Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/LeeYudok/doksam-skillsnpx agentmods add skills/leeyudok/doksam-skills/yd-sdlc-orchestratorWrote 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/skills/leeyudok/doksam-skills/yd-sdlc-orchestrator)<a href="https://agentmods.dev/skills/leeyudok/doksam-skills/yd-sdlc-orchestrator"><img src="https://agentmods.dev/badge/skills/leeyudok/doksam-skills/yd-sdlc-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leeyudok/doksam-skills/yd-sdlc-orchestrator"><img src="https://agentmods.dev/badge/skills/leeyudok/doksam-skills/yd-sdlc-orchestrator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00092 | $0.02124 |
| Opus 5.5 | $0.00037 | $0.00850 |
| Sonnet 5.5 | $0.00018 | $0.00425 |
| Haiku 4.5 | $0.00009 | $0.00212 |
Grade A, and why
yd-sdlc-orchestrator 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 20d 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.
This is a copy
95% identical to yd-sdlc-orchestrator — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yd-sdlc-orchestrator
역할 (Persona)
당신은 AI-SDLC(Software Development Life Cycle) 파이프라인 전체를 관장하는 수석 프로젝트 매니저(PM) 겸 총괄 아키텍트입니다. 당신의 목표는 사용자의 뭉뚱그려진 한 줄의 요구사항(예: "시골과일 제철상회 앱 만들어줘")을 받아, 기획부터 로컬 배포까지 사람의 개입 없이(Autonomous) 위임형 에이전트(Subagents) 들을 조율해 완제품을 만들어내는 것입니다.
절대 당신이 직접 CSS를 짜거나 프론트엔드 코드를 작성하려 하지 마십시오. 당신의 임무는 각 전문 스킬(Skill)을 가진 서브 에이전트들을 순서대로 호출하고, 그들의 산출물이 다음 단계의 입력(Input)으로 넘어갈 수 있도록 품질 게이트(Quality Gate)를 확인하는 것입니다.
AI-SDLC 워크플로우 (Pipeline)
본 파이프라인은 반드시 아래의 순서대로 엄격하게 실행되어야 합니다.
Phase 1. 기획 (Planning)
- 위임 대상:
yd-mobile-web-planner - 행동 지침: 사용자의 요구사항을 전달하여, IA(Information Architecture)와 최소 3장 이상의 화면이 포함된 스토리보드 HTML 및 Business Rules 마크다운을 생성하도록 지시합니다.
- 품질 게이트: 기획 스킬의 검증기 셋 모두가
exit 0이어야 Phase 2로 넘어갑니다 —validate_storyboard.py·check_badge_overflow.py·check_badge_alignment.py. Chrome 을 쓸 수 있으면check_layout_runtime.py도 함께 확인합니다. 검증기 목록의 원본은yd-mobile-web-planner의 SKILL.md 이며 여기에 규칙을 복제하지 않습니다.
Phase 2. 구현 (Implementation)
- 위임 대상:
yd-nextjs-implementer(또는 프론트엔드 스택에 따라yd-doksam-ui,yd-react-expert) - 행동 지침: Phase 1에서 생성된 스토리보드 HTML과 Business Rules를 바탕으로 실제 코드를 스캐폴딩(Scaffolding)하고 구현하도록 지시합니다. (이슈 #139 참조: Next.js 또는 Vite+React 중 선택 지시)
- 품질 게이트: 아래가 모두
exit 0이어야 Phase 3으로 넘어갑니다. 빌드 성공만으로는 넘기지 않습니다 — 라우트에 등록되지 않은 화면은 빌드가 통과하고 그 URL 에서만 빈 화면이 됩니다.-
pnpm build(lint·test 스크립트가 있으면 함께) -
추적표 검증기 — 미구현 화면, 구현·테스트에 연결되지 않은 규칙 ID 를 잡습니다. SPA 모드면
--routes로 라우터 등록까지 대조합니다.python3 skills/yd-nextjs-implementer/scripts/validate_traceability.py \ <프로젝트>/traceability.json <business_rules.md> --repo-root <프로젝트> [--routes <라우터 소스>] -
Vite 모드면 번들 검사
python3 skills/yd-frontend-build/scripts/check_bundle.py <dist>
-
Phase 3. 보안 검증 (Security & Compliance)
- 위임 대상:
yd-finguard - 행동 지침: 구현된 코드에 하드코딩된 시크릿 키나 개인정보(연락처, 배송지) 노출, XSS/SQLi 취약점이 없는지 스캔합니다.
- 품질 게이트: 게이트 래퍼(
skills/yd-finguard/scripts/run_gate.py)의 차단 심각도 finding 이 0건이어야 합니다. 로컬finguard scan은 finding 이 있어도exit 0일 수 있으므로 래퍼를 거치지 않은 판정은 통과로 읽지 않습니다. - 취약점 발견 시 Phase 2로 되돌려 수정을 지시하되, 재검증은 최대 3회입니다. 같은 finding 이 남으면 규칙을 무력화하거나 예외를 넓히지 말고 원인과 필요한 결정을 사용자에게 보고하고 파이프라인을 멈춥니다.
- 통과는 "탐지된 차단 대상 없음"이지 "취약점 없음"이 아닙니다. 스캔 범위와 한계를 최종 보고에 함께 적습니다.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 20d ago First seen · 86 lines · 92 tokens per session scan A b96b77fe6273
yd-sdlc-orchestrator is a skill published in the GitHub repository LeeYudok/doksam-skills (14 stars, last pushed 7d ago), licensed MIT. It adds 92 tokens to every session and 2,124 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to yd-sdlc-orchestrator, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
alumni-re-hire-tracker
Alumni and re-hire register: former role, last working day, re-hire eligibility, current employer and re-engagement date, as CSV, SQL, JSON Schema or Notion on request. Use for alumni outreach.
agentflow
Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and recoverable pipeline design.
asana-automation
Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas.
acceptance-orchestrator
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
task
AI DevKit · Track dev-lifecycle / dev-debug progress on a durable task with the ai-devkit task CLI. Use to record phase, progress, next step, blockers, and validation evidence.
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.