Skill audit report

agent-harness Audit report.

Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).

REVIEWED · REVIEWNeeds reviewGenerated Aug 22, 2026Heuristic metadata audit
87
Audit
81
Trust
91
Quality
78
Security
100
Maintain
92
Install

OpenAgentSkill Trust Score

81
Strong shortlist

OpenAgentSkill Trust Score

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

GitHub adoption

PASS

100

25K GitHub stars

Stars/forks activity

PASS

97

25K stars, 3.5K forks; issue activity unavailable in current metadata

Recent maintenance

PASS

100

Pushed today

License clarity

PASS

86

MIT

README/SKILL.md completeness

PASS

86

Metadata includes enough usage and workflow context

Dependency/runtime risk

INFO

72

command execution surface

Install availability

PASS

92

npx skills add alirezarezvani/claude-skills --skill agent-harness

Install command safety

PASS

92

standard package or runtime install path

Permission surface

INFO

62

shell or command execution, filesystem or document access

Repository evidence

PASS

86

https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness

Review status

INFO

66

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

8 Passed · 8 Needs review

Install path

92

PASS

npx skills add alirezarezvani/claude-skills --skill agent-harness

Repository

88

PASS

https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness

License

86

PASS

MIT

Maintenance

100

PASS

Pushed today

AI review

55

CHECK

The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.

README/SKILL.md completeness

86

PASS

Usable description available

Dependency risk

72

CHECK

command execution surface

Install command safety

92

PASS

standard package or runtime install path

Permission surface

62

CHECK

shell or command execution, filesystem or document access

Stars/forks activity

97

PASS

25K stars, 3.5K forks; issue activity unavailable in current metadata

Adoption

88

PASS

25K GitHub stars

Financial decision safety

58

CHECK

Research-only use: do not treat output as financial advice or execute a position without human approval.

Warnings

  • Financial research output is not financial advice; require human review before any live investment decision
  • The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.
  • Financial research output is not financial advice; require human review before any live investment decision.
  • 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