Skill audit report
AGENTS.md 거버넌스 시스템을 분석·생성하는 마스터 프롬프트. 현재 프로젝트를 분석하여 루트 AGENTS.md와 하위 AGENTS.md를 즉시 생성하고, 코드에서 찾은 팀 고유 지식(비대칭·테스트 경계·하드 제약·이중 방어·보안 경계)을 근거와 함께 Golden Rules에 반영하고, CLAUDE.md에 @AGENTS.md 링크를 추가한다. "AGENTS.md 만들어줘", "에이전트 규칙 만들어줘", "/agents-md" 호출 시 반드시 실행하라.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
WARN48
91 GitHub stars
Stars/forks activity
WARN48
91 stars, 28 forks; issue activity unavailable in current metadata
Recent maintenance
PASS88
2mo since push
License clarity
PASS86
MIT
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
PASS82
network or browser surface
Install availability
PASS92
npx skills add devbrother2024/skills --skill agents-md
Install command safety
PASS92
standard package or runtime install path
Permission surface
WARN48
shell or command execution, filesystem or document access
Repository evidence
PASS86
https://github.com/devbrother2024/skills/tree/main/agents-md
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add devbrother2024/skills --skill agents-md
Repository
88
https://github.com/devbrother2024/skills/tree/main/agents-md
License
86
MIT
Maintenance
88
2mo since push
AI review
55
The skill instructs to overwrite existing AGENTS.md without asking for confirmation, which could be destructive if the user did not intend to replace it. However, this is a deliberate design choice for a skill explicitly invoked by the user.
README/SKILL.md completeness
86
Usable description available
Dependency risk
82
network or browser surface
Install command safety
92
standard package or runtime install path
Permission surface
48
shell or command execution, filesystem or document access
Stars/forks activity
48
91 stars, 28 forks; issue activity unavailable in current metadata
Adoption
68
91 GitHub stars
Warnings
Method
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Compare nearby options