Skill audit report

Homunculus audit report.

A Claude Code plugin that watches how you work, learns your patterns, and evolves itself to help you better.

EXPERIMENTAL · REVIEWNeeds reviewGenerated Jun 23, 2026Heuristic metadata audit

Audit

Trust

Quality

Security

Maintain

Install

OpenAgentSkill Trust Score

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

377 GitHub stars

Stars/forks activity

WARN

377 stars, 45 forks; issue activity unavailable in current metadata

Recent maintenance

INFO

5mo since push

License clarity

WARN

Unknown

README/SKILL.md completeness

PASS

Metadata includes enough usage and workflow context

Dependency/runtime risk

INFO

command execution surface

Install availability

PASS

npx skills add humanplane/homunculus

Install command safety

PASS

standard package or runtime install path

Permission surface

INFO

shell or command execution, filesystem or document access

Repository evidence

PASS

https://github.com/humanplane/homunculus

Review status

PASS

AI review data available

Real agent outcomes

INFO

No agent outcome data yet

Checks

Install and adoption review

5 passed · 9 review

Install path

PASS

npx skills add humanplane/homunculus

Repository

PASS

https://github.com/humanplane/homunculus

License

CHECK

Unknown

Maintenance

CHECK

5mo since push

AI review

PASS

Approved with no listed issues

README/SKILL.md completeness

PASS

Usable description available

Dependency risk

CHECK

command execution surface

Install command safety

PASS

standard package or runtime install path

Permission surface

CHECK

shell or command execution, filesystem or document access

Stars/forks activity

FIX

377 stars, 45 forks; issue activity unavailable in current metadata

Adoption

INFO

377 GitHub stars

Warnings

License is unclear
Quality score needs review
Stars/forks activity: 377 stars, 45 forks; issue activity unavailable in current metadata
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.

Install path

Review the report before installing into production agents.

$ npx skills add humanplane/homunculus

Agent-readable metadata

Machine decision packet

Embedded JSON exposes suited tasks, suited agents, install command, trust score, safety gate, alternatives, and do-not-use conditions for agent review.

Install policy: review
Best agents: Shell + Developer Tools
Alternatives: 3

Open agent JSON

Signals

Audit score: 75/100
Quality: 68/100
Trust: 73/100
Install safety: 92/100
Permission surface: 62/100
Maintenance: 5mo since push
Events: 4 events
GitHub stars: 377
Last push: Jan 23, 2026

Agent safety v2

47/100 · Avoid automatic install

Experimentalreview

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Test manually in an isolated workspace and compare against safer alternatives.

High-risk permission hints: Shell or command execution
47/100 agent safety score

Shell or command execution

high

Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.

Network access

medium

Skill likely fetches remote pages, APIs, repositories, or external services.

Filesystem access

medium

Skill may read or write project files, documents, generated artifacts, or local workspace state.

High-risk permission hints: Shell or command execution
License is unclear

Back to skill Alternatives Audit badge SVG

Compare nearby options

Homunculus audit report.

Stars, maintenance, license, docs, install safety, permission surface, and installability.

Install and adoption review

Related skills to audit next

Opencode

Puppeteer

Codex