Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/joyehuang/minimind-notes/claude-mdgit clone --depth 1 https://github.com/joyehuang/minimind-notesWrote 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/joyehuang/minimind-notes/claude-md)<a href="https://agentmods.dev/instructions/joyehuang/minimind-notes/claude-md"><img src="https://agentmods.dev/badge/instructions/joyehuang/minimind-notes/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 | $0.06112 | $0.06112 |
| Opus 5 | $0.03056 | $0.03056 |
| Sonnet 5 | $0.01222 | $0.01222 |
| Haiku 4.5 | $0.00611 | $0.00611 |
Grade A, and why
minimind-notes 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 5d 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 — 722 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Structure
This repository now has a dual-track system:
- Public Teaching Track (
modules/) - Modular教学架构 - Personal Learning Track (
docs/) - 个人学习记录
modules/ - Public Teaching Modules
modules/
├── common/ # Shared utilities
├── 01-foundation/ # Basic components (4 modules)
└── 02-architecture/ # Architecture assembly (2 modules)
Each module contains:
README.md- Module navigationteaching.md- Teaching document (Why/What/How structure)code_guide.md- Source code walkthroughquiz.md- Self-assessment questionsexperiments/- Hands-on experiments
When user learns new content:
- Update personal learning track (
docs/) - If completing a module concept, optionally update/create module in
modules/
docs/ - Personal Learning Track
docs/
├── learning_log.md # Chronological learning record
├── knowledge_base.md # Topic-organized knowledge
└── notes.md # Index and navigation
Learning Notes Maintenance
IMPORTANT: This repository uses a three-tier note system for organized learning:
Note System Structure
minimind/
├── notes.md ← 总索引（entry point）
├── learning_log.md ← 学习日志（chronological）
├── knowledge_base.md ← 知识库（topical）
└── learning_materials/ ← 可执行示例代码
1. notes.md - 总索引
- Purpose: Central index and navigation hub
- Content:
- Links to other documents
- Current progress overview
- Quick reference table
- File structure diagram
- Update: When structure changes or new sections are added
2. learning_log.md - 学习日志
- Purpose: Chronological record of learning journey
- Content:
- Date-stamped entries (format:
### 2025-MM-DD: Topic) - Daily completed tasks (✅ checkbox list)
- Problems encountered and solutions (🐛 section)
- Personal thoughts and reflections (💭 section)
- Learning plans for next session
- Date-stamped entries (format:
- Update: At the end of each learning session
- Format Example:
### 2025-11-07: 深度理解 Transformer 核心组件 #### ✅ 完成事项 - [x] 理解 RMSNorm 原理 - [x] 理解 RoPE 位置编码 #### 💭 个人思考 - **收获**: ... - **疑问解答**: ...
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.
- 5d ago First seen · 722 lines · 6,112 tokens per session scan A b20d2279bc42
minimind-notes CLAUDE.md is an instructions file published in the GitHub repository joyehuang/minimind-notes (177 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 6,112 tokens to every session, about $0.0306 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
quarkus-workshop-langchain4j AGENTS.md
AGENTS.md instructions for quarkusio/quarkus-workshop-langchain4j, covering agents.md, project overview, technology stack, project structure and building and running.
LLM-dev-demo AGENTS.md
Instructions for A3RDLab/LLM-dev-demo, covering agents.md, 仓库性质, 环境与密钥约定, 依赖管理 and 常用命令.
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
mazelingo CLAUDE.md
Instructions for Yeq6X/mazelingo, covering mazelingo, ビルド・開発, 構造 and ルール.
VLA-Handbook AGENTS.md
AGENTS.md instructions for sou350121/VLA-Handbook, covering agents.md, 目标, 仓库快速导航, moltbot 写入协议 and 写入权限矩阵.
VLA-Handbook CLAUDE.md
Claude Code instructions for sou350121/VLA-Handbook, covering claude.md — vla 研究系统 v3, 0. 身份：不是赌注管理者，是你的对手, 1. 核心引擎：三视角对抗思辩（adversarial triad）, 1.1 为什么是三个视角 and 1.2 三视角定义.