.
release
(dev-only) release maintainer harness — MoAI-ADK production release (Enhanced GitHub Flow, scripts/release.sh + GoReleaser). NOT distributed to user projects.
sync
Synchronize documentation, codemaps, and create pull request.
gate
Run lint+format+type-check+test in parallel (pre-commit quality gate).
release
Release guide version (CHANGELOG + VERSION + README + landing sync + commit + push).