What is llm-wiki CLAUDE.md?

Project instructions for an LLM wiki, a knowledge base maintained from collected articles, papers, notes, and other raw sources. It defines separate folders for unchanged sources, the maintained wiki, and generated reports.

Use it to structure a personal research wiki, store source files, maintain topic and entity pages, record changes, and produce answers or reports from the collected material.

It prevents original source material from being changed and gives the system clear rules for organizing and updating knowledge.

How mduongvandinh/llm-wiki configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mduongvandinh/llm-wiki. 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/mduongvandinh/llm-wiki/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mduongvandinh/llm-wiki

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mduongvandinh/llm-wiki/claude-md/github.svg)](https://agentmods.dev/instructions/mduongvandinh/llm-wiki/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mduongvandinh/llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/mduongvandinh/llm-wiki/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mduongvandinh/llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/mduongvandinh/llm-wiki/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,189 This file is loaded in full into every session.

When invoked 2,189 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.

Model	Per session	Once invoked
Fable 5.1	$0.02189	$0.02189
Opus 5	$0.01094	$0.01094
Sonnet 5	$0.00438	$0.00438
Haiku 4.5	$0.00219	$0.00219

Measured 11d ago against content hash 72d31d498f7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

llm-wiki 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 11d 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 · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Wiki — Schema & Quy tắc vận hành

Hệ thống knowledge base cá nhân dựa trên pattern của Andrej Karpathy. LLM xây dựng và duy trì wiki từ nguồn thô. Con người chỉ đọc wiki và hỏi đáp.

Kiến trúc 3 lớp

raw/        → Nguồn thô (bất biến — LLM CHỈ ĐỌC, KHÔNG BAO GIỜ SỬA)
wiki/       → Wiki do LLM viết & duy trì hoàn toàn
outputs/    → Kết quả query, reports, phân tích
config.yaml → Cấu hình topics, feeds, lịch chạy

Cấu trúc thư mục

llm-wiki/
├── CLAUDE.md              ← File này — schema & quy tắc
├── config.yaml            ← Cấu hình hệ thống
├── raw/                   ← Nguồn thô (KHÔNG ĐƯỢC SỬA)
│   ├── articles/          ← Web articles (markdown, text)
│   ├── papers/            ← PDF, research papers
│   ├── notes/             ← Ghi chú cá nhân
│   ├── media/             ← Screenshots, diagrams
│   └── assets/            ← Downloaded images từ articles
├── wiki/                  ← LLM sở hữu toàn bộ
│   ├── INDEX.md           ← Catalog mọi trang wiki
│   ├── LOG.md             ← Timeline sự kiện
│   ├── entities/          ← Người, tổ chức, tool, project
│   ├── concepts/          ← Khái niệm, pattern, methodology
│   ├── sources/           ← Summary từng raw source
│   └── syntheses/         ← Phân tích tổng hợp, so sánh
├── outputs/               ← Kết quả query & reports
└── .discoveries/          ← Metadata cho auto-discovery
    ├── feeds.json         ← Nguồn đang theo dõi
    ├── gaps.json          ← Knowledge gaps cần lấp
    └── history.json       ← Nguồn đã xử lý (tránh trùng)

Quy tắc vàng

1. Raw sources là bất biến

KHÔNG BAO GIỜ sửa, xóa, hoặc di chuyển file trong raw/
Đây là source of truth — mọi thứ trong wiki phải truy ngược được về raw

2. Wiki do LLM sở hữu hoàn toàn

Con người KHÔNG sửa wiki bằng tay
LLM tạo, cập nhật, xóa trang wiki
Mỗi thay đổi phải được ghi vào LOG.md

3. Mỗi topic một file

Mỗi entity, concept, source summary là một file .md riêng
File name: kebab-case.md (VD: andrej-karpathy.md, llm-agents.md)
Không tạo file quá dài — tách thành nhiều file nếu > 500 dòng

Read the full file on GitHub · 281 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.

11d ago First seen · 281 lines · 2,189 tokens per session scan A 72d31d498f7f

Subscribe to this mod's changes

llm-wiki CLAUDE.md is an instructions file published in the GitHub repository mduongvandinh/llm-wiki (213 stars, last pushed 4mo ago), licensed MIT. It adds 2,189 tokens to every session, about $0.0109 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.

Andrej Karpathy Claude Code LLM obsidian

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

llm-wiki: Instructions file for Claude Code