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 ryanzhao1011/workframe --skill doc-graph-healthgit 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/doc-graph-health)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/doc-graph-health"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/doc-graph-health/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/ryanzhao1011/workframe/doc-graph-health"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/doc-graph-health.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 | $0.00111 | $0.01537 |
| Opus 5 | $0.00056 | $0.00768 |
| Sonnet 5 | $0.00022 | $0.00307 |
| Haiku 4.5 | $0.00011 | $0.00154 |
Grade B, and why
doc-graph-health scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
python "$(cat .claude/workframe-state/plugin-root.txt)/skills/doc-graph-health/scripts/graph_health.py" # 全量巡检 + 覆写报告 How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Graph Health 知识网健康巡检
定位
对应 LLM Wiki 闭环的「Audit 体检」阶段：让知识库能自我发现断链、孤岛、过期与缺口。
事实源分工：检测逻辑与阈值在本 skill scripts/graph_health.py；报告 projects/modules/graph-health.md 由脚本重算，勿手改正文；本 SKILL.md 只管「何时跑、怎么读、如何处置」。
怎么跑
从项目根目录执行（插件根路径由 SessionStart hook 写入 plugin-root.txt，不依赖 PATH）：
python "$(cat .claude/workframe-state/plugin-root.txt)/skills/doc-graph-health/scripts/graph_health.py" # 全量巡检 + 覆写报告
python "$(cat .claude/workframe-state/plugin-root.txt)/skills/doc-graph-health/scripts/graph_health.py" --dry # 只看摘要不写报告
跑完对比上次：git diff -- projects/modules/graph-health.md（收敛趋势比绝对数字重要）。
七项检测与处置
| 检测 | 含义 | 处置 |
|---|---|---|
| 断链 | wikilink / md 链接 / frontmatter related 目标不存在 |
少量直接修；成批查根因（改名未同步等） |
| 孤儿 | 入链=0 的文档（三源计入度；结构性文件已豁免） | 有价值 → 补上级 related / 正文链接；过时 → 归档 projects/archive/；两者都不做时留在报告里可见 |
| Hub | 被引 top10 | 只读参考——横向核心资产，重构/改名时优先评估影响面 |
| stale current-state | 超 45 天未同步 | stub 形态 → 排期 code-to-doc；有内容 → 让 @dev 核对代码后刷新 |
| 姊妹时差 | req overview 落后同 req prd >7 天 | 必须逐对抽读确认：比对 overview 定位段与 prd「变更与决策记录」，确认口径矛盾（如字段列数、规则枚举）→ 修 overview 正文（bump updated）；无矛盾 → 报告中该对会随 overview 下次更新自然消失 |
| updated 缺失/格式错 | 有 frontmatter 但 updated 不可解析——这些文件游离在 stale 判定之外 |
按 document-norms §2.7 补齐（实时 ISO-8601） |
| 概念热点 | 词表词高频提及但未链接 | 织网候选（补 wikilink）或评估是否立跨模块 spec |
概念热点的词表来源（项目自配）
优先级：.workframe-config.json 的 graph_health.hotspot_words（显式覆盖）→ projects/specs/_meta/taxonomy.md「## 能力域」表格（推荐正源：词表随项目 tags 纪律自然生长）→ 两者皆无则跳过本维度并在报告中给启用指引。
报告会标注词表来源与 taxonomy 的 updated 时间——词表停更 = 本维度漏检新概念，看到来源时间明显陈旧时先更新词表再看结论。
排除纪律（与巡检口径一致，勿放宽）
- 基线排除目录：
prototypes/（含 demo 整仓）、node_modules/、.claude/、tmp/、_draft/、assets/；项目可经 configgraph_health.extra_exclude_dirs追加 - 结构性豁免：
current-state/四件套、requirements/overview.md清单页（位置约定即入口，不计孤儿） - 行级噪声：骨架模板的固定 checklist 行会虚增热点计数——把该行的特征子串配进 config
graph_health.noise_line_markers，命中行不计热点
矛盾确认后的修复边界
- 修 overview 正文 = 实质变化 → 实时 bump
updated（document-norms§2.7） - 修完重跑脚本，确认该时差对从报告消失
- 跨 PRD 的口径矛盾（同一规则两处定义打架）超出本 skill 自动能力，发现后走 Issue / board 任务由 owner 处理
What ships with it
1 file 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.
- 9d ago First seen · 78 lines · 111 tokens per session scan B b524ce8c1c8d
doc-graph-health is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 22d ago), licensed MIT. It adds 111 tokens to every session and 1,537 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
latex-setup
Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like "setup latex", "biber vs bibtex", "latex compilation error", "install latex packages", "venue template", or "texlive…
knowledge-structures
A system for organizing notes into navigation pages, synthesis notes, and small standalone notes. A map of content is a note that links together related notes around one topic.
html-prototype
A method for creating single-file HTML mockups that open in a browser and follow a project's design tokens, such as its fonts, colours, spacing, corners, and shadows.
feature-acceptance
A browser-based acceptance testing process that compares an online implementation with a product requirements document and, when available, an HTML prototype. It records what is complete, partial, missing, or inconsistent, with screenshots and prioritized blockers.
prd
A skill for writing and reviewing product requirements documents, or PRDs: documents that describe what a product or feature should do. It covers structure, fields, rules, edge cases, metrics, page layouts, and related system or algorithm flows.
gbg
Convert any plan, PRD, feature idea, or brief into a sequenced goal-by-goal execution document with reviewer-gated commits — for everyday feature development, MVPs, migrations, refactors, and hardening alike. Generates a project brief, per-goal scope/tasks/acceptance criteria, an LLM-reviewer prompt (Codex/etc.), a…