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 AIGNE-io/doc-smith-skills --skill doc-smith-buildgit clone --depth 1 https://github.com/AIGNE-io/doc-smith-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/aigne-io/doc-smith-skills/doc-smith-build)<a href="https://agentmods.dev/skills/aigne-io/doc-smith-skills/doc-smith-build"><img src="https://agentmods.dev/badge/skills/aigne-io/doc-smith-skills/doc-smith-build/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/aigne-io/doc-smith-skills/doc-smith-build"><img src="https://agentmods.dev/badge/skills/aigne-io/doc-smith-skills/doc-smith-build.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 | $0.00035 | $0.01153 |
| Opus 5.5 | $0.00014 | $0.00461 |
| Sonnet 5.5 | $0.00007 | $0.00231 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
doc-smith-build 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 2mo 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc-Smith HTML 构建
双模式构建:--nav 生成导航和静态资源,--doc 构建单篇文档。
用法
# 生成 nav.js + 复制资源 + 创建重定向
node skills/doc-smith-build/scripts/build.mjs \
--nav --workspace .aigne/doc-smith --output .aigne/doc-smith/dist
# 构建单篇文档
node skills/doc-smith-build/scripts/build.mjs \
--doc .aigne/doc-smith/docs/overview/zh.md --path /overview \
--workspace .aigne/doc-smith --output .aigne/doc-smith/dist
选项
| Option | Alias | Description |
|---|---|---|
--nav |
生成 nav.js、复制 CSS、创建重定向页面 | |
--doc <file> |
构建单篇 MD 文件为 HTML | |
--path <path> |
文档路径(如 /overview),--doc 模式必需 |
|
--workspace <path> |
-w |
Doc-Smith workspace(默认 .aigne/doc-smith) |
--output <path> |
-o |
输出目录(默认 <workspace>/dist) |
模式说明
--nav 模式
从 document-structure.yaml + config.yaml 生成导航数据和静态资源。
输出:
assets/nav.js— 导航数据(window.__DS_NAV__ = {...}),侧边栏和语言切换由此驱动assets/docsmith.css— 内置基础样式assets/theme.css— 用户主题(不存在时创建空文件)index.html— 根重定向{lang}/index.html— 语言重定向
调用时机: 初始化时、文档结构变更后。
--doc 模式
构建单篇 MD 文件为完整 HTML 页面。
输入: MD 文件路径 + 文档 path
输出: dist/{lang}/docs/{path}.html
职责:
- Markdown → HTML 转换(markdown-it)
- 套 HTML 骨架(data-ds 锚点)
- 生成 TOC(页面内联)
- 处理图片占位符(
<!-- afs:image ... -->) /assets/路径转换为相对路径(见下方路径契约)- 拼接静态资源引用(CSS + nav.js)
不负责: 导航渲染(nav.js 客户端完成)、MD 清理(调用方负责)。
路径契约
MD 文件中使用 /assets/ 绝对路径引用资源,build.mjs 自动转换为相对路径:
| MD 中写法 | HTML 输出(depth=1) | HTML 输出(depth=2) |
|---|---|---|
 |
../../assets/logo.png |
../../../assets/logo.png |
- 路径包含
..的视为非法,不转换(防遍历攻击) - 旧格式
../../assets/仍由已有逻辑处理(向后兼容) - 外部 URL 不受影响
导航架构
侧边栏和语言切换由 nav.js 在客户端渲染:
- 使用
<script src>加载(兼容file://和http://协议) - 更新文档结构只需重新生成 nav.js,无需重建所有 HTML 页面
- TOC 仍在构建时内联生成(页面特有内容)
错误处理
| 错误类型 | 处理方式 |
|---|---|
| workspace 不存在 | 报告明确错误 |
| document-structure.yaml 缺失 | 报告明确错误 |
| MD 文件不存在 | 报告明确错误 |
--doc 缺少 --path |
报告明确错误 |
| 依赖未安装 | 在 scripts 目录执行 npm install |
What ships with it
4 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.
- 2mo ago First seen · 123 lines · 35 tokens per session scan A 56e2be14e6d6
doc-smith-build is a skill published in the GitHub repository AIGNE-io/doc-smith-skills (9 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,153 once invoked, about $0.0001 per session on Opus 5.5. 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.
doc-smith-build compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| doc-smith-buildAIGNE-io/doc-smith-skills | Skill | 9 | 7mo ago | Apache-2.0 | A | 35 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| apify-youtube-transcript-scrapersickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 48 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| ppt-reviewOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 2 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |