Skill audit report

Mycelium Audit report.

A Claude Code harness that forces agents to perform discovery and weigh evidence before writing code, ensuring they earn the right to start building.

EXPERIMENTAL · REVIEWNeeds reviewGenerated Oct 13, 2026Heuristic metadata audit

Audit

Trust

Quality

Security

Maintain

Install

OpenAgentSkill Trust Score

Strong shortlist

OpenAgentSkill Trust Score

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

WARN

41 GitHub stars

Stars/forks activity

WARN

41 stars, 3 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

2mo since push

License clarity

PASS

MIT

README/SKILL.md completeness

PASS

100

Metadata includes enough usage and workflow context

Dependency/runtime risk

PASS

database surface

Install availability

PASS

npx skills add haabe/mycelium

Install command safety

PASS

standard package or runtime install path

Permission surface

INFO

shell or command execution, database access

Repository evidence

PASS

https://github.com/haabe/mycelium

Review status

PASS

AI review data available

Agent Proven outcomes

INFO

No agent outcome data yet

Checks

Install and adoption review

8 Passed · 7 Needs review

Install path

PASS

npx skills add haabe/mycelium

Repository

PASS

https://github.com/haabe/mycelium

License

PASS

MIT

Maintenance

PASS

2mo since push

AI review

PASS

Approved with no listed issues

README/SKILL.md completeness

100

PASS

Usable description available

Dependency risk

PASS

database surface

Install command safety

PASS

standard package or runtime install path

Permission surface

CHECK

shell or command execution, database access

Stars/forks activity

FIX

41 stars, 3 forks; issue activity unavailable in current metadata

Adoption

CHECK

41 GitHub stars

Warnings

Low GitHub adoption signal
Quality score needs review
GitHub adoption: 41 GitHub stars
Stars/forks activity: 41 stars, 3 forks; issue activity unavailable in current metadata

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.

Review the source

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: Python + Codex
Alternatives: 3

Open agent JSON

Signals

Audit score: 80/100
Quality: 71/100
Trust: 77/100
Install safety: 92/100
Permission surface: 64/100
Maintenance: 2mo since push
Events: 4 events
GitHub stars: 41
Last push: Jul 30, 2026

Agent safety v2

48/100 · Avoid automatic install

Experimentalreview

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

Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.
High-risk permission hints: Shell or command execution
48/100 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.

Database access

medium

Skill may inspect schemas, query databases, or work with persistent stores.

High-risk permission hints: Shell or command execution
Low GitHub adoption signal
Skill source structure is not confirmed in the registry. Inspect the source and identify valid skill instructions before proposing an installation. A repository URL or GitHub stars do not prove installability.

Back to skill Alternatives Audit badge SVG

Compare nearby options

Mycelium Audit report.

OpenAgentSkill Trust Score

Install and adoption review

Related skills to audit next

Code Review

Appsmith

Implement