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 skills add LeeYudok/doksam-skills --skill yd-agents-yamlgit clone --depth 1 https://github.com/LeeYudok/doksam-skillsWrote 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-agents-yaml)<a href="https://agentmods.dev/skills/leeyudok/doksam-skills/yd-agents-yaml"><img src="https://agentmods.dev/badge/skills/leeyudok/doksam-skills/yd-agents-yaml/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-agents-yaml"><img src="https://agentmods.dev/badge/skills/leeyudok/doksam-skills/yd-agents-yaml.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 | $0.00129 | $0.01810 |
| Opus 5.5 | $0.00052 | $0.00724 |
| Sonnet 5.5 | $0.00026 | $0.00362 |
| Haiku 4.5 | $0.00013 | $0.00181 |
Grade A, and why
yd-agents-yaml 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 14d 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-agents-yaml — 2 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yd-agents-yaml
에이전트가 저장소를 파악하는 데 드는 탐색을 줄이려고, 저장소의 구조적 사실을
AGENTS.yaml 한 파일에 모은다. 사람이 읽는 규칙과 배경은 AGENTS.md 에 남기고,
AGENTS.yaml 은 구성요소 그래프·명령·시크릿 위치·정책 요약·알려진 함정처럼
파싱해서 쓰는 사실만 담는다. 검증기가 YAML 의 조용한 타입 변환과 부패한 경로를 잡는다.
| 파일 | 역할 |
|---|---|
AGENTS.md |
사람용 지침(SoT). 맨 위에 AGENTS.yaml 안내 한 단락 |
AGENTS.yaml |
기계 판독용 사실. 서술이 충돌하면 AGENTS.md 와 실제 코드가 이긴다 |
scripts/check-agents-yaml.sh |
이 스킬의 scripts/ 에서 수정 없이 복사 |
언제 쓰나
- AGENTS.yaml 이 없는 저장소에서 작업을 시작할 때 — 그 저장소 작업의 첫 chore 이슈로 세팅한다
- 구성요소·포트·경로·명령·환경변수가 바뀐 MR — 같은 MR 에서 AGENTS.yaml 도 고치고 검증기를 돌린다
- AGENTS.yaml 과 실제가 어긋난 걸 발견했을 때 — 실제(코드·파일시스템)를 확인해 둘 다 고친다
세팅 절차
- 조사 — 아래를 실제로 확인한다. 추측으로 채우지 않는다.
- 진입점·패키지 구조 (
ls, 모듈 파일, 서브커맨드 분기) - 코드가 읽는 환경변수 이름:
grep -rhoE 'Getenv\("[A-Z0-9_]+"' --include='*.go'/os.environ/process.env등 - 배포 단위(컨테이너·유닛·타이머·CI job)와 그 EnvironmentFile 경로
- 외부 의존(DB·LLM·API·소켓)과 어느 코드가 부르는지
- 시크릿 파일의 키 이름만:
grep -oE '^[A-Z_]+=' <file>— 값이 출력되는 명령(cat,env,inspect)은 쓰지 않는다 - 기존 메모리·README 의 함정(known issues)
- 진입점·패키지 구조 (
- AGENTS.yaml 작성 —
assets/AGENTS.yaml뼈대에서 시작한다. 섹션 규칙은 아래. - 검증기 설치 —
cp <skill>/scripts/check-agents-yaml.sh <repo>/scripts/ && chmod +x. 저장소에 맞게 고치지 않는다(아래 "확장"). - AGENTS.md 연결 — 맨 위에 다음 단락을 넣는다.
기계 판독용 정보는
AGENTS.yaml— 구성요소 그래프(nodes/edges),commands,secret_files(경로·키 이름만),policies,known_issues등. 작업 전 이 파일을 먼저 읽고, 구성요소·경로·명령·환경변수가 바뀌면 이 문서와 함께 갱신한다. 두 파일이 어긋나면 실제 코드·파일시스템을 확인해 둘 다 고친다. 고친 뒤엔scripts/check-agents-yaml.sh로 검증한다. 날짜·버전 값은 항상 따옴표로 감싼다. - 검증 —
scripts/check-agents-yaml.sh가[OK]인지, 그리고 일부러 망가뜨린 사본(따옴표 뺀 날짜, 없는 노드로 가는 엣지, 없는 경로)을 잡는지 한 번 확인한다. - 이슈 → 브랜치 → MR 로 올린다.
AGENTS.yaml, 검증기,AGENTS.md를 한 MR 에.
섹션 규칙
| 섹션 | 필수 | 내용 |
|---|---|---|
schema_version |
O | '1.0' (따옴표) |
meta |
O | 이름·설명·저장소/이슈 URL·브랜치 전략·updated: 'YYYY-MM-DD' |
nodes |
O | 구성요소. id(유일)·type·label·path(저장소 상대). 외부 의존도 노드로 둔다 |
edges |
O | {from, to, rel} + 해당 연결이 읽는 env: [키 이름] |
environments |
local / prod / ci 실행 환경 | |
ports |
{port: 정수, service, scope} |
|
commands |
그룹별 실행 명령. 첫 토큰이 저장소 파일이면 검증기가 존재를 확인한다 | |
secret_files |
{host, path, keys: [이름만], used_by}. 값은 절대 넣지 않는다 |
|
env_keys |
컴포넌트별 코드가 읽는 환경변수 이름 | |
policies |
{id, rule: 한 줄, source: 상세 문서 경로} — 상세는 source 가 SoT |
|
known_issues |
{id, summary, source, files} — 한 번 밟은 함정 |
|
docs |
문서 포인터 | |
x-* |
저장소 고유 섹션 (예: x-deliverables, x-catalog) |
What ships with it
4 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.
- 14d ago Changed 72fad8b25f50
- 20d ago First seen · 79 lines · 129 tokens per session scan A d04521e6f11d
yd-agents-yaml is a skill published in the GitHub repository LeeYudok/doksam-skills (14 stars, last pushed 7d ago), licensed MIT. It adds 129 tokens to every session and 1,810 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to yd-agents-yaml, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
apify-competitor-intelligence
Analyze competitor strategies, content, pricing, ads, and market positioning across Google Maps, Booking.com, Facebook, Instagram, YouTube, and TikTok.
autonomous-agent-patterns
Design patterns for building autonomous coding agents, inspired by Cline and OpenAI Codex.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".
deployment-engineer
Expert deployment engineer specializing in modern CI/CD pipelines, GitOps workflows, and advanced deployment automation. Masters GitHub Actions, ArgoCD/Flux, progressive delivery, container security, and platform engineering. Handles zero-downtime deployments, security scanning, and developer experience optimization.…
haskell-pro
Expert Haskell engineer specializing in advanced type systems, pure functional design, and high-reliability software. Use PROACTIVELY for type-level programming, concurrency, and architecture guidance.