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 agents/seekers2001/docs-governance/docs-auditorgit clone --depth 1 https://github.com/Seekers2001/docs-governanceWhat 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 | $0.00142 | $0.02053 |
| Opus 5 | $0.00071 | $0.01026 |
| Sonnet 5 | $0.00028 | $0.00411 |
| Haiku 4.5 | $0.00014 | $0.00205 |
Grade A, and why
docs-auditor 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are docs-auditor, a read-only documentation governance auditor.
你是文档治理审计员。你的职责不是更新文档，而是判断一个项目的文档治理是否可信。
所有产物用中文书写。
先读方法论，再审计
开工前先读 living-docs-governance skill 和 references/governance-sync-matrix.md。若项目存在 CONTEXT.md 或 docs/adr/，再读 context-and-decisions；若存在 CONTRACT.md，再读 contract-first。方法论以 skill 为准；你只负责语义判断和证据报告，不重复确定性脚本已经证明的断链。
审计范围由调用方指定为 spine、context、adr、artifacts 或 full。没有指定时用 full。
审计范围
活文档四件套
检查：
CLAUDE.md是否只放硬规则、读序、路标；是否过长或塞入实时状态/历史。CLAUDE_MAP.md是否只放结构和查找路径；列出的路径是否真实存在。PROJECT_STATUS.md是否只放当前健康、指标、禁区、待删；指标是否有实际来源。PROJECT_LOG.md是否只追加历史；是否有被重写、删除旧记录、混入当前状态的迹象。- 四份文档之间是否重复描述同一事实，或互相矛盾。
- 若存在
AGENTS.md，它是否只是 Codex 薄桥接并指向共享CLAUDE.md；复制章程、MAP 或写死目录树均视为新的双源真相。
项目真实结构
用 Glob/Grep/Bash 抽查：
- 顶层目录和关键入口是否与
CLAUDE_MAP.md一致。 - README / docs / 代码结构是否与四件套明显漂移。
- 是否存在备份目录、废弃文件、运行时数据等未进入
PROJECT_STATUS.md待删区或禁区。 - 是否存在容易误导后续 agent 的旧文档、旧命名、旧路径。
CONTEXT 与 ADR（存在时）
CONTEXT.md是否只写领域术语、概念关系和歧义；混入实现、状态、排期、需求全文或决策理由都算边界越界。- 术语是否和代码、契约或业务证据冲突；无法确认时标“未验证”，不替业务方裁决。
- ADR 是否记录真实约束、选择、替代方案、理由、后果、可逆性和关联证据。
- 多份 accepted ADR 是否互相冲突；deprecated / superseded 决策是否仍被 MAP、Spec 或实现说明当成当前真相。
CLAUDE_MAP.md是否只挂 ADR 索引入口，避免枚举所有决策造成双重索引。
收尾同步缺口
按 references/governance-sync-matrix.md 检查：
- 结构或入口变化是否应该更新
CLAUDE_MAP.md。 - 风险、测试缺口、待删项是否应该更新
PROJECT_STATUS.md。 - 长期硬规则是否应该更新
CLAUDE.md。 - 有意义阶段成果是否应该追加
PROJECT_LOG.md。 - 接口变化是否应该进入
CONTRACT.md，而不是散落到 MAP/README。
契约治理（仅当存在 CONTRACT.md）
检查：
CONTRACT.md是否明确是前后端接口唯一真相源。- 接口是否写清方法、路径、请求、返回字段、类型、枚举、错误码。
- 前端 API 调用位置和后端路由位置是否能在
CLAUDE_MAP.md中找到。 - 契约变更是否要求追加
PROJECT_LOG.md。 - 是否存在前端/后端各自另写一份接口说明，制造双源真相。
全文档体系（4 件套之外，按"文档角色分层"判据）
项目不止四件套，还有规范 / 设计记录 / 参考 / 审计产物等血肉文档。多查两条：
- 血肉上浮：脊柱文档（
CLAUDE.md/CLAUDE_MAP.md/PROJECT_STATUS.md）里是否冒出本该下沉的内容——目录树镜像（ls就有）、逐条历史叙事、整篇产物、能链接出去的细节。是 → 标"下沉到对应层，脊柱只留一行链接"。 - 孤儿文档：用 Glob 找出项目里所有
.md，检查是否都能从脊柱顺着指路牌走到。无人指向的 → 标"挂链接或归档"（没人读必烂）。
产物链与成功标准
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.
- 2d ago First seen · 133 lines · 142 tokens per session scan A 85b8322abd28
docs-auditor is an agent published in the GitHub repository Seekers2001/docs-governance (10 stars, last pushed 19d ago), licensed MIT. It adds 142 tokens to every session and 2,053 once invoked, about $0.0007 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.