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/lululu811/init-knowledge-base/lintnpx skills add lululu811/init-knowledge-base --skill lintgit clone --depth 1 https://github.com/lululu811/init-knowledge-baseWrote 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/lululu811/init-knowledge-base/lint)<a href="https://agentmods.dev/skills/lululu811/init-knowledge-base/lint"><img src="https://agentmods.dev/badge/skills/lululu811/init-knowledge-base/lint.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 5.1 | $0.00066 | $0.01848 |
| Opus 5 | $0.00033 | $0.00924 |
| Sonnet 5 | $0.00013 | $0.00370 |
| Haiku 4.5 | $0.00007 | $0.00185 |
Grade A, and why
lint 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 5d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lint 技能:知识图谱健康巡检
核心目标
定期运行此 skill,找出知识库长期演进中产生的结构性问题和质量问题。
触发条件
- 用户输入
/lint - 用户询问"我的知识库健康状况如何"
- 用户要求"检查知识库状态"或"检查健康"
巡检流水线
第 1 步:索引一致性检查
- 读取
wiki/index.md全部内容 - 扫描
wiki/下所有.md文件(排除 index.md 和 log.md) - 提取 index.md 中注册的所有双链链接
[[页面名称]] - 比对:找出已注册但文件不存在的条目 OR 文件存在但未注册的页面
第 2 步:双向链接健康检查
- 扫描所有
.md文件,提取所有[[双链]]格式的链接 - 如果链接指向的页面不存在 → 标记为死链
- 统计被引用的页面
- 找出从未被任何其他页面引用的页面 → 孤儿页面
第 3 步:认知冲突审查
- 全局搜索所有
.md文件中包含## 知识冲突的页面 - 提取每个冲突的简要描述
- 统计带未解决冲突的页面
第 4 步:来源可追溯性检查
- 扫描
wiki/下所有带有 frontmatter 的页面 - 检查
sources字段:- 页面类型为
source→ 必须有sources指向 raw/ 文件 - 页面类型为
concept/entity→ 建议有sources - 页面类型为
synthesis→ 必须有多个sources
- 页面类型为
- 标记 来源缺失页面
第 5 步:页面陈旧度检查
- 读取每个页面的
last_updated和created字段 - 计算距今天数:
- 超过 90 天未更新 → 标记为陈旧页面
- 超过 180 天未更新 → 标记为高度陈旧
- 特别关注
status = "draft"且超过 30 天的页面 → 长期草稿
第 6 步:重复内容检测(轻量启发式)
- 提取所有 wiki 页面的标题和正文前 200 字符
- 基于关键词集合计算 Jaccard 相似度:
- 相似度 > 0.8 → 标记为潜在重复
- 标题相似度对比:页面标题的编辑距离 < 3 → 标记为疑似重名
- 报告重复页面组
注意:此检测为轻量启发式,结果仅供参考,需人工判断。
第 7 步:概念空缺检测
- 扫描所有
.md文件,提取所有[[双链]]格式的链接 - 区分两类链接:
- 死链:链接指向的页面完全不存在(已在第 2 步检测)
- 概念空缺:链接指向的页面不存在,但被 多个页面(≥2)引用
- 按被引用次数排序概念空缺:
- 被 ≥5 个页面引用 → 高优先空缺(强烈建议创建)
- 被 3-4 个页面引用 → 中优先空缺
- 被 2 个页面引用 → 低优先空缺
- 报告概念空缺列表,附引用来源
第 8 步:知识质量评分
对每个页面进行快速质量评估:
| 维度 | 标准 | 权重 |
|---|---|---|
| 有定义/摘要 | 页面有"一句话定义"或"核心摘要"区块 | 20% |
| 有双向链接 | 页面至少包含 2 个出站链接 | 20% |
| 有来源 | 页面 sources 字段非空 |
20% |
| 有更新 | 90 天内更新过 | 20% |
| 有结构化内容 | 页面包含 3 个以上标题区块 | 20% |
计算每页得分,标记低质量页面(得分 < 40%)。
报告输出规范
## 🩺 知识库健康体检报告 — YYYY-MM-DD
### 📊 概览统计
| 指标 | 数值 |
|------|------|
| 总页面数 | N |
| 平均质量分 | N% |
| 健康度评级 | 🟢 良好 / 🟡 一般 / 🔴 需关注 |
### ✅ 绿灯项
- [运行良好的项目]
### ⚠️ 黄灯项
- **N 个孤儿页面**: [列表]
- **N 个未同步索引**: [列表]
- **N 个长期草稿**: [列表]
- **N 个陈旧页面**: [列表]
- **N 个来源缺失**: [列表]
### ❌ 红灯项
- **N 个死链**: [来源页面] → [[不存在的目标页面]]
- **N 个未解决的知识冲突**: [页面名称]
- **N 组潜在重复**: [页面 A] ≈ [页面 B] (相似度 X%)
- **N 个低质量页面**: [列表]
### 🔍 概念空缺(被引用但无独立页面)
- **高优先**: [[空缺概念 A]] — 被 5 个页面引用: [[来源1]], [[来源2]], ...
- **中优先**: [[空缺概念 B]] — 被 3 个页面引用: [[来源1]], ...
- **低优先**: [[空缺概念 C]] — 被 2 个页面引用: [[来源1]], [[来源2]]
### 💡 建议研究方向
基于知识库当前状态,以下方向值得进一步探索:
1. **补充来源**: [[PageA]] 仅有 1 个来源,建议寻找更多参考资料
2. **创建空缺页面**: [[空缺概念 A]] 被高频引用,建议尽快创建独立页面
3. **更新陈旧内容**: [[PageB]] 超过 180 天未更新,建议执行 `/refresh` 联网验证
4. **解决冲突**: [[PageC]] 存在未解决的知识冲突,建议核实并更新
5. **深化分析**: [[PageD]] 与 [[PageE]] 存在关联但无综合分析,建议创建 synthesis 页面
### 🛠️ 下一步行动
1. 是否需要自动修复未同步索引?
2. 是否需要针对知识冲突进行重新推演?
3. 是否需要合并/删除重复页面?
4. 是否需要为高优先概念空缺创建页面?
5. 是否需要执行 `/refresh` 更新陈旧页面?
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.
- 5d ago First seen · 145 lines · 66 tokens per session scan A a4cccf557bda
lint is a skill published in the GitHub repository lululu811/init-knowledge-base (23 stars, last pushed 21d ago), licensed MIT. It adds 66 tokens to every session and 1,848 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…