Borrowing it
Nothing to install: this file belongs to helloianneo/obsidian-ai-second-brain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/helloianneo/obsidian-ai-second-brain/main/CLAUDE.mdgit clone --depth 1 https://github.com/helloianneo/obsidian-ai-second-brainWrote 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/instructions/helloianneo/obsidian-ai-second-brain/claude-md)<a href="https://agentmods.dev/instructions/helloianneo/obsidian-ai-second-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/helloianneo/obsidian-ai-second-brain/claude-md/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/instructions/helloianneo/obsidian-ai-second-brain/claude-md"><img src="https://agentmods.dev/badge/instructions/helloianneo/obsidian-ai-second-brain/claude-md.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 | $0.01215 | $0.01215 |
| Opus 5 | $0.00607 | $0.00607 |
| Sonnet 5 | $0.00243 | $0.00243 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
obsidian-ai-second-brain CLAUDE.md 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 10d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal LLM Wiki
AI 知识管理员的工作手册。把这个文件放在你的 Obsidian vault 根目录。
目录职责
- raw/ — 原始素材，不可变。AI 只读，永不修改。按主题分子目录，允许多级嵌套。PDF/视频/xlsx/图片保持原文件名。
- wiki/ — AI 维护的消化笔记。允许多级子目录。每篇文章 md 格式，命名自由（描述性即可）。
- assets/ — 配图资源。
两个特殊文件（必须维护）
- wiki/index.md — 全局索引。每篇 wiki 文章一行，按主题分组，带链接 + 一句话摘要 + Updated 日期。
- wiki/log.md — Append-only 操作日志，记录每次 ingest / query archive / lint。
三个触发行为
触发 1：Ingest（录入素材）
触发词： "加到 wiki"、"ingest 这个"、"把这个收进来"、给 AI 一份新素材并暗示要保存。
动作：
- 把素材存进
raw/<最合适的主题>/。主题不存在就新建。文件名保持原样（PDF/视频/图片）或起描述性名（md 笔记）。 - 编译成
wiki/<对应主题>/<文章>.md：- 和现有文章是同一核心论点 → 合并进去，更新 Sources 和受影响的小节
- 全新概念 → 新建文章，按概念命名，不按 raw 文件名
- 跨多个主题 → 落在最相关的主题下，在文章末尾加"See Also"交叉引用
- 检查事实冲突：新素材和已有内容矛盾时，在文章里标注分歧和来源归属。
- 级联更新：扫同主题下其他受影响文章，更新它们的 Updated 日期。
- 更新 wiki/index.md：给每篇改动过的文章补/改条目。
- 追加 wiki/log.md：
## [YYYY-MM-DD] ingest | <主文章标题> - Updated: <级联更新的文章标题>
触发 2：Query（查询）
触发词： "我知道啥关于 X"、"wiki 里有没有 Y"、"根据我的 wiki 总结一下 Z"、"对比 A 和 B"。
动作：
- 先读
wiki/index.md定位相关文章。 - 读文章合成答案。优先引用 wiki 内容，其次才用 AI 自己的训练知识。
- 引用时用 markdown 链接：
[文章标题](wiki/主题/文章.md)。 - 默认只在对话里答，不写文件。
例外——用户说"存下来"/"归档到 wiki"：
- 把答案作为新文章写进最相关的
wiki/<主题>/。 - 不合并进已有文章（归档内容是合成答案，不是素材）。
- 更新 index.md，摘要前缀加
[Archived]。 - log.md 追加：
## [YYYY-MM-DD] query | Archived: <页面标题>
触发 3：Lint（体检）
触发词： "lint wiki"、"体检"、"wiki 有啥问题"。
确定性检查（尽量自动修）：
wiki/index.md↔ 实际文件一致性：文件存在但索引缺 → 补条目；索引指向死文件 → 标[MISSING]- wiki 内部 markdown 链接失效：同名文件在别处 → 改路径；找不到 → 报告
- See Also 链接：同主题明显缺的交叉引用 → 补；链接已删文件 → 删
启发式检查（只报告，不自动改）：
- 跨文章事实矛盾
- 新素材让旧论点过时
- 源头分歧没标注
- 孤岛页面（没人引用）
- 跨主题该链没链的概念
- 反复被提及但没独立页面的概念
完成后追加 log.md：
## [YYYY-MM-DD] lint | <N> issues found, <M> auto-fixed
约定
- 所有 wiki 内部链接用相对当前文件的路径。
- 对话里引用 wiki 文章用相对 vault 根的路径（例如
wiki/主题/xxx.md）。 - 日期用今天的日期。Updated 反映文章内容最后变动的时间，不是文件系统时间戳。
- raw 绝对不能改。如果发现 raw 里有错，在 wiki 文章里标注"source contains error"而不是改 raw。
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.
- 10d ago First seen · 91 lines · 1,215 tokens per session scan A f0d6d6c8c4fc
obsidian-ai-second-brain CLAUDE.md is an instructions file published in the GitHub repository helloianneo/obsidian-ai-second-brain (252 stars, last pushed 4mo ago), licensed MIT. It adds 1,215 tokens to every session, about $0.0061 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.