harness-audit

harness-audit is a skill for Codex from hashgraph-online/awesome-codex-plugins. It costs 112 tokens per session (1,394 once invoked), scanned A, original, Apache-2.0.

An audit skill for reviewing a coding-agent platform's setup across seven areas, such as agent coverage, skills, hooks, rules, commands, and documentation. It produces scores and suggested actions.

In plain words
What is it for?
Use it for platform health checks, periodic reviews, and regression checks after adding or changing agent capabilities.
Why use it?
It helps find missing files, unused rules, broken links between commands and agents, and other gaps in the platform configuration.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it for platform health checks, periodic reviews, and regression checks after adding or changing agent capabilities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hashgraph-online/awesome-codex-plugins/harness-audit
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add hashgraph-online/awesome-codex-plugins --skill harness-audit
Clone the repo
git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for harness-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/harness-audit/github.svg)](https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/harness-audit)
Your own site
<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/harness-audit"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/harness-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for harness-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/harness-audit"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/harness-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,394 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.01394
Opus 5 $0.00056 $0.00697
Sonnet 5 $0.00022 $0.00279
Haiku 4.5 $0.00011 $0.00139

Measured 3d ago against content hash a2b8fb0a1c7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

harness-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/Colin4k1024/tsp/skills/harness-audit/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harness 能力面审计

对当前平台配置进行 7 维度评分,定位能力短板并给出优先改进建议。


触发方式

/harness-audit

或由 harness-optimizer specialist 直接调用。


7 个评估维度

1. Agent Coverage(代理覆盖)

检查所有角色是否有对应的 agents/roles/*.md 生成文件,specialist agents 是否与 commands/ 命令一一对应。

评分标准

  • 90–100:所有角色 + 全部 specialist 覆盖完整
  • 70–89:≥ 2 个角色或 specialist 缺失
  • < 70:核心角色缺失 agent 文件

2. Skill Completeness(技能完整性)

检查 skills/skills/skills/ 中所有技能是否有有效 SKILL.md,role.yaml 中引用的技能是否实际存在。

评分标准

  • 90–100:无悬空引用,所有 SKILL.md 齐备
  • 70–89:1–3 处悬空引用
  • < 70:多处悬空引用或 SKILL.md 缺失

3. Hook Effectiveness(Hook 有效性)

检查 hooks/hooks.json 配置是否启用关键 hook,session_start.py/session_end.py 是否能实际运行。

评分标准

  • 90–100:hooks 配置完整,smoke 验证通过
  • 70–89:hooks 存在但未启用
  • < 70:hooks 缺失或运行报错

4. Rule Enforcement(规则执行)

检查 rules/ 中所有规则文件是否被 CLAUDE.md/AGENTS.md 或角色的 governance_rules 字段引用。

评分标准

  • 90–100:无孤立规则,所有规则有引用入口
  • 70–89:≤ 3 个孤立规则
  • < 70:> 3 个孤立规则或核心规则未引用

5. Command Coverage(命令覆盖)

检查 commands/ 中每个命令是否在 CLAUDE.md/AGENTS.md 的命令面中列出,specialist 与命令是否匹配。

评分标准

  • 90–100:命令与 AGENTS.md 门面一致
  • 70–89:1–2 个命令缺少文档入口
  • < 70:> 2 个命令游离于门面之外

6. Documentation Quality(文档质量)

检查 docs/runbooks/docs/memory/(若存在)中关键手册是否存在,AGENTS.md 中链接的文件是否实际可访问。

评分标准

  • 90–100:所有 AGENTS.md 链接文件存在,docs/memory/ 已初始化
  • 70–89:≤ 5 个链接失效
  • < 70:> 5 个链接失效或 docs/memory/ 不存在

7. Integration Depth(集成深度)

评估 role.yaml 中 recommended_ecc_skills / recommended_domain_skills 覆盖情况,以及各角色能力与其职责的匹配度。

评分标准

  • 90–100:所有角色至少有 3 个 ecc + 2 个 domain skills(适用角色)
  • 70–89:部分角色 skills 配置稀疏
  • < 70:多个角色零 skills 配置

标准输出格式

## Harness Audit Report — {date}

### Overall Score: {score}/100

| 维度 | 得分 | 状态 | 主要问题 |
|------|------|------|---------|
| Agent Coverage | XX | ✅/⚠️/❌ | ... |
| Skill Completeness | XX | ✅/⚠️/❌ | ... |
| Hook Effectiveness | XX | ✅/⚠️/❌ | ... |
| Rule Enforcement | XX | ✅/⚠️/❌ | ... |
| Command Coverage | XX | ✅/⚠️/❌ | ... |
| Documentation Quality | XX | ✅/⚠️/❌ | ... |
| Integration Depth | XX | ✅/⚠️/❌ | ... |

### Top Actions(优先级排序)

1. **[优先级:高]** {具体行动} — 影响维度:{维度名}
2. ...

### Recommendations

- {建议1}
- {建议2}

Read the full file on GitHub · 136 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 136 lines · 112 tokens per session scan A a2b8fb0a1c7f

Subscribe to this mod's changes

harness-audit is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (956 stars, last pushed today), licensed Apache-2.0. It adds 112 tokens to every session and 1,394 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Related

Other skills, from other repositories

search

Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.

taishi-i/awesome-ChatGPT-repositories · 57 tokens

sprr

Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".

wilsonfreitas/awesome-quant · 60 tokens

bprr

Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.

wilsonfreitas/awesome-quant · 61 tokens

drawio-reconstruction

Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw.io elements carry text and structure, SVG covers simple icons that match the reference, and cropped or transparent PNGs preserve complex visuals. Use when the user wants a diagram image, research figure…

HKUSTDial/Supervisor-Skills · 102 tokens

benchmark-paper-template

Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluation Framework, Empirical Findings, optional Companion Method). Returns a completeness audit, a six-part Introduction logic chain, a Section 2-7 skeleton, and a pre-submission checklist. Use when…

HKUSTDial/Supervisor-Skills · 96 tokens

reverse-engineering-android-malware-with-jadx

Reverse engineers malicious Android APK files using JADX decompiler to analyze Java/Kotlin source code, identify malicious functionality including data theft, C2 communication, privilege escalation, and overlay attacks. Examines manifest permissions, receivers, services, and native libraries. Activates for requests…

adriannoes/awesome-agentic-ai · 82 tokens