OpenAgentSkill
GitHub200+

Skill audit report

context-tax-audit Audit report.

Inventory everything an agent injects into each request besides the user's message, such as system prompt, environment info, skill list, tool definitions, per-turn context blocks and reminders, and check necessity, frequency, precision, position and prompt-cache impact. Use when reviewing an agent's prompt assembly, chasing low cache hit rates, or trimming per-turn overhead.

BLOCKED · BLOCKNeeds reviewGenerated Nov 6, 2026Heuristic metadata audit
78
Audit
74
Trust
69
Quality
75
Security
100
Maintain
92
Install

OpenAgentSkill Trust Score

74
Strong shortlist

OpenAgentSkill Trust Score

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

GitHub adoption

INFO

76

510 GitHub stars

Stars/forks activity

INFO

65

510 stars, 39 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

100

8d since push

License clarity

PASS

86

MIT

README/SKILL.md completeness

INFO

76

Public metadata needs stronger README/SKILL.md context

Dependency/runtime risk

WARN

54

command execution surface, credential or environment access

Install availability

PASS

92

npx skills add MiniMax-AI/mcode-stack --skill context-tax-audit

Install command safety

PASS

92

standard package or runtime install path

Permission surface

WARN

50

secrets or environment access, shell or command execution

Repository evidence

PASS

86

https://github.com/MiniMax-AI/mcode-stack/tree/main/stacks/ronny/skills/context-tax-audit

Review status

WARN

46

AI review approval is missing

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

7 Passed · 12 Needs review

Install path

92

PASS

npx skills add MiniMax-AI/mcode-stack --skill context-tax-audit

Repository

88

PASS

https://github.com/MiniMax-AI/mcode-stack/tree/main/stacks/ronny/skills/context-tax-audit

License

86

PASS

MIT

Maintenance

100

PASS

8d since push

AI review

55

CHECK

Review approval is missing

README/SKILL.md completeness

84

PASS

Usable description available

Dependency risk

54

FIX

command execution surface, credential or environment access

Install command safety

92

PASS

standard package or runtime install path

Permission surface

50

FIX

secrets or environment access, shell or command execution

Stars/forks activity

65

CHECK

510 stars, 39 forks; issue activity unavailable in current metadata

Adoption

88

PASS

510 GitHub stars

Warnings

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • AI review approval is missing
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • Dependency/runtime risk: command execution surface, credential or environment access
  • Permission surface: secrets or environment access, shell or command execution
  • Review status: AI review approval is missing

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.