Borrowing it
Nothing to install: this file belongs to stevenflyai/llm-wiki-web. 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/stevenflyai/llm-wiki-web/main/CLAUDE.mdgit clone --depth 1 https://github.com/stevenflyai/llm-wiki-webWrote 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/stevenflyai/llm-wiki-web/claude-md)<a href="https://agentmods.dev/instructions/stevenflyai/llm-wiki-web/claude-md"><img src="https://agentmods.dev/badge/instructions/stevenflyai/llm-wiki-web/claude-md.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 | $0.01681 | $0.01681 |
| Opus 5 | $0.00840 | $0.00840 |
| Sonnet 5 | $0.00336 | $0.00336 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
llm-wiki-web 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 8d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki 项目配置文件 (CLAUDE.md / AGENTS.md)
本文件是 Karpathy LLM Wiki 模式的核心配置,供 Claude Code / Codex 等 LLM Agent 读取。 每次启动新会话时,请先阅读此文件,然后阅读
wiki/INDEX.md。
项目概述
本项目是一个 LLM 驱动的个人知识库,灵感来自 Andrej Karpathy 的 LLM Knowledge Base 模式。
核心理念:
- LLM 作为"编译器",将原始资料(
raw/)编译成结构化的 Wiki(wiki/) - Wiki 是"活的"知识库,会不断更新和自我修复
- 使用 Obsidian 作为前端界面,方便浏览和导航
目录结构
llm-wiki/
├── CLAUDE.md # 本文件:项目配置与规则(Agent 必读)
├── raw/ # 原始资料(人工添加,不由 LLM 编辑)
│ ├── papers/ # 学术论文(.pdf 或转换后的 .md)
│ ├── articles/ # 文章、博客(.md)
│ ├── repos/ # 代码仓库笔记(.md)
│ └── images/ # 图片资源
├── wiki/ # LLM 编译生成的结构化 Wiki(主要由 LLM 维护)
│ ├── INDEX.md # 所有 Wiki 文章的主索引(必须保持最新)
│ ├── LOG.md # Wiki 演化日志(记录每次重要操作)
│ ├── concepts/ # 核心概念文章
│ ├── tools/ # 工具和框架文章
│ ├── research/ # 研究进展文章
│ └── tutorials/ # 教程和实践指南
├── output/ # 查询结果、幻灯片、图表(临时输出)
│ ├── queries/ # Q&A 查询结果
│ ├── slides/ # Marp 幻灯片
│ └── charts/ # Matplotlib 图表
├── _meta/ # 元数据、编译状态
│ └── compile_state.json
└── scripts/ # 辅助脚本
├── compile.py # 编译脚本
├── query.py # 查询脚本
└── lint.py # 健康检查脚本
会话启动协议
每次开始新会话时,按以下顺序操作:
- 读取本文件 (
CLAUDE.md) — 了解项目规则 - 读取
wiki/INDEX.md— 了解现有知识库内容 - 读取
wiki/LOG.md— 了解最近的变更历史 - 确认任务 — 根据用户指令执行相应操作
Wiki 文章规范
文章结构模板
每篇 Wiki 文章必须遵循以下格式:
# [文章标题]
**类别**: [concepts/tools/research/tutorials]
**最后更新**: YYYY-MM-DD
**相关文章**: [[文章A]], [[文章B]]
**原始来源**: [来源文件名或URL]
---
## 概述
[2-3句话的简明摘要]
## 核心内容
[详细内容,使用小节组织]
### 子节1
...
### 子节2
...
## 关键要点
- 要点1
- 要点2
- 要点3
## 延伸阅读
- [[相关文章1]]
- [[相关文章2]]
## 原始来源引用
- `raw/papers/xxx.md` — 第X页
- `raw/articles/xxx.md`
反向链接规范
使用 Obsidian 双链格式 [[文章名]] 进行内部链接。
每篇文章的"相关文章"字段必须保持最新。
操作命令
编译操作 (Compile)
触发词: "编译"、"compile"、"更新 wiki" 操作:
- 读取
raw/下所有未处理的文件(检查_meta/compile_state.json) - 对每个新文件:提取关键概念,更新或创建对应的 wiki 文章
- 更新
wiki/INDEX.md中的条目 - 在
wiki/LOG.md中记录本次编译 - 更新
_meta/compile_state.json
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.
- 8d ago First seen · 187 lines · 1,681 tokens per session scan A ed4b0dc93279
llm-wiki-web CLAUDE.md is an instructions file published in the GitHub repository stevenflyai/llm-wiki-web (19 stars, last pushed 3mo ago), licensed MIT. It adds 1,681 tokens to every session, about $0.0084 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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.