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 chenyk2016/kb-metabolism --skill kb-structuregit clone --depth 1 https://github.com/chenyk2016/kb-metabolismWrote 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/chenyk2016/kb-metabolism/kb-structure)<a href="https://agentmods.dev/skills/chenyk2016/kb-metabolism/kb-structure"><img src="https://agentmods.dev/badge/skills/chenyk2016/kb-metabolism/kb-structure.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 | $0.00172 | $0.01290 |
| Opus 5 | $0.00086 | $0.00645 |
| Sonnet 5 | $0.00034 | $0.00258 |
| Haiku 4.5 | $0.00017 | $0.00129 |
Grade A, and why
kb-structure 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 7d 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
kb-structure：目录结构与命名的守门 · 体检 · 整理
先读宪法：库内 90-system/目录规范.md 是唯一真相源（顶层形态、铁律、命名规范、机读参数、当前状态）。本技能只带执行程序；冲突时以库内文档为准——人改规则只改那个文件。宪法放库内而非技能目录，因为它是库的可变状态而非技能的知识：人要在 Obsidian 里看到它，其他工具也要读它，它的修订和库结构变更属于同一个 commit。
库里还没有宪法时：提议从 assets/目录规范.template.md 实例化到库的 90-system/（逐节确认后写入）。用户不建则只做最保守动作（新笔记落 kb captureDir），不移动、不建目录——不凭记忆虚构规则。
设计前提：漂移不可避免（多数写入不经过任何技能）。系统健康取决于发现违规的延迟 × 矫正的成本。kb ≥0.4.0 的 kb_id 让移动不再丢续命信号，矫正已经便宜；本技能把发现做成机器活（审计脚本），把矫正做成审批流。
职能一：守门（用户开口的时刻）
存笔记 → 落宪法"当前状态"节的捕捉区，命名 YYYY-MM-DD-主题.md，零分类（分类摩擦杀捕捉欲）。kb managed 范围优先走 kb_add；仅当用户指定语义位置时按口诀核对落点。
建目录 → 顶层：默认拒绝（封顶见宪法参数），给现有区归属建议；用户坚持则照办。第 3 层起：不建，改 90-system 的 MOC 索引笔记。2 层内：过"行动性问题"（进行中/长期/参考/归档哪类？）。
复制笔记 → 拒绝，按用途给替代：多处可见→双链/MOC；标记重要→提 tier（走 kb 分诊）；备份→git 已在备份。一篇笔记一个路径。
职能二：体检（用户说"检查/体检/整理结构"，或随周消化跑）
node <本技能目录>/scripts/audit.mjs --vault <库根> # --json 出结构化全量
六检：顶层膨胀、深度超限、命名违规、managed 同名笔记（反链错乱源）、assets 孤儿/断链、内容副本。参数读宪法的 kb-structure:params 注释块（顶层上限、深度上限、日期前缀、豁免区）。报告即提案清单——把报告呈给用户，按修复动作分组讲清，等判决。
职能三：整理（人批准后才动手）
- 移动：
git mv 源 目标→ 检查正文assets/相对引用，图片随笔记同迁 - 改名（高危：动 basename 即动 wikilink 解析）：
git mv→ grep 全库[[旧名与](旧路径→ 改写所有引用 → 汇报改写数 - 删除类：永不执行——转交 kb 处决名单流程（AI 提案，人是法官）
- 收尾：
kb index --vault <库根>（kb_id 认亲，信号无损）→ 分批 commit，每批一个
命名速查（完整规则与推导在宪法）
| 规则 | 为什么 |
|---|---|
| basename 全库唯一 | kb 反链按 basename 解析，同名会记账错乱（实现机制的硬约束） |
捕捉笔记 YYYY-MM-DD-主题.md |
时间是捕捉时零摩擦的轴，天然排序与唯一化 |
目录 NN-名称 |
锁定排序 + 可口头寻址 |
中文可用；禁空格与 \:*?"<>| |
人可读优先；跨平台路径安全 |
| assets 每顶层区一个，内容标识命名 | 引用短、同迁便宜、天然免撞名 |
边界
- 移动、删除、顶层建目录永不自作主张——提案给人判决。
- 不改
.kb/config.json、不碰 tier/信号/处决名单（kb-metabolism 主技能领地）。 - 只管装有 kb-metabolism 的库；库外目录有各自的规矩。
What ships with it
2 files 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.
- 7d ago First seen · 52 lines · 172 tokens per session scan A e55997be901d
kb-structure is a skill published in the GitHub repository chenyk2016/kb-metabolism (0 stars, last pushed 26d ago), licensed MIT. It adds 172 tokens to every session and 1,290 once invoked, about $0.0009 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Tasks, Sheets, Docs, and Slides.
anyr
Use when reading, searching, creating, or updating Anytype documents (objects, spaces, types, properties, files, chats) from the command line with the configured anyr CLI, including JSON output patterns for scripting.
Wikimate Link
A note-linking workflow for Obsidian, an app for storing linked Markdown notes. It finds clearly related notes and can group notes on one topic into a table-of-contents note.
feishu
A guide for operating Feishu, a workplace collaboration platform used for messages, documents, tasks, calendars, and groups.
obsidian-knowledge
Use for any knowledge work in an Obsidian vault — capturing a quick note or link, organizing an Inbox, or turning bigger material (PDFs, docx, slides, syllabi, papers, transcripts, URL lists) into structured, teaching-quality notes. Works for any subject, adapts to the vault it's in, and does as much or as little…