agent-rules-skill

왜 쓰나요

핵심 기능

Follows the agents.md convention
Detects build / test / lint commands automatically
Captures coding conventions from existing code
One file works across Claude Code, Cursor, Codex, etc.
Keeps the file short — agents.md is for orientation, not novels

라이브 데모

실제 사용 모습

agent-rules-skill.replay ▶ 준비됨

0/0

설치

작성자 저장소 · Claude Skills 공식 문서

사용 사례

실전 활용법: agent-rules-skill

Generate an AGENTS.md for a repo that doesn't have one

👤 Teams introducing AI coding agents to an existing codebase ⏱ ~15 min beginner

언제 쓸까: Your team just started using Claude Code / Cursor and nobody's written the orientation doc.

흐름

Run it on your repo

Use agent-rules-skill. Analyze this repo and draft an AGENTS.md following the convention.✓ 복사됨

→ Draft with build/test commands, lint config, style notes, gotchas
Refine

Add a section on where not to edit (generated files, vendor/).✓ 복사됨

→ Section added with explicit paths
Commit

Commit as docs/AGENTS.md.✓ 복사됨

→ File committed at repo root or in docs/

결과: A living AGENTS.md that makes future agent sessions start with context.

함정

AGENTS.md balloons into an everything-doc — Keep it focused on what an agent needs. Link to README for humans.

함께 쓰기: filesystem · git

Generate per-package AGENTS.md files in a monorepo

👤 Monorepo maintainers ⏱ ~30 min intermediate

언제 쓸까: Different packages have different conventions; a single root AGENTS.md isn't enough.

흐름

Scan packages

Use agent-rules-skill. For each package in packages/, generate a tailored AGENTS.md capturing its specifics.✓ 복사됨

→ One AGENTS.md per package
Root summary

Generate a root AGENTS.md that links to per-package files and lists shared rules.✓ 복사됨

→ Root file with pointers

결과: Agents pick up the right context based on which package they're working in.

함께 쓰기: filesystem

Keep AGENTS.md in sync with an evolving repo

👤 Repos where AGENTS.md goes stale fast ⏱ ~10 min beginner

언제 쓸까: You added new build commands or changed conventions and AGENTS.md lies about them.

흐름

Diff

Use agent-rules-skill. Compare current AGENTS.md to what the repo actually has now. What's stale?✓ 복사됨

→ List of drift items
Update

Update only the stale parts; leave human-written sections alone.✓ 복사됨

→ Minimal diff preserving human commentary

결과: AGENTS.md stays trustworthy.

함께 쓰기: git

조합

다른 MCP와 조합해 10배 효율

agent-rules-skill + filesystem

Apply generated files directly

Write the draft to AGENTS.md at repo root.✓ 복사됨

agent-rules-skill + git

Commit as a focused change

Commit the new AGENTS.md with a message describing what it covers.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출
scan_repo	repo path	First step on any repo
draft_agents_md	scan output	Drafting new file
diff_check	existing AGENTS.md + current repo	Staleness check

비용 및 제한

운영 비용

API 쿼터: None
호출당 토큰: Modest — repo scan + short output
금액: Free
팁: Run on focused directories in huge monorepos; whole-repo scans are token-heavy.

보안

권한, 시크릿, 파급범위

자격 증명 저장: None

데이터 외부 송신: Repo contents go through Claude API during scan

문제 해결

자주 발생하는 오류와 해결

Generated commands don't match CI

Verify against actual CI config; skill infers from common files but not always correct

File is too long

Prompt for conciseness; agents.md is meant to be short

대안