Skill audit report

Agents From Scratch audit report.

Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.

REVIEWED · REVIEWSafe to tryGenerated Jun 17, 2026Heuristic metadata audit
83
Audit
85
Trust
76
Quality
90
Security
76
Maintain
92
Install

OpenAgentSkill Trust Score

85
Strong shortlist

Stars, maintenance, license, docs, install safety, permission surface, 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

INFO

76

826 GitHub stars

Stars/forks activity

INFO

71

826 stars, 211 forks; issue activity unavailable in current metadata

Recent maintenance

INFO

76

5mo since push

License clarity

PASS

86

MIT

README/SKILL.md completeness

PASS

90

Metadata includes enough usage and workflow context

Dependency/runtime risk

PASS

90

no major dependency risk hints in public metadata

Install availability

PASS

92

npx skills add pguso/agents-from-scratch

Install command safety

PASS

92

standard package or runtime install path

Permission surface

PASS

100

no high-risk permission surface in public metadata

Repository evidence

PASS

86

https://github.com/pguso/agents-from-scratch

Review status

PASS

88

AI review data available

Checks

Install and adoption review

9 passed · 3 review

Install path

92

PASS

npx skills add pguso/agents-from-scratch

Repository

88

PASS

https://github.com/pguso/agents-from-scratch

License

86

PASS

MIT

Maintenance

76

CHECK

5mo since push

AI review

88

PASS

Approved with no listed issues

README/SKILL.md completeness

90

PASS

Usable description available

Dependency risk

90

PASS

no major dependency risk hints in public metadata

Install command safety

92

PASS

standard package or runtime install path

Permission surface

100

PASS

no high-risk permission surface in public metadata

Stars/forks activity

71

CHECK

826 stars, 211 forks; issue activity unavailable in current metadata

Adoption

88

PASS

826 GitHub stars

Warnings

  • Quality score needs review

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

Related skills to audit next