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-triagenpx skills add GYF0311/lorekit --skill wiki-triagegit 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-triage)<a href="https://agentmods.dev/skills/gyf0311/lorekit/wiki-triage"><img src="https://agentmods.dev/badge/skills/gyf0311/lorekit/wiki-triage.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 | $0.00091 | $0.01270 |
| Opus 5 | $0.00046 | $0.00635 |
| Sonnet 5 | $0.00018 | $0.00254 |
| Haiku 4.5 | $0.00009 | $0.00127 |
Grade A, and why
wiki-triage 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.
What it actually says
wiki-triage
工作台淤积的定期清算。不挂定时任务，先生说才跑；AI 负责扫描与预判，裁决权永远在先生。
设计原因：入库门 = 先生的明确指令（契约红线），所以内容会合规地停在工作台。 本 skill 是反向流程——把账单递到先生面前，把"裁决 91 条"压缩成"对 4 组说是/否"。
When to trigger
- 先生说"整理一下工作台"、"清算工作台"、"工作台该清了"
- 先生问"工作台堆了什么"、"有什么该入库的"
不要触发：先生只是让你在工作台里找/放某个文件（那是普通文件操作）。
安全红线
- 未勾选前不动任何文件——扫描与账单是只读动作。
- 丢弃一律
lorekit trash，禁止rm；破坏性动作不用&&串联。 原料/、知识库/不在扫描范围；本 skill 只处理_工作台/与复盘候选。- 先生勾选"入库"= 明确入库指令，走完整 wiki-ingest 流程，不走捷径。
Step 1 — 确定性扫描（只读）
lorekit workbench report --json # 默认：账龄 ≥45 天进候选；14 天内动过的目录整体跳过
lorekit workbench report --json --stale-days 30 # 先生指定阈值时调整
CLI 输出四组机械事实：candidates（路径/mtime/账龄/大小）、activeDirs（活跃项目，
已跳过）、excluded（固定排除层：_工作台/转写/、_工作台/日记收件/）、freshFiles。
注意语义：项目目录（用户自建文件夹）14 天内动过整目录跳过；标准过程桶
（收件/草稿/临时/待整理/下载）按单文件判账龄——桶里有新文件不影响老文件进候选。
不要自己写 find 片段重复这份逻辑；CLI 是候选生成的 SSOT。
另扫 fileback 候选堆积：读 输出/复盘/ 最近 2-3 份 synthesis 的
"Suggested fileback candidates" 小节，未消化的候选一并列入账单。
Step 2 — AI 预判分组
对扫描结果逐条判断，分四组（判断是 AI 做，裁决是先生做）：
| 组 | 判断标准 | 建议动作 |
|---|---|---|
| 入库候选 | 完成度高的成稿、含可复用结论 | wiki-ingest（原料落定 → 建页/追加） |
| 归档候选 | 已完结项目的留存资料（面试记录、调研包） | mv 到 _归档/<项目名>/ |
| 丢弃候选 | 明显废稿、过期临时文件、被后续版本取代的旧稿 | lorekit trash |
| 进行中 | 所在目录 14 天内有改动，或先生说过在做 | 不出现在账单，自动跳过 |
拿不准的条目归入"归档候选"并注明存疑，绝不归入丢弃。
Step 3 — 账单（对话内呈现）
按组输出，每条一行：编号 | 文件 | 最后修改 | 一句话理由。
末尾给先生极简回复格式：全部同意 / 1,3 同意，2 归档改留着 / 只做归档组。
Step 4 — 按勾选执行
- 入库：完整走
wiki-ingest（mv 进原料/定稿路径 → frontmatter 记original_path→ 编译/追加知识库/页 → 反链 →lorekit ingest record）。 - 归档：
mv到_归档/<项目名>/，保持原文件名；归档层可被lorekit search --all第二级召回检索到。 - 丢弃：逐条
lorekit trash，不批量串联。 - fileback 候选：勾选的走
wiki-fileback追加 Timeline。
Step 5 — 收尾
lorekit sync（刷新索引 + MEMORY.md 统计 + doctor）lorekit lint确认无新增 hard issue（重点看 unresolved-source）log.md末尾追加一行：## [YYYY-MM-DD HH:mm] triage | 入库 N / 归档 N / 丢弃 N / 跳过 N- 向先生汇报执行结果与 Trash 可恢复提示
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 · 76 lines · 91 tokens per session scan A 49bf8445c5e4
wiki-triage is a skill published in the GitHub repository GYF0311/lorekit (5 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,270 once invoked, about $0.0005 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
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…"…
kb-preferences
Use when user wants to view, update, reset, or audit report preferences stored in vault kb.yaml. Triggers on '/kb-preferences', 'update report prefs', 'change report style', 'my preferences', or when a passive reflection step in another skill needs to propose preference updates.
flashcard-generator
Generate educational flashcards from topics, documents, notes, or study materials. Produces structured JSON data and can create polished Tailwind CSS HTML flashcard review pages with interactive card flipping, progress, tags, and difficulty labels.
manim-animation-maker
Create educational explainer videos with a Manim plus FFmpeg workflow. Use when the user asks for Manim animation, math/physics/geometry/algorithm visualization, formula derivation, concept explainer video, scene planning, MP4 rendering, preview frames, or video quality checks.
bili-note
Turn Bilibili videos that are already registered and parsed in MindSpace, or Bilibili opus/article posts, into evidence-linked Markdown learning notes. Use whenever the user asks to 提取、提炼、总结、整理 B站/Bilibili 视频、课程、动态、图文或专栏，保存学习笔记，结合评论区补充观点，或从已解析视频中查找带时间戳的内容和关键画面。Video tasks require an authorized mediaId from the current…
knowledge-organize
This skill should be used when the user asks to "梳理知识", "整理笔记", "画知识框架", "总结要点", "提炼知识点", "一章总结", "知识清单", "帮我整理这章", "做个知识图谱", "总结重点", "画思维导图", "归纳知识点", "整本书的要点", "帮我提炼考点", or when the user provides textbooks, lecture notes, slides, or documents and wants structured knowledge outlines, key point extraction, chapter…