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/gyf0311/lorekit/wiki-lintnpx skills add GYF0311/lorekit --skill wiki-lintgit clone --depth 1 https://github.com/GYF0311/lorekitWrote 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/gyf0311/lorekit/wiki-lint)<a href="https://agentmods.dev/skills/gyf0311/lorekit/wiki-lint"><img src="https://agentmods.dev/badge/skills/gyf0311/lorekit/wiki-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 | $0.00060 | $0.01684 |
| Opus 5 | $0.00030 | $0.00842 |
| Sonnet 5 | $0.00012 | $0.00337 |
| Haiku 4.5 | $0.00006 | $0.00168 |
Grade A, and why
wiki-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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-lint
给 corpus 做一次健康检查。只报告，不自动修——任何修改都要用户或后续 skill 明确决定。每条问题必须给出可执行的修复建议。
When to trigger
- 用户说"lint 一下"、"体检"、"检查 corpus"、"看看有没有问题"
- 用户说"知识库最近有啥毛病"、"health check"
wiki-ingest/wiki-fileback写完后的--quick自检- 周期性维护（例如每周一次）
不要触发：
- 用户要写新内容 →
wiki-ingest/wiki-fileback
Decision tree
根据用户意图选模式：
lorekit lint --quick（ingest/fileback 自检用）- v0.4.x 中是默认 lint 的兼容别名，用于避免自检命令参数漂移
lorekit lint（默认 / 用户显式触发）——CLI 实际检查项见下节- 工作台清理 → 交给
wiki-triageskill（on-demand 清算账单），不在 lint 范围
关键原则：lint 输出是 diagnostics 列表，不是 diff。用户点头后才交给相应 skill 处理（拆重复 → wiki-ingest，修断链 → lorekit links(fix/stub/backlog/plain)）。
Tools to use
lorekit lint/lorekit lint --quick— 主命令lorekit doctor— 每日体检（frontmatter / 断链 / 元数据一致性的子集）lorekit search— 验证断链目标lorekit links suggest/fix/stub/backlog/plain— 断链处置闭环（AI 判断选哪种，CLI 执行）；links plained查可重连的降级记录- 底层：Read / Grep
Output format
按严重级别分组输出，每条问题带可执行建议：
=== lorekit lint 报告 ===
corpus: <path>
扫描页数: 342
[ERROR] frontmatter 缺失（2 条）
- 知识库/概念/RAG.md：缺 updated_at
修复：在 frontmatter 补 updated_at: 2026-04-15 22:30
- ...
[WARN] 断链（5 条）
- 知识库/实体/lorekit.md 引用 [[fat skill]]，目标不存在
修复：(a) 新建 知识库/概念/fat skill.md；(b) 改为 [[已有同义页]]；(c) 删除此链接
[WARN] 孤岛（3 条）
- 知识库/实体/李四.md 没有任何反向链接
修复：ingest 一条提到[[李四]]的内容，或评估是否合并
[INFO] 可合并的相似页（2 组）
- 知识库/概念/RAG.md vs 知识库/概念/检索增强生成.md
修复：人工 review 后合并到 RAG.md，把另一篇 redirect
[INFO] 过期（valid_until 已到）（1 条）
- 知识库/实体/求职.md：valid_until 2026-03-31
修复：review 并更新 compiled truth，或延长 valid_until
铁律：
- 只报告，不自动改
- 每条都有具体的修复命令 / 建议
- 报告写进
系统/_CHANGELOG.md（追加一行本次 lint 摘要） - 完整报告写入
corpus/输出/体检报告/lint-YYYY-MM-DD.md（frontmatter 必含graph-excluded: true）
CLI 实际检查项（v0.4.x lorekit lint）
本节与 src/commands/lint.ts 对齐；skills-cli-drift smoke test 防命令漂移，本节防能力描述漂移。
硬性问题（计入失败，exit 1）：
- frontmatter 必填字段：
type/title/slug/created/updated（_工作台/_归档/与入口文档豁免） - 断链：所有
[[...]]指向的目标页必须可解析（共享 resolver，图片嵌入不误报；知识库/模板/占位符豁免） - 孤岛：无任何入链的页面（过渡区 / 模板 /
graph-excluded: true豁免） - workbench-source-link：知识库页把
_工作台/当 source 引用 - unresolved-source：知识库页 frontmatter 的
原料/、知识库/来源引用解析不到真实文件
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 · 116 lines · 60 tokens per session scan A 53fe2b32e95f
wiki-lint is a skill published in the GitHub repository GYF0311/lorekit (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,684 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 2026-08-31.
Other skills, from other repositories
wiki-ingest
Ingest exactly one research paper or source document into an open-llm-wiki vault. Use when the user explicitly asks to add, ingest, process, or publish a paper into the wiki. The workflow parses the source, drafts a source page, runs independent QA, publishes only after the quality gate passes, extracts and normalizes…
openkb-deck-neon
Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷). Generates a polished single-file HTML deck in the Aurora Glass visual direction (near-black…
openkb-deck-editorial
Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content. Generates a polished single-file HTML deck in the Editorial Monocle visual direction (warm cream background, serif type, brick-red accent) — designed to be opened in a browser…
mindbase
Maintain a persistent AI-tended research wiki. Activates when the user wants to ingest a source (PDF, URL, article, paste), capture a thought, build the wiki context, query what's already known, lint for orphans/contradictions, or maintain page conventions. Phrases include "add this to my wiki", "today I decided…"…
wiki-knowledge-agent
Turn chat-pasted text/links into a verified, translated, searchable wiki knowledge base. When a user pastes a link or text (in ANY channel — Discord, Slack, CLI, etc.), fetch+verify it, classify it (useful vs ad), translate+summarize it into the target language, save it to the wiki, and optionally alert on…
wiki-ingest
Digest a course source file into the wiki. This skill should be used when the user says "ingest", "消化", "process this PDF/slide", or drops a course file into raw/ and wants it turned into wiki pages. Reads the source, deduplicates via manifest, creates source + concept pages, and finds cross-course connections.