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 instructions/sungjunlee/beopsuny-skill/claude-mdgit clone --depth 1 https://github.com/sungjunlee/beopsuny-skillWrote 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/instructions/sungjunlee/beopsuny-skill/claude-md)<a href="https://agentmods.dev/instructions/sungjunlee/beopsuny-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/sungjunlee/beopsuny-skill/claude-md.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 | $0.00753 | $0.00753 |
| Opus 5 | $0.00377 | $0.00377 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
beopsuny-skill CLAUDE.md 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 5d 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
beopsuny-skill
한국 법무 실무를 위한 Claude Code skill. 이 파일은 에이전트 온보딩용 포인터 문서다 — 내용 사본을 두지 않는다 (사본은 drift 검사 없이 썩는다).
단일 소스 지도
| 무엇 | 단일 소스 |
|---|---|
| 스킬 본체 — 의도 라우터, always-on gate, 안전 경계, 소스 가용성·degradation, 법률 원칙(정확 인용·공식 링크·시행일·환각 방지) | skills/beopsuny/SKILL.md |
| 워크플로우·계약 상세 (소스 접근, 조사, 계약 검토, 출력, 메모리 등) | skills/beopsuny/references/*.md (SKILL.md 라우터가 로딩 지점) |
| 데이터 소스 우선순위, source family, 초기화 절차 | skills/beopsuny/references/source-access.md |
| 사용자 안내, 설치, 자산 인벤토리, 품질 계약 지도, 변경·릴리즈 체크리스트 | README.md |
| 제품 방향, Non-Goals, Objectives, 전역 Decisions | spec/charter.md |
| 시스템 경계와 소유권 | spec/system-map.md |
| capability 계약 (6종) | spec/capabilities.md |
| 구조 결정 아카이브 (단일 스킬 vs split, 전환 트리거) | DESIGN.md |
| 무엇을 왜 했는지 (실행 단위 사실, 완료 근거, 리뷰) | GitHub Issues / PRs |
| 어떻게 했는지 (실행 기록, 결정 경위, 재발견 방지) | backlog/sprints/ + backlog/sprints/_context.md |
| 무엇이 바뀌었는지 (릴리즈 노트) | CHANGELOG.md |
작업 규칙
- 문서 문구를 고치기 전에
tests/validate_skill_contracts.py에서 해당 문구를 grep한다 — 다수의 check가 문서 문자열에 결합되어 있다. check를 고칠 때는 전문 문장 재고정 대신 토큰·구조 검사로 옮긴다. - 하나의 계약 개념은 집이 1곳이다. 다른 문서에는 재요약 대신 포인터만 둔다.
- 히스토리도 집이 1곳이다. 같은 사건을 여러 표면에 서술하지 않는다 — 위 지도의 3행(GitHub / sprint / CHANGELOG)이 각각 다른 질문에 답한다. CHANGELOG 항목은 사용자 관점에서 무엇이 바뀌었고 왜 그게 중요한지를 쓰고, 설계 경위·시행착오·mutation 표는 sprint 파일이나 PR로 위임한다. 항목이 길어지면 대개 sprint에 있어야 할 서사가 넘어온 것이다.
- 완료된 GitHub 이슈의 로컬 사본을 만들지 않는다(
backlog/completed/는 #245에서 은퇴). 완료 근거는 이슈 코멘트에 남긴다. - 변경 절차와 검증 게이트는 README의
품질 계약 변경 체크리스트를 따른다. 최소 게이트:
PYTHONPATH=.test-deps python3 tests/validate_skill_contracts.py
PYTHONPATH=.test-deps python3 tests/evaluate_scenario_outputs.py
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.
- 5d ago First seen · 33 lines · 753 tokens per session scan A d6f72192627f
beopsuny-skill CLAUDE.md is an instructions file published in the GitHub repository sungjunlee/beopsuny-skill (3 stars, last pushed 2d ago), licensed MIT. It adds 753 tokens to every session, about $0.0038 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 instructions, from other repositories
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
stockbit-mcp CLAUDE.md
Claude Code instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.
devin-handoff AGENTS.md
Instructions for club-cog/devin-handoff, covering devin handoff — agent guide, what this is, when to hand off, finding the script and how to use.
agentic-seo-skills AGENTS.md
Instructions for agencia-conversion/agentic-seo-skills, covering agentic seo — agent runtime contract, mission, six pillars, audience and delivery — web companion first.
superpowers-graph CLAUDE.md
Claude Code instructions for RonMizrahi/superpowers-graph, covering superpowers-graph — repository guide, sources of truth, changing the graph — the eval ships with the change and rules that are not obvious from the code.
pbnz-skills AGENTS.md
AGENTS.md instructions for PBNZ/pbnz-skills, covering agents.md — pbnz-skills, start-here map — where things live and ground rules.