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.
npx agentmods add commands/seekers2001/docs-governance/governance-auditgit clone --depth 1 https://github.com/Seekers2001/docs-governanceWrote 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.
[](https://agentmods.dev/commands/seekers2001/docs-governance/governance-audit)<a href="https://agentmods.dev/commands/seekers2001/docs-governance/governance-audit"><img src="https://agentmods.dev/badge/commands/seekers2001/docs-governance/governance-audit.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00043 | $0.00783 |
| Opus 5 | $0.00022 | $0.00392 |
| Sonnet 5 | $0.00009 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
governance-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
对当前工作目录做一次只读文档治理审计。铁律：永远从最便宜的判定层开始，失败就短路——确定性检查一个脚本秒出退出码，轮不到大模型；别拿劳斯莱斯买菜。
第一步 · 便宜层（确定性脚本，必须先跑）：
bash <插件目录>/scripts/audit-cheap.sh <scope>
范围：spine（四件套/删除区/LOG）、context、adr、artifacts（Markdown 链接、TEST-ID、孤儿文档）、full。它检查路径与链接断裂、ADR 索引、LOG 活跃+归档的只追加完整性、>200 条触发、派生数据库误提交、删除区复活和跨文档 TEST-ID 断链。
- 退出码 1（红）→ 短路：直接把脚本输出整理成审计报告交给用户，不要调用 docs-auditor——确定性问题先修，修完再来。
- 退出码 0（绿）→ 进第二步。
第二步 · 贵层（LLM 裁判，只判机器判不了的模糊问题）：
调用 docs-auditor 子 agent，只聚焦机器判不了的问题：CONTEXT 边界与术语冲突、ADR 决策冲突、过期/归档文档是否被当当前真相、Spec/Issue/代码/TEST-ID/评审是否闭环、STATUS 指标证据、脊柱越界与重复真相。便宜层已经查过的不要重复查。
用户参数（可选）：$ARGUMENTS
- 不带参数：使用
full。 - 带范围：只审对应范围；语义层也只看相关问题。
- 带具体路径或
contract：在所选范围外再重点核对该对象，但仍保持只读。
执行要求：
- 只读扫描，不修改任何文件。
- 先检查
CLAUDE.md/CLAUDE_MAP.md/PROJECT_STATUS.md/PROJECT_LOG.md是否存在；不存在就报告缺失，不要创建。 - 抽查
CLAUDE_MAP.md里的路径是否真实存在。 - 检查
PROJECT_STATUS.md的指标是否像是实际量过；无法验证就标“未验证”。 - 检查
PROJECT_LOG.md是否保持历史流水账职责。 - 如存在
CONTRACT.md，检查其是否和前后端接口位置形成单一真相源。 - 如存在
AGENTS.md，检查它是否只桥接共享CLAUDE.md；不得复制章程或 MAP。 - 外部 Issue Tracker 不可用时，把相关状态写成“未验证”，不猜任务是否完成。
- 输出审计报告：总体结论、P0/P1/P2 发现、证据、建议、待人工确认项。
- 默认只在回复中输出；只有用户明确要求保存，才写入
docs/audits/YYYY-MM-DD-*.md。
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.
- 5d ago First seen · 40 lines · 43 tokens per session scan A d0c8e2b37694
governance-audit is a command published in the GitHub repository Seekers2001/docs-governance (28 stars, last pushed 22d ago), licensed MIT. It adds 43 tokens to every session and 783 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.