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 rules/lawofall/agentcore/doc-governancegit clone --depth 1 https://github.com/Lawofall/AgentCoreWhat 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 | $0.00000 | $0.01994 |
| Opus 5 | $0.00000 | $0.00997 |
| Sonnet 5 | $0.00000 | $0.00399 |
| Haiku 4.5 | $0.00000 | $0.00199 |
Grade A, and why
doc-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 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
文档治理
docs/ 与 rules/ 定位
| 维度 | docs/ 设计文档 |
.cursor/rules/ 规则 |
|---|---|---|
| 本质 | 项目知识资产(What/Why) | AI 行为指令(How) |
| 读者 | 人 + AI | AI |
灰色地带优先放 docs/,rules 简短引用。
内容策略
- 语言:公开设计文档与贡献说明以中文为准;根 README 可保留一句英文产品介绍(检索 / 跨工具 AI)。不维护完整英文 docs。
- 文档是现状说明书,不是变更日志——变更历程交给 git。推广到所有现行通道(提示词、对用户的结论、规则、注释、记忆条目)→ 现行信息。
- 出门检验:改完的现行文须仍会改变以后怎么做(同上);落地同一改动把已完成阶梯、废名二选一、施工日记带出权威文。
- 只记录代码看不出来的东西:决策与理由、被否决方案、约束边界、跨系统集成点。
- 检验标准:「AI 读完代码后还缺什么信息?」缺的才写。
- 主循环归属:新增 / 改写
docs/专题时,开头写一行「主循环归属」——服务主循环(说·组·看·拍·收 + 记)哪一拍。答不出的须标明是平台底座、工程内务还是实验项目,这三类不进产品叙事、不进路线图产品方向表。判据全文 → 定位 §二;docs/03已全篇覆盖,可抄格式。
现状目录 vs 规划目录
- 公开边界:公开仓只 track
docs/01–05(及索引.md等公开入口)。规划目录docs/06-规划/可存在于维护者本地磁盘,但不入公开树(gitignore;与 README /AGENTS.md/ 索引一致)。公开 clone 勿依赖该目录存在。 - 现状目录 = 已落地现状 + 已确认的目标架构蓝图:既写代码已实现的行为/契约/决策理由/约束,也可保留已确认但未落地的目标设计(用 ⏳ 标注未落地部分)——蓝图本身是 01–05 的价值。
- 🗂️ 纯讨论提案不进 01–05:未定稿的提案/草案/讨论记录只放维护者本地的
06-规划;公开现状目录如需提及,只留短说明「详细提案不在公开仓 / 维护者本地」,或链到已公开替代(如 产品路线图摘要),禁止留下指向docs/06-规划/的可点击死链。 - 文档滞后即修正:标 ⏳ 但代码其实已实现 = 文档没更新,就地改写为现状(标 ✅)、留在 01–05,不要迁走。
- 状态标记:🗂️ 仅用于维护者本地规划稿;⏳ 可出现在 01–05,但仅限已确认的目标设计(非提案)。
- 落地即更新:⏳ 项代码落地后,把对应 01–05 段落由 ⏳ 改写为现状。
- 不设归档子目录:
docs/下禁止归档/或同类「已落地副本」目录;变更历史以 git 为准。 - 规划文档落地后(维护者):结论迁入
01–05对应现状文档 → 本地06-规划原文可删,并在本地规划索引「已退役系列」记一行结论去向即可;公开读者以01–05+ 路线图摘要为准。 - 禁止「移入归档保留全文」——若决策理由写不进 01–05,说明尚未真正落地,应留在维护者本地 06 标 ⏳/🗂️,而非归档进公开树。
同步规则
- 必须同步更新:架构变更、接口契约变更、核心依赖变更、数据模型变更。
- 不需更新:纯重构、不改行为的 Bug 修复、样式/文案微调。
- 发现不准确:立即暂停 → 指出不一致 → 提议修正 → 等人确认。
生命周期
- 删减处标一个
→ 见代码: {单指针};禁止清单式罗列。 - 被否决方案留一行「方案 + 否决理由」;已撤销决策只留「现状 X、因 Y」。
- 方案被替代:迁移记录到新文档 → 删旧文档,不留废弃文档。
权威与防回潮
- 一文一权威:同一决策只在一篇写满;他文一句 + 链接。新决策先定权威文,再改
related/ 路线图一行。 - 热区权威(现行):Stop / 姿势 A → 执行引擎;PermissionAxes → 安全;交付验收 / 拦截定案 → 编排器;提示词写什么 → 上下文工程 · 提示词设计原则(How →
prompt-design.mdc);什么信息留在现行通道 → 现行信息;勿增实体 → 定位 §二;BrowserSession → 前端技术 §9.12;断线只读 → 双模式;多 worker/Redis → 部署拓扑 §六。 - frontmatter
status:与文内 ⏳ 正交——landed= 主体已落地;reference= 入口/地图/手册;blueprint= 主体仍是未落地目标设计(少用)。定义见 索引。 - 禁止「远期规划 §x」孤儿引用:公开仓写「详细提案不在公开仓」或链 路线图摘要;代码注释同规,禁硬链
docs/06-规划/。 - 跨文章节指针写「§编号 + 完整章节名」:
pnpm check:doc-sections(CI contracts +release:gate)只校验章节名与目标文## N、名逐字相等的复合指针。缩写成「§五 客户端架构」(真名带「(桌面 + 手机)」)即掉出守卫范围;纯编号「§十二」完全不被守——曾有约 20 处因该文重编号整批失效且长期无人发现。要提高覆盖就把标题写全,别去放宽检查器(放宽即引入误报,噪一次就会被关掉)。§9.12这类决策号不是章节号,本就不在守卫面内。 - 契约变更 PR:必须触权威 docs(本规则「同步规则」);权威不明时先在索引/分区地图补行再改专题。
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 · 68 lines · 0 tokens per session scan A 1b1693e34333
doc-governance is a cursor rule published in the GitHub repository Lawofall/AgentCore (78 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,994 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
project-overview
Core project architecture, patterns, and conventions for the AI Documentation Generator.
code-patterns
Python code style and recurring patterns (config, logging, errors, paths).
cursorrules
You are an AI agent building the module: {{MODULENAME}} This module is part of the Mnemosyne Neural OS ecosystem by XPACEGEMS LLC.
core-project-context
Canonical project context and ownership rules.
backend-python
Python and FastAPI standards for the backend.
dashboard-typescript
React and TypeScript standards for the operator dashboard.