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 skills/ryanzhao1011/workframe/document-normsnpx skills add ryanzhao1011/workframe --skill document-normsgit clone --depth 1 https://github.com/ryanzhao1011/workframeWrote 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/ryanzhao1011/workframe/document-norms)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/document-norms"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/document-norms.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 | $0.00119 | $0.12499 |
| Opus 5 | $0.00060 | $0.06249 |
| Sonnet 5 | $0.00024 | $0.02500 |
| Haiku 4.5 | $0.00012 | $0.01250 |
Grade B, and why
document-norms scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- 损坏报警时手动跑 `python "$(cat .claude/workframe-state/plugin-root.txt)/scripts/check-stale-modules.py" rebuild-index` 全量重建 How it starts
The opening of the file, as written. The whole thing — 757 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Norms 文档规范 Skill
定位
本 skill 是 modules/ 体系下文档写作和管理的单一规范来源，覆盖文档归属、frontmatter、overview、索引、SOP、反模式、写作质量分级 11 个章节。
章节化引用模式：业务 skill（prd-writer / module-init / test-case-design / module-index-refresh / code-to-doc / migrate-to-modules / 其他文档创作 skill）在 SKILL.md 顶部声明前置依赖 skill: document-norms §X §Y，按需读对应章节而非整 skill——本 skill 章节多、篇幅大，整读成本远高于按需读单章。
适用范围：
- modules/ 体系下的项目
- 其他形态项目选用，frontmatter 标准与 obsidian 增强部分通用
不替代：
obsidian-doc-structure/obsidian-link-audit/obsidian-safe-write/obsidian-history-check4 个 obsidian-* skill —— 本 skill 只在 §9 说明何时调用它们- 项目配备的发布 skill（如
feishu-publish）—— 平台 specific 字段由发布 skill 自管
章节索引
| § | 章节 | 主要调用方 |
|---|---|---|
| §1 | 完整文档归属矩阵 | prd-writer / module-init / test-case-design / code-to-doc |
| §2 | frontmatter 字段标准（含 §2.7 updated 时间戳规范） |
prd-writer / module-init / test-case-design / code-to-doc / 任何文档落盘 skill |
| §3 | 三段制 overview.md 通用约定 + 机器维护段边界格式 | module-init / module-index-refresh |
| §4 | 索引层级与同步规则 | module-init / module-index-refresh |
| §5 | 链接与资源引用 | prd-writer / 任何文档创作 skill |
| §6 | 资源位置（prototypes/ assets/ tmp/） | prd-writer |
| §7 | 操作分类（系统维护 vs 实质性产出） | librarian / self-iteration |
| §8 | 修改前/后查漏 SOP（含 L2 obsidian 反链查漏） | 任何文档修改 skill |
| §9 | obsidian 增强（何时调 4 个 obsidian-* skill） | obsidian-link-audit / obsidian-doc-structure |
| §10 | 反模式清单 | 全场景兜底 |
| §11 | 写作质量与精简纪律分级 | 任何文档创作/修改 skill |
§1 完整文档归属矩阵
1.1 modules/ 体系下治理资产层（projects/）归属
| 内容类型 | 归属路径 | type | 创建 skill |
|---|---|---|---|
| 全产品架构总图 | projects/modules/overview.md |
overview |
module-init / module-index-refresh |
| 基础模块导览 | projects/modules/<basic>/overview.md |
overview |
同上 |
| 基础模块 schema | projects/modules/<basic>/module.yaml |
YAML | module-init |
| 跨子模块共享实体 | projects/modules/<basic>/shared/<name>.md |
concept |
手动 |
| 子模块导览 | projects/modules/<basic>/<sub>/overview.md |
overview |
module-init / module-index-refresh |
| 子模块 schema | projects/modules/<basic>/<sub>/submodule.yaml |
YAML | module-init |
| 代码现状（架构） | <sub>/current-state/architecture.md |
current-state |
code-to-doc |
| 代码现状（API） | <sub>/current-state/api-surface.md |
current-state |
code-to-doc |
| 代码现状（数据模型） | <sub>/current-state/data-model.md |
current-state |
code-to-doc |
| 代码现状（代码索引） | <sub>/current-state/code-map.md |
current-state |
code-to-doc |
| 需求清单导览 | <sub>/requirements/overview.md |
overview |
module-init / module-index-refresh |
| 需求 meta | <sub>/requirements/<req_slug>/meta.yaml |
YAML | module-init |
| 需求总览（跨子需求） | <sub>/requirements/<req_slug>/overview.md |
overview |
module-init |
| PRD（按子需求；流程图内嵌其「业务流程与逻辑」章） | <sub>/requirements/<req_slug>/<sub_req_slug>/prd.md |
prd |
prd-writer |
| HTML 原型 | <sub>/requirements/<req_slug>/<sub_req_slug>/prototypes/ |
prototype |
prd-writer |
| 测试用例 | <sub>/requirements/<req_slug>/<sub_req_slug>/test-cases/ |
test-case |
test-case-design |
| 评审与复盘产物（上线复盘 / 代码评审 / 方案评审） | <sub>/requirements/<req_slug>/<sub_req_slug>/reviews/ |
review |
手动 |
| 草稿需求（未立项） | <sub>/requirements/_draft/<slug>.md |
concept |
手动 |
| 子模块决策记录 ADR | <sub>/decisions/<YYYY-MM-DD>-<title>.md |
decision |
手动 |
| 子模块调研 | <sub>/research/<topic>.md |
research |
手动 |
| 子模块杂项 | <sub>/others/<name>.md |
concept |
手动 |
| 跨模块技术方案 | projects/specs/plans/<YYYY-MM-DD>-<plan-name>.md |
plan |
手动 |
| 跨模块设计规范 | projects/specs/{design-system,api-conventions,compliance}/ |
concept |
手动 |
| 单模块分析产物（指标 / 反馈 / 竞品） | <sub>/research/{METRICS,FEEDBACK,COMP}-{序号}.md（研究类归 research/，不是 others/——后者是杂项黑洞，见 §10 反模式） |
research |
对应 PM skill |
| 跨模块分析产物（指标体系 / 反馈分析 / 竞品分析） | projects/specs/{METRICS,FEEDBACK,COMP}-{序号}.md |
research / concept |
product-metrics-design / user-feedback-analysis / competitive-analysis |
| Issues | projects/issues/{TYPE}-{seq}.yaml（扁平 + 全局序号；TYPE = BUG / SEC） |
YAML schema（projects/issues/TEMPLATES.md） |
手动 / qa |
| Tasks | projects/board.yaml |
YAML | task-management |
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.
- 4d ago First seen · 757 lines · 119 tokens per session scan B 9ecaa0b2eb01
document-norms is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 17d ago), licensed MIT. It adds 119 tokens to every session and 12,499 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
html-prototype
Generate HTML prototypes (single-file, browser-openable) for product mockups using the user's design system — fonts, color scales, radii, shadows, components, all driven by a tokens.css file. Use when the user asks to make a 原型 / mockup / HTML 设计图 / 设计图给前端 for a PRD module, OR redesign an existing prototype. Output…
feature-acceptance
研发提测后接管浏览器，对照 PRD（必给）+ HTML 原型（自动找）逐项验收线上实现，产出差异清单（实现 / 部分实现 / 未实现 / 与原型或 PRD 不一致）+ 截图证据 + 阻塞问题排序。Use whenever PM 说「验收 XX」「跑一下 XX」「研发提测了」「对一下需求和线上」「点一下 XX 看符不符合需求」「看哪些实现了哪些没做」「上线前 check」「灰度验收」「acceptance」「QA check」，or 给出 PRD 路径 + 线上 URL 让 Claude 走流程。也适用于 PM 想自己点某功能、判断和需求差异时陪她一起跑。区别于 prd skill：本 skill 验证线上现状，不修改 PRD…
prd
Write, rewrite, polish, restructure, or review product requirements documents (PRDs). Use whenever a task touches a 需求文档 / PRD —— 新写、重构、统一口径、补页面结构 / 字段 / 规则 / 边界 / 异常处理、加指标口径定义、按数据看板或某类骨架组织章节，或把讨论 / 会议记录整理成正式产品文档。Trigger even when the user does NOT say "写需求" —— e.g. "把这个加到…
ui-walkthrough
把一份 UI 设计 HTML 和研发上线的页面，同视口、同状态截图比对 + 读 computed style 实锤，产出 UI 还原度差异清单（结构 / 组件 / 颜色 / 字体 / 圆角 / 图标 / 间距 七维，每条标明设计值 vs 线上值）。Use whenever PM 说「UI 走查」「走查一下 UI」「对一下 UI」「UI 还原度」「还原度走查」「线上跟设计稿对一下」「前端还原得对不对」「页面跟这份 HTML 对一下」「UI 验收」「设计还原走查」，或给出 设计 HTML 路径 + 线上 URL 让 Claude 比视觉差异。区别于 feature-acceptance skill：那个验业务逻辑 / 字段 / 操作…
daily-research
Daily research briefing. When the user says "今天的调研""跑一份调研简报""每日调研""今日行业动态""扫一下最近有什么新东西""补一下今天的简报"，或在会话里要求生成 / 补一份当日情报简报时，触发本 skill。它在当前会话里实时联网调研用户配置的领域（默认是 AI 应用层 / 框架 / 论文 / 模型 / 研究员与厂商落地动态），产出一份中文简报写入 /YYYY-MM-DD.md。即使用户没说"用 skill"、只说"今天调研呢""帮我看下今天有什么进展"也要触发。本 skill 只生成简报，不自动归档。.
competitor-research
建/补 竞品与 AI 调研文档时遵循。覆盖 AI 应用 / 行业产品现状（竞品库）、Agent 模块汇总与框架深挖（研究库）。规定按菜单梳理全部功能、无账号用帮助中心反推菜单、功能截图只用真实 UI 图、标题与排版口径、主题分流与增量。Use when 写竞品现状 / AI 应用产品文档 / 模块汇总 / 框架对比 / 调研沉淀。.