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 skills add Seekers2001/docs-governance --skill living-docs-governancegit 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/skills/seekers2001/docs-governance/living-docs-governance)<a href="https://agentmods.dev/skills/seekers2001/docs-governance/living-docs-governance"><img src="https://agentmods.dev/badge/skills/seekers2001/docs-governance/living-docs-governance/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.
<a href="https://agentmods.dev/skills/seekers2001/docs-governance/living-docs-governance"><img src="https://agentmods.dev/badge/skills/seekers2001/docs-governance/living-docs-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00266 | $0.08926 |
| Opus 5 | $0.00133 | $0.04463 |
| Sonnet 5 | $0.00053 | $0.01785 |
| Haiku 4.5 | $0.00027 | $0.00893 |
Grade A, and why
living-docs-governance 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.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
活文档治理（Living Docs Governance）
长期项目最先腐烂的是文档层：README 在撒谎、架构笔记描述着一次从没上线的重构、每次进会话 agent 都在重新推导本该一读就懂的上下文。活文档治理把项目文档当成一个小的、各司其职的系统，而不是一堆散文件：四份互相链接的文档，每份只干一件事，外加一个 agent 进会话时读它们的固定顺序。
这是维护期的实践。"我刚 clone 了一个陌生仓库"那种一次性问题，用代码库 onboarding 类技能。本技能负责的是：让 onboarding 出来的那张图，在几个月的改动之后依然为真。
在 Claude Code 中，可由配套的
docs-governor/docs-auditoragent 执行；在 Codex 或没有这些自定义 agent 的宿主中，由当前 agent 直接按本 skill 执行，必要时再使用宿主提供的只读探索或执行型子 agent。本 skill 始终是方法论唯一来源。
什么时候启用
满足任一条就启用：
- 项目长过几个模块，文档开始和代码漂移。
- agent 或队友在会话之间丢失上下文，反复重新发现同一套结构。
- 没人能从单一位置回答"这项目现在健康度如何？""上周改了啥？"。
- 死文件和废弃实验堆积，偶尔被误重建。
- 你想给一个单人/小团队项目一层耐用、低开销的治理，又不想上大型多人仓库那套重 CI 机器。
不要在用完即弃的脚本、或活不过这周的仓库上用——那是过度治理。
渐进式采用：从最小开始，但提前看到下一级
别一上来铺满四件套——那本身就是过度治理。从最小起步，真正关键的不是"按需补"，是提前认出"下一级快需要了"的预警信号，在它真痛之前就备好。等漂移出事（STATUS 撒谎、重建已删文件）才补，文档已经烂了一轮、返工已经发生——治理的价值在防患，不在救火。
| 当前规模 | 该有 | 下一级的预警信号（看到就准备上） |
|---|---|---|
| 单文件 / 用完即弃 | 什么都不用 | —— |
| 长过几个模块、要维护一阵 | CLAUDE.md（几条硬规则 + 路标） | 开始有人问"这项目现在健康吗" → 备 STATUS |
| 有健康 / 风险 / 待删要追 | + PROJECT_STATUS.md | AI/新人开始"找不到某功能""改错地方" → 备 MAP |
| 找东西 / 跨 Module 改开始费劲 | + CLAUDE_MAP.md | Module 权责、状态归属、依赖或主流程开始说不清 → 备 ARCHITECTURE |
| Module 架构需要共享 | + ARCHITECTURE.md（可选血肉） | 反复问“为什么这样设计” → 备 ADR；要追历史 → 备 LOG |
| 要追溯决策与历史 | + PROJECT_LOG.md（四件套齐） | 分出前后端、接口字段对不上 → 备 CONTRACT |
| 分前后端 / 多服务 | + CONTRACT.md（见 contract-first） |
—— |
预警信号的意义：让你在痛之前上对应那一级，而不是等它腐烂出事再救火。
团队共享 vs 个人：治理文件放哪一层
四件套是项目级、团队共享的——进 git，所有协作者 / agent 共用，写的是"团队共识的真相"。个人临时偏好别塞进去（会污染团队视图）：那些放 CLAUDE.local.md（同目录、不提交）或 ~/.claude/（全局个人）。判据一句话：帮整个团队一致 → 进项目四件套；只是你一个人的习惯 → 进 .local / 全局。
怎么运作
这套系统 = 四份脊柱文档（角色严格分离）+ 分级读取协议 + 让它们保持最新的更新规则 + 阶段收尾时的查漏补缺矩阵。CONTEXT.md、docs/adr/、契约、测试和回归台账都是按真实需要长出的血肉，不是第五到第九份必建脊柱。
Claude Code / Codex 入口适配
两端共用本 skill，不复制方法论：
| 用户意图 | Claude Code 入口 | Codex / ChatGPT 入口 | 详细执行流程 |
|---|---|---|---|
| 空项目初始化 | /governance-init |
$living-docs-governance + “初始化空项目治理” |
本文“空项目初始化”执行模式 |
| 已有项目治理 | /governance |
$living-docs-governance + “治理当前项目” |
本文“已有项目治理”执行模式 |
| 只读审计 | /governance-audit |
$living-docs-governance + “只读审计” |
本文“只读审计”执行模式 |
| 阶段同步 | /governance-sync |
$living-docs-governance + “阶段收尾同步” |
本文“阶段同步”执行模式 |
| LOG 复盘 | /governance-retro |
$living-docs-governance + “复盘 PROJECT_LOG” |
本文“日志复盘”执行模式 |
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.
- 3d ago Changed · +91 lines · +21 tokens per session 8cfa9200b6de
- 9d ago First seen · 212 lines · 245 tokens per session scan A 691827906ace
living-docs-governance is a skill published in the GitHub repository Seekers2001/docs-governance (69 stars, last pushed 4d ago), licensed MIT. It adds 266 tokens to every session and 8,926 once invoked, about $0.0013 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…