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 rojim666/SztuCode --skill doc-typesetgit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/doc-typeset)<a href="https://agentmods.dev/skills/rojim666/sztucode/doc-typeset"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/doc-typeset/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/rojim666/sztucode/doc-typeset"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/doc-typeset.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 | $0.00127 | $0.05431 |
| Opus 5.5 | $0.00051 | $0.02172 |
| Sonnet 5.5 | $0.00025 | $0.01086 |
| Haiku 4.5 | $0.00013 | $0.00543 |
Grade A, and why
doc-typeset 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 1mo 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 — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
doc-typeset Skill
职责
接收上游 design-token skill 的 token 输出和原始文档内容，输出排版美化的完整 HTML 字符串。
输入契约
interface TypesetInput {
content: string; // 原始文档内容（Markdown 或纯文本）
design_tokens: DesignTokens; // 来自 doc-design-token skill 的 token 对象
genre: string; // 文档类型（如 legal-contract, academic-paper 等）
scene_type?: string; // 可选：场景类型（如 formal, casual）
}
输出契约
interface TypesetOutput {
html: string; // 美化后的完整 HTML 字符串
template_used: string; // 实际使用的模板名称
components_inserted: string[]; // 插入的装饰组件列表
}
模板选择逻辑
- 检查
genre是否命中垂类（legal-contract / academic-paper / government-doc / business-report / meeting-minutes / stock-research / annual-report） - 命中 → 加载
prompts/{genre}.md（排版 prompt）+templates/{genre}.html（HTML 骨架） - 未命中 → 加载
prompts/base.md+templates/base.html
渐进加载：只在实际需要时读取对应的 prompt 和 template 文件，不要预先加载所有文件。
装饰组件使用指南
| 组件 | 用途 | 触发条件 |
|---|---|---|
callout |
重要提示、警告、危险信息 | 内容含"注意""警告""重要""严禁"等关键词 |
divider |
章节分隔 | 主要章节之间，或文档需要视觉分隔时 |
section-marker |
编号章节标题 | 有序章节，需突出层级时 |
data-card |
数据/指标展示 | 表格含 KPI、评级、统计数据时 |
页面模型规范：语义 Section + CSS @page
自 S-26060126E 起，封面页 / 分节 / 横向页 / 页眉页脚页码 统一由「语义
<section role>+ CSS@page」表达。这是生成 HTML 时表达"分页结构"的唯一方式。
(a) 语义分节 <section>
<body> 下的顶层 <section> 按 DOM 顺序映射为独立 docx 节（节边界自动插 nextPage 分节符）。无 <section> 时按单节处理。
<body>
<section role="cover"> … </section> <!-- 封面节 -->
<section role="body" data-page-restart="1"> … </section> <!-- 正文，页码从 1 重起 -->
<section role="financials" data-orientation="landscape"> … </section> <!-- 横向节（财务报表） -->
</body>
| 属性 | 说明 | 默认 |
|---|---|---|
role |
开放字符串；用于 section[role=X]{page:Y} 命名页绑定 |
无 |
data-orientation |
portrait / landscape（横向 = 取文档尺寸交换宽高，取代旧 section-break landscape） |
文档默认 |
data-margin-top/bottom/left/right |
该节页边距（cm），按属性合并，未设项回落文档默认 | 文档默认 |
data-page-restart |
该节页码起始值（写入 pgNumType@w:start） |
不重起 |
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.
- 1mo ago First seen · 406 lines · 127 tokens per session scan A 8e8b7c4270bd
doc-typeset is a skill published in the GitHub repository rojim666/SztuCode (109 stars, last pushed 4d ago), licensed MIT. It adds 127 tokens to every session and 5,431 once invoked, about $0.0005 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 2026-09-12.
Other skills, from other repositories
creative-popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
rebuild-package-diagrams
Render a reverse-spec rebuild package as traced, script-checked visuals — a Mermaid ER diagram of model.md entities, capability use cases as BPMN processes, and one browsable HTML catalog. Use on "ER diagram from the entities", "draw the data model", "use cases as BPMN", "browsable HTML of the rebuild package", "ER…
slides
Create, revise, review, and export native, editable PowerPoint decks from PPTD source in the main conversation.
design-skill
Use BEFORE building or restyling anything a user will see — web/mobile UIs, landing pages, dashboards, components, emails, AND creative work like Three.js/WebGL/canvas/SVG scenes, data-viz, games, and animations — to make it look intentional and polished, not generic; covers tokens, type, color, layout, motion…