llm-wiki-web: Instructions file for Claude Code

CLAUDE.md

llm-wiki-web CLAUDE.md is an instructions file for Claude Code from stevenflyai/llm-wiki-web. It costs 1,681 tokens per session, scanned A, original, MIT.

A project instruction file for an LLM-driven personal knowledge base, where an AI agent turns source material into organised Wiki pages. It defines the project structure, startup reading order, and writing rules.

In plain words
What is it for?
Use it in the LLM Wiki project to guide agents working with papers, articles, repository notes, images, Wiki categories, indexes, logs, queries, and generated outputs.
Why use it?
It gives coding agents consistent project context before they edit or generate files. This reduces misplaced content, outdated indexes, and inconsistent handling of raw sources and generated pages.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is stevenflyai/llm-wiki-web's own configuration. It tells Claude Code how to work on llm-wiki-web itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-wiki-web configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/stevenflyai/llm-wiki-web/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/stevenflyai/llm-wiki-web

Made for: Claude Code.

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.

agentmods badge for llm-wiki-web CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stevenflyai/llm-wiki-web/claude-md.svg)](https://agentmods.dev/instructions/stevenflyai/llm-wiki-web/claude-md)
Your own site
<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>
Per session 1,681 This file is loaded in full into every session.
When invoked 1,681 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash ed4b0dc93279, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

CLAUDE.md · 187 lines

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:

  1. 读取本文件 (CLAUDE.md) — 了解项目规则
  2. 读取 wiki/INDEX.md — 了解现有知识库内容
  3. 读取 wiki/LOG.md — 了解最近的变更历史
  4. 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:

  1. 读取 raw/ 下所有未处理的文件(检查 _meta/compile_state.json
  2. 对每个新文件:提取关键概念,更新或创建对应的 wiki 文章
  3. 更新 wiki/INDEX.md 中的条目
  4. wiki/LOG.md 中记录本次编译
  5. 更新 _meta/compile_state.json

Read the full file on GitHub · 187 lines

Changes

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.

  1. 8d ago First seen · 187 lines · 1,681 tokens per session scan A ed4b0dc93279

Subscribe to this mod's changes

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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens