Skill audit report
Harness Books audit report.
📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev
OpenAgentSkill Trust Score
Stars, maintenance, license, docs, dependency risk, and installability.
The Trust Score is OpenAgentSkill's adoption layer. It is designed to help an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
PASS86
2.4K GitHub stars
Recent maintenance
PASS88
2mo since push
License clarity
WARN42
Unknown
README/SKILL.md completeness
PASS90
Metadata includes enough usage and workflow context
Dependency risk
PASS90
no major dependency risk hints in public metadata
Install availability
PASS92
npx skills add wquguru/harness-books
Repository evidence
PASS86
https://github.com/wquguru/harness-books
Review status
PASS88
AI review data available
Checks
Install and adoption review
Install path
92
npx skills add wquguru/harness-books
Repository
88
https://github.com/wquguru/harness-books
License
45
Unknown
Maintenance
88
2mo since push
AI review
88
Approved with no listed issues
README/SKILL.md completeness
90
Usable description available
Dependency risk
90
no major dependency risk hints in public metadata
Adoption
88
2.4K GitHub stars
Warnings
- License is unclear
- License clarity: Unknown
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