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 yike-gunshi/forge-skills --skill forge-doc-policygit clone --depth 1 https://github.com/yike-gunshi/forge-skillsWrote 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/yike-gunshi/forge-skills/forge-doc-policy)<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-doc-policy"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-doc-policy/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/yike-gunshi/forge-skills/forge-doc-policy"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-doc-policy.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00140 | $0.01539 |
| Opus 5 | $0.00070 | $0.00770 |
| Sonnet 5 | $0.00028 | $0.00308 |
| Haiku 4.5 | $0.00014 | $0.00154 |
Grade A, and why
forge-doc-policy 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/forge-doc-policy：文档落地治理规范
这是一个规范型 skill，不主动产出代码或文档，作为其他 forge-* skill 和 LLM 自觉行为的当前真相源。
全程中文。
设计目标
解决三层文档治理痛点：
| 层级 | 痛点 | 本 skill 提供 |
|---|---|---|
| 写时约束 | AI 创建文档时落到错位置（forge skill 部分约束 + CLAUDE.md 表不全 + 直接对话完全无约束） | doc-paths.md 三层白名单 + LLM 强校验铁律 |
| 读时索引 | 文档分散，找不到最新信息 | frontmatter-schema.md（索引自动生成脚本规划中，见 CHANGELOG Roadmap） |
| 生命周期 | 不带元数据，分不清活/死文档 | frontmatter-schema.md 必填字段（批量回填脚本规划中，见 CHANGELOG Roadmap） |
文件清单（仅列已实现的文件）
| 文件 | 作用 |
|---|---|
SKILL.md |
本文件，元信息和装载说明 |
doc-paths.md |
当前真相源、模块附录、active 工作区、archive 白名单 |
frontmatter-schema.md |
frontmatter 字段定义（4 必填 + 2 选填） |
claude-md-snippet.md |
项目 CLAUDE.md 复制粘贴的引用段 |
CHANGELOG.md |
版本号 + 演进记录 + 规划中的能力（Roadmap） |
scripts/init-project.sh |
新项目 day 0 一键脚手架（幂等，绝不覆盖） |
规划中但未实现的脚本/模板（audit-project.sh、build-index.sh 等）见 CHANGELOG.md 的 Roadmap 节，不出现在本清单，避免被误引导执行。
装载方式（三选一，按场景）
装载 1：项目 CLAUDE.md 引用（当前主装载，Sprint A）
每个项目的 CLAUDE.md（项目根 / ~/claudecode_workspace/CLAUDE.md）加 3 行引用段，详见 claude-md-snippet.md。
Why：规则源头在本 skill，所有项目通过引用读取，不复制副本。
装载 2：新项目 day 0（✅ 已就绪）
~/.claude/skills/forge-doc-policy/scripts/init-project.sh
在新项目根跑一次：创建 docs/ 标准骨架 + 拷贝 CLAUDE.md 模板 + 配 .gitignore + 生成 docs/README.md。
装载 3：老项目接入（手动方式）
init-project.sh幂等且绝不覆盖已有文件，老项目也可安全跑一遍补齐缺失骨架- frontmatter 缺失、目录偏差人工按
doc-paths.md白名单核对
LLM 强校验铁律（每次创建 .md / 新目录前必须执行）
本段被
claude-md-snippet.md引用，写进每个项目 CLAUDE.md。
- 自查 — 核对目标路径是否在
doc-paths.md的层 1 白名单内 - 违规处理 — 若不在白名单 / 介于多个目录 / 涉及新分类 → 停下问用户（给 2-3 个候选路径）
- 合规处理 — 在白名单内 → 静默写入，不打断用户
- 铁律 — 违反 1-3 的写入即视为 bug，用户报告后 AI 必须立即移动文件 + 在 memory 加 feedback
Why 不上 PreToolUse hook：Hook 误伤会让用户频繁被打断，3 次就会自己关掉，反而失效。LLM 自觉 + 违规才问 = 更友好且对 forge skill 已有约束的补强。（决策渊源见 CHANGELOG）
触发关键词
| 用户说 | 行为 |
|---|---|
| "文档治理" / "forge-doc-policy" | 进入本 skill，按用户具体诉求路由（查白名单 / 装载 / 审计） |
| "文档放哪" / "这个文档应该放哪" | 读 doc-paths.md 给路径建议 |
| "docs 目录乱了" / "想清理文档" | 按 doc-paths.md 白名单人工核对 |
| AI 准备创建任意 .md 或新目录 | 自查 doc-paths.md 三层白名单（LLM 强校验铁律） |
What ships with it
8 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.
- 11d ago First seen · 104 lines · 140 tokens per session scan A 866fcb4de34c
forge-doc-policy is a skill published in the GitHub repository yike-gunshi/forge-skills (13 stars, last pushed 1mo ago), licensed MIT. It adds 140 tokens to every session and 1,539 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 2026-08-30.
Other skills, from other repositories
vastai
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
forge-evolution
Autonomous persona evolution pipeline for failure-driven capability growth.
docs-context
Super Base Context — project doc loader & synchronizer. Triggers even without explicit "load docs"/"sync docs." READ MODE — load architecture/modules/coding/decision docs when work references project state: code work (write/modify/remove); design (features/APIs/schemas/architecture); review (modules, past solutions)…
houtu-dependencies
Skill "houtu-dependencies" from lujiafa/houtu-project-skills, covering houtu framework — ai agent coding guide, core principles, code generation workflow (must be executed in order), step 1 — detect version & dependencies and step 2 — identify scenario & select module.
senzing-entity-resolution
Guides AI agents through Senzing entity resolution workflows using the Senzing MCP server. Covers data mapping to Senzing format, SDK code generation (Python, Java, C#, Rust, TypeScript/Node.js), documentation search, error troubleshooting, sample data access, reporting and visualization, SDK setup guides, and…