ClaudeLearning: Instructions file for Claude Code

CLAUDE.md

ClaudeLearning CLAUDE.md is an instructions file for Claude Code from zsutxz/ClaudeLearning. It costs 1,534 tokens per session, scanned A, original, MIT.

A set of project instructions for Claude Code, an AI coding assistant, in a multi-project repository. It defines communication language, Git rules, project structure, setup commands, and details about several Python AI-agent projects.

In plain words
What is it for?
Use it to guide Claude Code while working on the repository’s Python AI-agent projects, their dependencies, commands, imports, configuration, and Git workflow.
Why use it?
It gives the coding assistant repository-specific context, such as which directory to use and how projects are organized. It also prevents automatic commits and sets the required communication language.

Instructions file for Claude Code

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

This is zsutxz/ClaudeLearning's own configuration. It tells Claude Code how to work on ClaudeLearning 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 ClaudeLearning configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zsutxz/ClaudeLearning. 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/zsutxz/ClaudeLearning/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zsutxz/ClaudeLearning

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 ClaudeLearning CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zsutxz/claudelearning/claude-md/github.svg)](https://agentmods.dev/instructions/zsutxz/claudelearning/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zsutxz/claudelearning/claude-md"><img src="https://agentmods.dev/badge/instructions/zsutxz/claudelearning/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.

agentmods 80×15 button for ClaudeLearning CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zsutxz/claudelearning/claude-md"><img src="https://agentmods.dev/badge/instructions/zsutxz/claudelearning/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,534 This file is loaded in full into every session.
When invoked 1,534 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 $0.01534 $0.01534
Opus 5 $0.00767 $0.00767
Sonnet 5 $0.00307 $0.00307
Haiku 4.5 $0.00153 $0.00153

Measured 8d ago against content hash 41ae7c065d45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ClaudeLearning 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 · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 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.

语言和Git规则

  • 语言:使用中文进行交流
  • Git规则:不自动提交任何代码更改,手动提交前需要明确确认

Project Overview

多项目技术试验仓库,包含独立的子项目。每个子项目有自己的依赖和运行方式,必须在各自目录下运行(导入路径依赖)。

子项目

AgentSdkTest — 多模型AI代理框架

Python 3.10+ 项目,提供统一的AI代理接口,支持 Claude(智谱AI)/OpenAI/DeepSeek/Ollama 多模型切换。

核心架构:UniversalAIAgent(基类)→ UniversalTaskAgent / UniversalCodeAgent / UniversalTalkAgent,通过 provider 参数切换模型。工厂模式在 lib/factory.py,基类与子类在 lib/multi_agent.py

cd AgentSdkTest
pip install -r requirements.txt           # 安装依赖
python quick_start.py                      # 交互式菜单(主入口,推荐)
python run_all_examples.py                 # 运行所有示例

环境变量配置在 config/.env,加载优先级:config/.env > .env。API密钥格式为智谱AI(id.secret)。

导入路径:必须在 AgentSdkTest 目录下运行,使用 from lib.multi_agent import UniversalAIAgent。AgentSdkTest 有独立的 .mcp.json

Research — 技术调研代理

继承 UniversalTaskAgent,添加文献检索、数据处理、报告生成、质量检查模块(modules/literature_retrieverdata_processorreport_generatorquality_checkertool_manager)。

cd Research
pip install -r requirements.txt
python example_usage.py                    # 运行示例
pytest test/                               # 运行测试(test_research_agent.py)

所有方法都是异步的,需要 asyncio.run() 调用。Research 自动将 AgentSdkTest 添加到 sys.pathfrom lib.multi_agent import UniversalTaskAgent)。Research/reports/ 已在 .gitignore 排除。

Prompt/ — 提示词模板集合

中文提示词模板(Gemini、翻译、排版、打分器等),纯 Markdown 文本。

_bmad/ — BMAD 企业框架(当前 v6.10.0,bmb v2.1.0)

BMAD 工作流通过 Claude Code 技能系统调用,模块在 _bmad/bmb(Builder)与 _bmad/bmm(Model)。配置 _bmad/config.toml / config.user.toml 由 installer 管理勿手改,持久定制放 _bmad/custom/。技能以 bmad-* 前缀调用(如 bmad-prdbmad-agent-pmbmad-architecture)。产物输出到 _bmad-output/

升级(在项目根、非交互执行):

npx bmad-method@latest install --action quick-update --directory . --yes            # 同版本快速更新(保留 custom/)
npx bmad-method@latest install --action update --pin bmb=<tag> --directory . --yes   # 跨版本 / 改 external 模块 pin

注意:交互 prompt 在非 TTY(脚本)下会卡住,须显式 --directory + --yesquick-update 不跨版本,update/install 才重新解析 external;--action update 会用系统用户名覆盖 user_name,需在 _bmad/custom/config.user.toml 持久化保护。

Read the full file on GitHub · 97 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 · 97 lines · 1,534 tokens per session scan A 41ae7c065d45

Subscribe to this mod's changes

ClaudeLearning CLAUDE.md is an instructions file published in the GitHub repository zsutxz/ClaudeLearning (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,534 tokens to every session, about $0.0077 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 2026-09-03.

Related

Other instructions, from other repositories

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 · 7,126 tokens

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

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

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