Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/chenyuxiaojin/xiaochen-skills/cyxj-obsidian-build)<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-obsidian-build"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-obsidian-build/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/chenyuxiaojin/xiaochen-skills/cyxj-obsidian-build"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-obsidian-build.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 | $0.00107 | $0.02847 |
| Opus 5 | $0.00053 | $0.01424 |
| Sonnet 5 | $0.00021 | $0.00569 |
| Haiku 4.5 | $0.00011 | $0.00285 |
Grade A, and why
cyxj-obsidian-build 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 12d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian 知识库编译器
灵感来源:Andrej Karpathy 的 LLM Wiki 方法论 核心理念:LLM 增量构建并维护一个持久的 Wiki — 一个结构化、互相链接的 Markdown 文件集合。知识编译一次,持续维护,而不是每次查询时重新推导。
定位库(任何操作之前先做)
全文的 $VAULT 指 Obsidian 库的根目录。确认方式:
- 当前工作目录(或用户明确给出的路径)下存在
.obsidian/目录 → 该目录即$VAULT - cwd 不是库(没有
.obsidian/)→ 停下来问用户库路径,不要猜 - 用户给的路径不存在或仍无
.obsidian/→ 终止并报告,不要在错误的目录里建任何东西
「首次运行」的建目录、写 CLAUDE.md 等动作,必须在确认 $VAULT 之后才能执行。
三层架构
Layer 1: Raw Sources(原始资料)— 用户写的,LLM 只读不写
↓ LLM 编译
Layer 2: Wiki(知识层)— LLM 全权维护,用户只读
↑ 规则来自
Layer 3: Schema(配置层)— SKILL.md + $VAULT/CLAUDE.md
Layer 1: Raw Sources(原始资料)
用户的原始笔记。完全不可变 — LLM 读取但绝不修改这些文件。库根 CLAUDE.md 除外(仅首次运行或用户要求时可写,见「权限边界」)。
包括:日记、灵感、收藏的文章、资源笔记等。具体目录结构由 $VAULT/CLAUDE.md 定义。
Layer 2: Wiki(知识层)
LLM 维护的知识产物,存放在 $VAULT/资源库/Wiki/(默认,可在 CLAUDE.md 中自定义)。
Wiki 层包含:
- 概念页 — 工具、人物、方法论的结构化页面
- 合成页 — Query 操作产生的对比分析、总结
- index.md — 按分类组织的内容目录
- log.md — 操作时间线日志
所有跨笔记的链接关系都在 Wiki 页面里维护。原始笔记不需要写任何链接 — Obsidian 的反向链接面板会自动显示哪些 Wiki 页面引用了它。
Layer 3: Schema(配置层)
分两部分:
- 本 SKILL.md — 操作流程、页面模板、权限边界(通用逻辑)
$VAULT/CLAUDE.md— 库专属配置(目录结构、分类体系)
用户在 Obsidian 库目录启动 Claude Code 时,CLAUDE.md 被自动读取。
首次运行
前提:已按「定位库」确认 $VAULT。如果 $VAULT/CLAUDE.md 不存在,先生成它再开始工作:
- 扫描库的顶层目录结构
- 读
${CLAUDE_PLUGIN_ROOT}/skills/cyxj-obsidian-build/templates/vault-claude-md.md,按实际目录调整后生成 CLAUDE.md - 让用户确认或修改后再继续
同时创建 Wiki/index.md 和 Wiki/log.md(格式见
${CLAUDE_PLUGIN_ROOT}/skills/cyxj-obsidian-build/templates/index-and-log.md)。
操作一:Ingest(摄入)
将原始资料编译进 Wiki。一篇资料可能触及 10-15 个 Wiki 页面。
单条摄入
用户指定一篇笔记(或刚添加的新笔记):
- 读取配置:从
$VAULT/CLAUDE.md获取目录结构和分类体系 - 读取资料:用
obsidian-cli read读取指定笔记 - 讨论要点:和用户简要讨论这篇笔记的核心内容和值得提取的概念
- 识别概念:提取笔记中的概念、工具名、人名、方法论
- 匹配 Wiki:对每个概念,用
obsidian-cli search检查是否已有 Wiki 页面- 已有 → 用
obsidian-cli read读取,用obsidian-cli append追加新信息 - 没有 → 用
obsidian-cli create创建新概念页,模板与规则见${CLAUDE_PLUGIN_ROOT}/skills/cyxj-obsidian-build/templates/concept-page.md
- 已有 → 用
- 更新索引:更新
Wiki/index.md,添加新页面条目 - 记录日志:追加到
Wiki/log.md - 汇报结果:告诉用户创建/更新了哪些页面
What ships with it
4 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.
- 12d ago First seen · 228 lines · 107 tokens per session scan A 563c3211a501
cyxj-obsidian-build is a skill published in the GitHub repository chenyuxiaojin/xiaochen-skills (6 stars, last pushed 8d ago), licensed MIT. It adds 107 tokens to every session and 2,847 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
g-resume
Re-hydrate a fresh session with the right slice of the durable record. The read-side counterpart to /g-retro — selectively retrieves the relevant retro, ADRs, journal, and handoff keyed by the current branch/milestone/first-task, and assembles a focused re-entry briefing. Loads distilled context into a clean window…
knowledge-audit
Knowledge base health audit. Scans knowledge docs, analyzes content composition, detects stale references, tiny/oversized files, three-criteria compliance, outputs health report and optimization suggestions.
kn-init
Use at the start of a new session to read project docs, understand context, and see current state.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive-mine
Nightly scan of session transcripts -- extract decisions, tasks, people, insights.
alive-people
Weekly -- cross-reference people mentions, nudge stale contacts.