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 nongjun/feishu-cursor-claw --skill project-docs-managementgit clone --depth 1 https://github.com/nongjun/feishu-cursor-clawWrote 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/nongjun/feishu-cursor-claw/project-docs-management)<a href="https://agentmods.dev/skills/nongjun/feishu-cursor-claw/project-docs-management"><img src="https://agentmods.dev/badge/skills/nongjun/feishu-cursor-claw/project-docs-management.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 5.1 | $0.00080 | $0.01172 |
| Opus 5 | $0.00040 | $0.00586 |
| Sonnet 5 | $0.00016 | $0.00234 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
project-docs-management 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 8d 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
项目结构化知识库初始化
本技能仅用于首次搭建。知识库建好后的所有维护（巡检、整理散乱文档、审计模块旧文档）统一由
doc-gardener技能负责。
核心理念
给 Agent 一张地图，而不是一本说明书。
- 渐进式披露：
AGENTS.md是 Cursor 原生 AI 入口文件（≤250行），指向文档/深层文档 - 不在仓库里 = 不存在：把隐性知识搬入仓库
- 为 Agent 可读性优化：文档不含示例代码，充分信任大模型
命名规范
一切使用中文命名：文件、目录、导航文档、架构文档全部中文，.md 格式。
知识库目录结构
项目根目录/
├── AGENTS.md # Cursor 原生 AI 入口文件（≤250行）
├── 架构.md # 项目鸟瞰图
├── 文档/ # 结构化知识库（唯一真相源）
│ ├── 设计文档/ # 标注验证状态
│ ├── 核心信念/ # 团队工程原则与长期规范
│ ├── 执行计划/
│ │ ├── 进行中/
│ │ ├── 已完成/
│ │ └── 技术债务/
│ ├── 产品规格/
│ ├── 参考资料/
│ ├── 质量评分/
│ ├── 凭据与配置/ # 开发阶段直接记录明文
│ └── 变更日志/
AGENTS.md 编写规则
Cursor 原生文件，AI 助手启动时自动读取，是 AI 理解项目的唯一入口。
严格 ≤250 行。必含：项目概述、技术栈、知识库索引、目录结构、标准模块结构、核心编码规范、部署约束、凭据位置。 禁止放入：详细 API 文档、完整部署步骤、数据库 Schema、冗长示例代码。
架构.md 编写规则
必含：业务域划分、代码包分层、模块依赖关系、部署拓扑（容器/端口/域名）、数据存储。
文档分类规则
- 设计文档：开头必须标注
验证状态: ✅已验证 | ⚠️部分验证 | ❌未验证 | 🚧设计中 - 核心信念：不随任务变化的长期约定
- 执行计划：复杂任务签入
进行中/，完成移至已完成/，技术债务单独记录 - 质量评分：各模块成熟度（⭐~⭐⭐⭐⭐⭐）、改动风险
- 凭据与配置：Token/密码/API Key 集中明文记录
- 变更日志：跨模块的重大变更
初始化工作流（使用子 agent 并行）
必须使用 Task 工具启动子 agent 并行处理，不指定 model 参数（继承父级模型）。
阶段1：搭建结构 + 扫描现有文档（并行）
同时启动 2 个子 agent：
| 子 agent | 任务 |
|---|---|
| agent-A | 创建 文档/ 完整目录结构（含所有子目录） |
| agent-B | 递归扫描项目下所有 .md 文件，生成完整文档清单（路径、大小、修改时间、初步分类） |
阶段2：编写核心文档 + 分类现有文档（并行）
根据扫描结果，启动 3-4 个子 agent：
| 子 agent | 任务 |
|---|---|
| agent-C | 编写 架构.md（读取代码结构、docker-compose、nginx配置） |
| agent-D | 编写 AGENTS.md（基于架构.md和文档/结构，含知识库索引+编码规范+模块结构模板） |
| agent-E | 将系统级文档迁移到 文档/ 对应子目录 |
| agent-F | 整合凭据信息（读取 .env、credentials 文件，生成凭据总览） |
阶段3：收尾
- 为设计文档补验证状态头部
- 建立初始质量评分
- 生成初始化审计报告存入
文档/变更日志/ - 备份原始文档目录
详细参考
- 各类文档完整模板，见 reference.md
- 基于瑞小美AiOS项目的实际示例，见 examples.md
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 97 lines · 80 tokens per session scan A 658f076b2652
project-docs-management is a skill published in the GitHub repository nongjun/feishu-cursor-claw (14 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,172 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
metabot
Unified MetaBot CLI for personal Memory, Skill Hub, durable Agent Bus messaging, agent registry, Agent Teams, T5T, scheduling, and bridge runtime operations.
docs-adr
Create and maintain lightweight Architecture Decision Records as agent-readable decision memory — what was decided, why, and which alternatives were rejected. Use when "record this decision", "set up ADRs", "the agent keeps suggesting Y again". Docs vs code drift → plan-docs-sync. Session state → handoff.
docs-domain-modeling
Build and sharpen a project's domain model — a CONTEXT.md glossary and ubiquitous language. Use when pinning down terminology, or the agent "uses the wrong words". Repo decision-memory system (INDEX.md, rejected alternatives) → docs-adr.
checkpoint
Save a session checkpoint — what was done, what's next, any blockers.
note
Quick note — save a decision, observation, or thought to persistent memory.
resume
Resume from last checkpoint — load full context and continue where you left off.