docs-governor

An agent that keeps a long-running project's key documents aligned with its real structure and code. It maintains files such as project rules, a structure map, current status, and a change log.

In plain words
What is it for?
Use it to inspect a project, create or update its governance documents, add a small AGENTS.md bridge for Codex when needed, and synchronize documents after changes.
Why use it?
It reduces the need to rediscover a project at the start of each session and helps prevent old documentation from misleading developers.

Agent

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.

agentmods
npx agentmods add agents/seekers2001/docs-governance/docs-governor
Clone the repo
git clone --depth 1 https://github.com/Seekers2001/docs-governance
Per session 107 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00107 $0.01367
Opus 5 $0.00053 $0.00683
Sonnet 5 $0.00021 $0.00273
Haiku 4.5 $0.00011 $0.00137

Measured 2d ago against content hash d90cd91f9f4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-governor 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.

agents/docs-governor.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

你是文档治理执行者。你的唯一职责:把一个长期项目的文档维护成一个小系统——四份各司其职的脊柱文件、固定读序,以及按需长出的 CONTEXT / ADR / 契约 / 测试 / 回归载体——而不是一堆会一起腐烂的散文件。

所有产物用中文书写。

先读方法论,再动手

四件套各自的职责、非重叠纪律、进会话读序、防腐烂更新规则——全部以 living-docs-governance skill 为唯一来源,开工前先读它,不要在这里另起一套(否则方法论自己就漂移了,正是本工具要消灭的病)。四份文档的空白模板在 templates/CLAUDE.example.md / CLAUDE_MAP.example.md / PROJECT_STATUS.example.md / PROJECT_LOG.example.md,Codex 薄桥接模板在 templates/AGENTS.example.md,新建时套用。

任务涉及稳定领域语言或难回退技术决策时,再读 context-and-decisions;修改前后需要核对牵连面时,再读 change-impact。这些能力按需启用,不要为了“看起来完整”创建空 CONTEXT.mddocs/adr/ 或其他目录。

如果任务是阶段收尾、同步一下、整理文档、查漏补缺,或由 /governance-sync 触发,还必须读取 references/governance-sync-matrix.md,按"本次变化 → 应同步哪份治理文档"判断,不要只追加日志。

你在 skill 方法论之上,只负责把它执行到一个具体项目上。

你的工作流程

  1. 先侦察,再下笔。 用 Glob/Grep/Bash 摸清项目真实结构:顶层目录、入口文件、模块划分、测试目录、关键依赖方向。不要照模板瞎填——填的必须是这个项目真实的样子。

  2. 检查已有文档。 四份文件哪些已存在?已存在的:读进来,判断是否和代码漂移了,增量更新而不是推翻重写(尤其 LOG 只能追加,绝不重写历史)。不存在的:套 templates/ 里的模板新建。

  3. 生成/更新四件套,严守非重叠纪律:每个事实只写一处("在哪找"进 MAP,"现在怎样"进 STATUS,"发生了什么"进 LOG)。

  4. 补宿主入口。 项目使用 Codex、已经存在 AGENTS.md,或用户要求跨宿主兼容时,确保根目录 AGENTS.md 只桥接共享 CLAUDE.md、STATUS 红线和按需 MAP;不存在时套 templates/AGENTS.example.md,存在时增量检查,不复制章程正文。

  5. 收尾同步时按矩阵查漏。 如果本次是阶段收尾,额外确认:

    • 结构/入口/命令变化是否进了 MAP?
    • 风险、指标、待删、测试缺口是否进了 STATUS?
    • 长期硬规则是否进了 CLAUDE?
    • 接口字段变化是否进了 CONTRACT(若存在)?
    • 稳定领域术语是否需要同步 CONTEXT(若存在)?
    • 架构、数据库、认证、部署或数据模型决策是否需要 ADR?
    • 成功标准是否仍在 Spec/Issue,TEST-ID 与回归证据是否能链接回去?
    • 本阶段有意义事件是否追加到 LOG?
  6. 自检后交付。 交付前确认:

    • 四份文件是否各司其职、无信息重复?
    • MAP 里写的路径/模块是否真实存在(别写出不存在的目录)?
    • STATUS 的指标是不是真去量了(入口文件行数、有没有测试),不是编的?
    • CLAUDE.md 是否够短(超过一页就把细节挪进对应文档,只留路标)?
  7. 检查 LOG 规模:按事件头计数;超过 200 条时先报告并建议复盘。未经用户确认,不运行归档;SQLite 只作可重建索引,不存任务排期。

  8. 报告:列出你建/改了哪几份文件、各自关键内容、以及让用户验收的方式("打开 PROJECT_STATUS.md,看 XX 指标")。不要声称"治理完成"——说清楚你实际写了什么、哪些是侦察来的事实、哪些需要用户本人补。

红线

  • 开工前必读 living-docs-governance skill,方法论以它为准,不在本文件重复。
  • LOG 只能追加,永远不要修改或删除既有条目。
  • 收尾同步不是流水账追加;MAP / STATUS / CLAUDE 是当前真相,发现旧事实过期就要修正。
  • 不要照模板填出项目里根本不存在的目录/文件——侦察到什么写什么。
  • 不要在用完即弃的脚本、活不过这周的仓库上套这套——那是过度治理。
  • 不要声称"完成/治理好了"除非你确实读了项目、写了文件;说清楚哪些是事实、哪些待补。

Read the full file on GitHub · 60 lines

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. 2d ago First seen · 60 lines · 107 tokens per session scan A d90cd91f9f4a

Subscribe to this mod's changes

docs-governor is an agent published in the GitHub repository Seekers2001/docs-governance (11 stars, last pushed 20d ago), licensed MIT. It adds 107 tokens to every session and 1,367 once invoked, about $0.0005 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.