abc/analysis_claude_code
1
0
Fork 0
mirror of https://github.com/shareAI-lab/analysis_claude_code.git synced 2026-02-04 13:16:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: enhance README with learning path, badges, and better structure

Browse Source 
README improvements:
- Add Python/Tests/License badges for credibility
- Add "What You'll Learn" section with clear outcomes
- Add visual learning path diagram (v0 -> v4 progression)
- Add recommended learning approach
- Add version comparison table with tools/insights
- Add skills system documentation with table
- Add configuration section
- Add contributing guidelines
- Improve file structure documentation

Both English and Chinese READMEs updated with same improvements.

Test improvements:
- Comprehensive unit tests (25 tests) covering v0-v4
- Comprehensive integration tests (21 tests) with edge cases
- TodoManager, SkillLoader, Agent Types all tested

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
CrazyBoyM 2026-01-25 02:39:33 +08:00
parent 7d71386a8e
commit 14eac29103
2 changed files with 248 additions and 156 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

202
README.md
View File

@ -1,5 +1,9 @@
# Learn Claude Code - Bash is all you & agent need # Learn Claude Code - Bash is all you & agent need
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
[![Tests](https://github.com/shareAI-lab/learn-claude-code/actions/workflows/test.yml/badge.svg)](https://github.com/shareAI-lab/learn-claude-code/actions)
[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](./LICENSE)
> **Disclaimer**: This is an independent educational project by [shareAI Lab](https://github.com/shareAI-lab). It is not affiliated with, endorsed by, or sponsored by Anthropic. "Claude Code" is a trademark of Anthropic. > **Disclaimer**: This is an independent educational project by [shareAI Lab](https://github.com/shareAI-lab). It is not affiliated with, endorsed by, or sponsored by Anthropic. "Claude Code" is a trademark of Anthropic.
**Learn how modern AI agents work by building one from scratch.** **Learn how modern AI agents work by building one from scratch.**
@ -8,7 +12,7 @@
--- ---
**A note to readers:** ## Why This Repository?
We created this repository out of admiration for Claude Code - **what we believe to be the most capable AI coding agent in the world**. Initially, we attempted to reverse-engineer its design through behavioral observation and speculation. The analysis we published was riddled with inaccuracies, unfounded guesses, and technical errors. We deeply apologize to the Claude Code team and anyone who was misled by that content. We created this repository out of admiration for Claude Code - **what we believe to be the most capable AI coding agent in the world**. Initially, we attempted to reverse-engineer its design through behavioral observation and speculation. The analysis we published was riddled with inaccuracies, unfounded guesses, and technical errors. We deeply apologize to the Claude Code team and anyone who was misled by that content.
@ -20,32 +24,61 @@ Over the past six months, through building and iterating on real agent systems,
<img height="400" alt="demo" src="https://github.com/user-attachments/assets/0e1e31f8-064f-4908-92ce-121e2eb8d453" /> <img height="400" alt="demo" src="https://github.com/user-attachments/assets/0e1e31f8-064f-4908-92ce-121e2eb8d453" />
## What is this? ## What You'll Learn
A progressive tutorial that demystifies AI coding agents like Kode, Claude Code, and Cursor Agent. After completing this tutorial, you will understand:
**5 versions, ~1100 lines total, each adding one concept:** - **The Agent Loop** - The surprisingly simple pattern behind all AI coding agents
- **Tool Design** - How to give AI models the ability to interact with the real world
- **Explicit Planning** - Using constraints to make AI behavior predictable
- **Context Management** - Keeping agent memory clean through subagent isolation
- **Knowledge Injection** - Loading domain expertise on-demand without retraining
| Version | Lines | What it adds | Core insight | ## Learning Path
|---------|-------|--------------|--------------|
| [v0](./v0_bash_agent.py) | ~50 | 1 bash tool | Bash is all you need | ```
| [v1](./v1_basic_agent.py) | ~200 | 4 core tools | Model as Agent | Start Here
| [v2](./v2_todo_agent.py) | ~300 | Todo tracking | Explicit planning | |
| [v3](./v3_subagent.py) | ~450 | Subagents | Divide and conquer | v
| [v4](./v4_skills_agent.py) | ~550 | Skills | Domain expertise on-demand | [v0: Bash Agent] -----> "One tool is enough"
| 16-50 lines
v
[v1: Basic Agent] ----> "The complete agent pattern"
| 4 tools, ~200 lines
v
[v2: Todo Agent] -----> "Make plans explicit"
| +TodoManager, ~300 lines
v
[v3: Subagent] -------> "Divide and conquer"
| +Task tool, ~450 lines
v
[v4: Skills Agent] ---> "Domain expertise on-demand"
+Skill tool, ~550 lines
```
**Recommended approach:**
1. Read and run v0 first - understand the core loop
2. Compare v0 and v1 - see how tools evolve
3. Study v2 for planning patterns
4. Explore v3 for complex task decomposition
5. Master v4 for building extensible agents
## Quick Start ## Quick Start
```bash ```bash
# Clone the repository
git clone https://github.com/shareAI-lab/learn-claude-code
cd learn-claude-code
# Install dependencies # Install dependencies
pip install anthropic python-dotenv pip install -r requirements.txt
# Configure API key # Configure API key
cp .env.example .env cp .env.example .env
# Edit .env with your ANTHROPIC_API_KEY # Edit .env with your ANTHROPIC_API_KEY
# Run any version # Run any version
python v0_bash_agent.py # Minimal python v0_bash_agent.py # Minimal (start here!)
python v1_basic_agent.py # Core agent loop python v1_basic_agent.py # Core agent loop
python v2_todo_agent.py # + Todo planning python v2_todo_agent.py # + Todo planning
python v3_subagent.py # + Subagents python v3_subagent.py # + Subagents
@ -67,6 +100,16 @@ while True:
That's it. The model calls tools until done. Everything else is refinement. That's it. The model calls tools until done. Everything else is refinement.
## Version Comparison
| Version | Lines | Tools | Core Addition | Key Insight |
|---------|-------|-------|---------------|-------------|
| [v0](./v0_bash_agent.py) | ~50 | bash | Recursive subagents | One tool is enough |
| [v1](./v1_basic_agent.py) | ~200 | bash, read, write, edit | Core loop | Model as Agent |
| [v2](./v2_todo_agent.py) | ~300 | +TodoWrite | Explicit planning | Constraints enable complexity |
| [v3](./v3_subagent.py) | ~450 | +Task | Context isolation | Clean context = better results |
| [v4](./v4_skills_agent.py) | ~550 | +Skill | Knowledge loading | Expertise without retraining |
## File Structure ## File Structure
``` ```
@ -77,55 +120,15 @@ learn-claude-code/
├── v2_todo_agent.py # ~300 lines: + TodoManager ├── v2_todo_agent.py # ~300 lines: + TodoManager
├── v3_subagent.py # ~450 lines: + Task tool, agent registry ├── v3_subagent.py # ~450 lines: + Task tool, agent registry
├── v4_skills_agent.py # ~550 lines: + Skill tool, SkillLoader ├── v4_skills_agent.py # ~550 lines: + Skill tool, SkillLoader
├── skills/ # Example skills (for learning) ├── skills/ # Example skills (pdf, code-review, mcp-builder, agent-builder)
└── docs/ # Detailed explanations (EN + ZH) ├── docs/ # Technical documentation (EN + ZH)
├── articles/ # Blog-style articles (ZH)
└── tests/ # Unit and integration tests
``` ```
## Using the Agent Builder Skill
This repository includes a meta-skill that teaches agents how to build agents:
```bash
# Scaffold a new agent project
python skills/agent-builder/scripts/init_agent.py my-agent
# Or with specific complexity level
python skills/agent-builder/scripts/init_agent.py my-agent --level 0 # Minimal
python skills/agent-builder/scripts/init_agent.py my-agent --level 1 # 4 tools (default)
```
### Install Skills for Production Use
```bash
# Kode CLI (recommended)
kode plugins install https://github.com/shareAI-lab/shareAI-skills
# Claude Code
claude plugins install https://github.com/shareAI-lab/shareAI-skills
```
See [shareAI-skills](https://github.com/shareAI-lab/shareAI-skills) for the full collection of production-ready skills.
## Key Concepts
### v0: Bash is All You Need
One tool. Recursive self-calls for subagents. Proves the core is tiny.
### v1: Model as Agent
4 tools (bash, read, write, edit). The complete agent in one function.
### v2: Structured Planning
Todo tool makes plans explicit. Constraints enable complex tasks.
### v3: Subagent Mechanism
Task tool spawns isolated child agents. Context stays clean.
### v4: Skills Mechanism
SKILL.md files provide domain expertise on-demand. Knowledge as a first-class citizen.
## Deep Dives ## Deep Dives
**Technical tutorials (docs/):** ### Technical Documentation (docs/)
| English | 中文 | | English | 中文 |
|---------|------| |---------|------|
@ -135,35 +138,78 @@ SKILL.md files provide domain expertise on-demand. Knowledge as a first-class ci
| [v3: Subagent Mechanism](./docs/v3-subagent-mechanism.md) | [v3: 子代理机制](./docs/v3-子代理机制.md) | | [v3: Subagent Mechanism](./docs/v3-subagent-mechanism.md) | [v3: 子代理机制](./docs/v3-子代理机制.md) |
| [v4: Skills Mechanism](./docs/v4-skills-mechanism.md) | [v4: Skills 机制](./docs/v4-Skills机制.md) | | [v4: Skills Mechanism](./docs/v4-skills-mechanism.md) | [v4: Skills 机制](./docs/v4-Skills机制.md) |
**Original articles (articles/) - Chinese only, social media style:** ### Articles (articles/) - Chinese, Social Media Style
- [v0文章](./articles/v0文章.md) | [v1文章](./articles/v1文章.md) | [v2文章](./articles/v2文章.md) | [v3文章](./articles/v3文章.md) | [v4文章](./articles/v4文章.md)
- [上下文缓存经济学](./articles/上下文缓存经济学.md) - Context Caching Economics for Agent Developers - [v0文章](./articles/v0文章.md) - Bash is All You Need
- [v1文章](./articles/v1文章.md) - The $30M Secret in 400 Lines
- [v2文章](./articles/v2文章.md) - Self-Constraining with Todo
- [v3文章](./articles/v3文章.md) - Subagent Mechanism
- [v4文章](./articles/v4文章.md) - Skills Mechanism
- [上下文缓存经济学](./articles/上下文缓存经济学.md) - Context Caching Economics
## Using the Skills System
### Example Skills Included
| Skill | Purpose |
|-------|---------|
| [agent-builder](./skills/agent-builder/) | Meta-skill: how to build agents |
| [code-review](./skills/code-review/) | Systematic code review methodology |
| [pdf](./skills/pdf/) | PDF manipulation patterns |
| [mcp-builder](./skills/mcp-builder/) | MCP server development |
### Scaffold a New Agent
```bash
# Use the agent-builder skill to create a new project
python skills/agent-builder/scripts/init_agent.py my-agent
# Specify complexity level
python skills/agent-builder/scripts/init_agent.py my-agent --level 0 # Minimal
python skills/agent-builder/scripts/init_agent.py my-agent --level 1 # 4 tools
```
### Install Skills for Production
```bash
# Kode CLI (recommended)
kode plugins install https://github.com/shareAI-lab/shareAI-skills
# Claude Code
claude plugins install https://github.com/shareAI-lab/shareAI-skills
```
## Configuration
```bash
# .env file options
ANTHROPIC_API_KEY=sk-ant-xxx # Required: Your API key
ANTHROPIC_BASE_URL=https://... # Optional: For API proxies
MODEL_ID=claude-sonnet-4-5-20250929 # Optional: Model selection
```
## Related Projects ## Related Projects
| Repository | Purpose | | Repository | Description |
|------------|---------| |------------|-------------|
| [Kode](https://github.com/shareAI-lab/Kode) | Full-featured open source agent CLI (production) | | [Kode](https://github.com/shareAI-lab/Kode) | Production-ready open source agent CLI |
| [shareAI-skills](https://github.com/shareAI-lab/shareAI-skills) | Production-ready skills for AI agents | | [shareAI-skills](https://github.com/shareAI-lab/shareAI-skills) | Production skills collection |
| [Agent Skills Spec](https://github.com/anthropics/agent-skills) | Official specification | | [Agent Skills Spec](https://github.com/anthropics/agent-skills) | Official specification |
### Use as Template
Fork and customize for your own agent projects:
```bash
git clone https://github.com/shareAI-lab/learn-claude-code
cd learn-claude-code
# Start from any version level
cp v1_basic_agent.py my_agent.py
```
## Philosophy ## Philosophy
> The model is 80%. Code is 20%. > **The model is 80%. Code is 20%.**
Modern agents like Kode and Claude Code work not because of clever engineering, but because the model is trained to be an agent. Our job is to give it tools and stay out of the way. Modern agents like Kode and Claude Code work not because of clever engineering, but because the model is trained to be an agent. Our job is to give it tools and stay out of the way.
## Contributing
Contributions are welcome! Please feel free to submit issues and pull requests.
- Add new example skills in `skills/`
- Improve documentation in `docs/`
- Report bugs or suggest features via [Issues](https://github.com/shareAI-lab/learn-claude-code/issues)
## License ## License
MIT MIT
@ -172,4 +218,4 @@ MIT
**Model as Agent. That's the whole secret.** **Model as Agent. That's the whole secret.**
[@baicai003](https://x.com/baicai003) [@baicai003](https://x.com/baicai003) | [shareAI Lab](https://github.com/shareAI-lab)

186
README_zh.md
View File

@ -1,4 +1,8 @@
# Learn Claude Code # Learn Claude Code - Bash 就是 Agent 的一切
[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
[![Tests](https://github.com/shareAI-lab/learn-claude-code/actions/workflows/test.yml/badge.svg)](https://github.com/shareAI-lab/learn-claude-code/actions)
[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](./LICENSE)
> **声明**: 这是 [shareAI Lab](https://github.com/shareAI-lab) 的独立教育项目，与 Anthropic 无关，未获其认可或赞助。"Claude Code" 是 Anthropic 的商标。 > **声明**: 这是 [shareAI Lab](https://github.com/shareAI-lab) 的独立教育项目，与 Anthropic 无关，未获其认可或赞助。"Claude Code" 是 Anthropic 的商标。
@ -8,7 +12,7 @@
--- ---
**致读者：** ## 为什么有这个仓库？
这个仓库源于我们对 Claude Code 的敬佩 - **我们认为它是世界上最优秀的 AI 编程代理**。最初，我们试图通过行为观察和推测来逆向分析它的设计。然而，我们当时发布的分析内容充斥着不准确的信息、缺乏依据的猜测和技术错误。我们在此向 Claude Code 团队以及所有被这些内容误导的朋友深表歉意。 这个仓库源于我们对 Claude Code 的敬佩 - **我们认为它是世界上最优秀的 AI 编程代理**。最初，我们试图通过行为观察和推测来逆向分析它的设计。然而，我们当时发布的分析内容充斥着不准确的信息、缺乏依据的猜测和技术错误。我们在此向 Claude Code 团队以及所有被这些内容误导的朋友深表歉意。
@ -20,32 +24,61 @@
<img height="400" alt="demo" src="https://github.com/user-attachments/assets/0e1e31f8-064f-4908-92ce-121e2eb8d453" /> <img height="400" alt="demo" src="https://github.com/user-attachments/assets/0e1e31f8-064f-4908-92ce-121e2eb8d453" />
## 这是什么？ ## 你将学到什么
一个渐进式教程，揭开 Kode、Claude Code、Cursor Agent 等 AI Agent 的神秘面纱。 完成本教程后，你将理解：
**5 个版本，总共约 1100 行，每个版本只添加一个概念：** - **Agent 循环** - 所有 AI 编程代理背后那个令人惊讶的简单模式
- **工具设计** - 如何让 AI 模型能够与真实世界交互
- **显式规划** - 使用约束让 AI 行为可预测
- **上下文管理** - 通过子代理隔离保持代理记忆干净
- **知识注入** - 按需加载领域专业知识，无需重新训练
| 版本 | 行数 | 新增内容 | 核心洞察 | ## 学习路径
|------|------|---------|---------|
| [v0](./v0_bash_agent.py) | ~50 | 1 个 bash 工具 | Bash 就是一切 | ```
| [v1](./v1_basic_agent.py) | ~200 | 4 个核心工具 | 模型即代理 | 从这里开始
| [v2](./v2_todo_agent.py) | ~300 | Todo 追踪 | 显式规划 | |
| [v3](./v3_subagent.py) | ~450 | 子代理 | 分而治之 | v
| [v4](./v4_skills_agent.py) | ~550 | Skills | 按需领域专业 | [v0: Bash Agent] -----> "一个工具就够了"
| 16-50 行
v
[v1: Basic Agent] ----> "完整的 Agent 模式"
| 4 个工具，~200 行
v
[v2: Todo Agent] -----> "让计划显式化"
| +TodoManager，~300 行
v
[v3: Subagent] -------> "分而治之"
| +Task 工具，~450 行
v
[v4: Skills Agent] ---> "按需领域专业"
+Skill 工具，~550 行
```
**推荐学习方式：**
1. 先阅读并运行 v0 - 理解核心循环
2. 对比 v0 和 v1 - 看工具如何演进
3. 学习 v2 的规划模式
4. 探索 v3 的复杂任务分解
5. 掌握 v4 构建可扩展的 Agent
## 快速开始 ## 快速开始
```bash ```bash
# 克隆仓库
git clone https://github.com/shareAI-lab/learn-claude-code
cd learn-claude-code
# 安装依赖 # 安装依赖
pip install anthropic python-dotenv pip install -r requirements.txt
# 配置 API Key # 配置 API Key
cp .env.example .env cp .env.example .env
# 编辑 .env 填入你的 ANTHROPIC_API_KEY # 编辑 .env 填入你的 ANTHROPIC_API_KEY
# 运行任意版本 # 运行任意版本
python v0_bash_agent.py # 极简版 python v0_bash_agent.py # 极简版（从这里开始！）
python v1_basic_agent.py # 核心 Agent 循环 python v1_basic_agent.py # 核心 Agent 循环
python v2_todo_agent.py # + Todo 规划 python v2_todo_agent.py # + Todo 规划
python v3_subagent.py # + 子代理 python v3_subagent.py # + 子代理
@ -67,6 +100,16 @@ while True:
就这样。模型持续调用工具直到完成。其他一切都是精化。 就这样。模型持续调用工具直到完成。其他一切都是精化。
## 版本对比
| 版本 | 行数 | 工具 | 核心新增 | 关键洞察 |
|------|------|------|---------|---------|
| [v0](./v0_bash_agent.py) | ~50 | bash | 递归子代理 | 一个工具就够了 |
| [v1](./v1_basic_agent.py) | ~200 | bash, read, write, edit | 核心循环 | 模型即代理 |
| [v2](./v2_todo_agent.py) | ~300 | +TodoWrite | 显式规划 | 约束赋能复杂性 |
| [v3](./v3_subagent.py) | ~450 | +Task | 上下文隔离 | 干净上下文 = 更好结果 |
| [v4](./v4_skills_agent.py) | ~550 | +Skill | 知识加载 | 专业无需重训 |
## 文件结构 ## 文件结构
``` ```
@ -77,21 +120,53 @@ learn-claude-code/
├── v2_todo_agent.py # ~300 行: + TodoManager ├── v2_todo_agent.py # ~300 行: + TodoManager
├── v3_subagent.py # ~450 行: + Task 工具，代理注册表 ├── v3_subagent.py # ~450 行: + Task 工具，代理注册表
├── v4_skills_agent.py # ~550 行: + Skill 工具，SkillLoader ├── v4_skills_agent.py # ~550 行: + Skill 工具，SkillLoader
├── skills/ # 示例 Skills（用于学习） ├── skills/ # 示例 Skills（pdf, code-review, mcp-builder, agent-builder）
└── docs/ # 详细文档 (中英双语) ├── docs/ # 技术文档（中英双语）
├── articles/ # 公众号风格文章
└── tests/ # 单元测试和集成测试
``` ```
## 使用 Agent Builder Skill ## 深入阅读
本仓库包含一个元技能，教 Agent 如何构建 Agent： ### 技术文档 (docs/)
| English | 中文 |
|---------|------|
| [v0: Bash is All You Need](./docs/v0-bash-is-all-you-need.md) | [v0: Bash 就是一切](./docs/v0-Bash就是一切.md) |
| [v1: Model as Agent](./docs/v1-model-as-agent.md) | [v1: 模型即代理](./docs/v1-模型即代理.md) |
| [v2: Structured Planning](./docs/v2-structured-planning.md) | [v2: 结构化规划](./docs/v2-结构化规划.md) |
| [v3: Subagent Mechanism](./docs/v3-subagent-mechanism.md) | [v3: 子代理机制](./docs/v3-子代理机制.md) |
| [v4: Skills Mechanism](./docs/v4-skills-mechanism.md) | [v4: Skills 机制](./docs/v4-Skills机制.md) |
### 原创文章 (articles/) - 公众号风格
- [v0文章](./articles/v0文章.md) - Bash 就是一切
- [v1文章](./articles/v1文章.md) - 价值 3000 万美金的 400 行代码
- [v2文章](./articles/v2文章.md) - 用 Todo 实现自我约束
- [v3文章](./articles/v3文章.md) - 子代理机制
- [v4文章](./articles/v4文章.md) - Skills 机制
- [上下文缓存经济学](./articles/上下文缓存经济学.md) - Agent 开发者必知的成本优化
## 使用 Skills 系统
### 内置示例 Skills
| Skill | 用途 |
|-------|------|
| [agent-builder](./skills/agent-builder/) | 元技能：如何构建 Agent |
| [code-review](./skills/code-review/) | 系统化代码审查方法论 |
| [pdf](./skills/pdf/) | PDF 操作模式 |
| [mcp-builder](./skills/mcp-builder/) | MCP 服务器开发 |
### 脚手架生成新 Agent
```bash ```bash
# 脚手架生成新 Agent 项目 # 使用 agent-builder skill 创建新项目
python skills/agent-builder/scripts/init_agent.py my-agent python skills/agent-builder/scripts/init_agent.py my-agent
# 或指定复杂度级别 # 指定复杂度级别
python skills/agent-builder/scripts/init_agent.py my-agent --level 0 # 极简 python skills/agent-builder/scripts/init_agent.py my-agent --level 0 # 极简
python skills/agent-builder/scripts/init_agent.py my-agent --level 1 # 4 工具 (默认) python skills/agent-builder/scripts/init_agent.py my-agent --level 1 # 4 工具
``` ```
### 生产环境安装 Skills ### 生产环境安装 Skills
@ -104,66 +179,37 @@ kode plugins install https://github.com/shareAI-lab/shareAI-skills
claude plugins install https://github.com/shareAI-lab/shareAI-skills claude plugins install https://github.com/shareAI-lab/shareAI-skills
``` ```
详见 [shareAI-skills](https://github.com/shareAI-lab/shareAI-skills) 获取完整的生产就绪 skills 集合。 ## 配置说明
## 核心概念 ```bash
# .env 文件选项
### v0: Bash 就是一切 ANTHROPIC_API_KEY=sk-ant-xxx # 必需：你的 API key
一个工具。递归自调用实现子代理。证明核心是极小的。 ANTHROPIC_BASE_URL=https://... # 可选：API 代理
MODEL_ID=claude-sonnet-4-5-20250929 # 可选：模型选择
### v1: 模型即代理 ```
4 个工具 (bash, read, write, edit)。完整 Agent 在一个函数里。
### v2: 结构化规划
Todo 工具让计划显式化。约束赋能复杂任务。
### v3: 子代理机制
Task 工具生成隔离的子代理。上下文保持干净。
### v4: Skills 机制
SKILL.md 文件按需提供领域专业知识。知识作为一等公民。
## 深入阅读
**技术教程 (docs/):**
| English | 中文 |
|---------|------|
| [v0: Bash is All You Need](./docs/v0-bash-is-all-you-need.md) | [v0: Bash 就是一切](./docs/v0-Bash就是一切.md) |
| [v1: Model as Agent](./docs/v1-model-as-agent.md) | [v1: 模型即代理](./docs/v1-模型即代理.md) |
| [v2: Structured Planning](./docs/v2-structured-planning.md) | [v2: 结构化规划](./docs/v2-结构化规划.md) |
| [v3: Subagent Mechanism](./docs/v3-subagent-mechanism.md) | [v3: 子代理机制](./docs/v3-子代理机制.md) |
| [v4: Skills Mechanism](./docs/v4-skills-mechanism.md) | [v4: Skills 机制](./docs/v4-Skills机制.md) |
**原创文章 (articles/) - 公众号风格:**
- [v0文章](./articles/v0文章.md) | [v1文章](./articles/v1文章.md) | [v2文章](./articles/v2文章.md) | [v3文章](./articles/v3文章.md) | [v4文章](./articles/v4文章.md)
- [上下文缓存经济学](./articles/上下文缓存经济学.md) - Agent 开发者必知的成本优化指南
## 相关项目 ## 相关项目
| 仓库 | 用途 | | 仓库 | 说明 |
|------|------| |------|------|
| [Kode](https://github.com/shareAI-lab/Kode) | 全功能开源 Agent CLI（生产环境） | | [Kode](https://github.com/shareAI-lab/Kode) | 生产就绪的开源 Agent CLI |
| [shareAI-skills](https://github.com/shareAI-lab/shareAI-skills) | 生产就绪的 AI Agent Skills | | [shareAI-skills](https://github.com/shareAI-lab/shareAI-skills) | 生产 Skills 集合 |
| [Agent Skills Spec](https://github.com/anthropics/agent-skills) | 官方规范 | | [Agent Skills Spec](https://github.com/anthropics/agent-skills) | 官方规范 |
### 作为模板
Fork 并自定义为你自己的 Agent 项目：
```bash
git clone https://github.com/shareAI-lab/learn-claude-code
cd learn-claude-code
# 从任意版本级别开始
cp v1_basic_agent.py my_agent.py
```
## 设计哲学 ## 设计哲学
> 模型是 80%，代码是 20%。 > **模型是 80%，代码是 20%。**
Kode 和 Claude Code 等现代 Agent 能工作，不是因为巧妙的工程，而是因为模型被训练成了 Agent。我们的工作就是给它工具，然后闪开。 Kode 和 Claude Code 等现代 Agent 能工作，不是因为巧妙的工程，而是因为模型被训练成了 Agent。我们的工作就是给它工具，然后闪开。
## 贡献
欢迎贡献！请随时提交 issues 和 pull requests。
- 在 `skills/` 中添加新的示例 skills
- 在 `docs/` 中改进文档
- 通过 [Issues](https://github.com/shareAI-lab/learn-claude-code/issues) 报告 bug 或建议功能
## License ## License
MIT MIT
@ -172,4 +218,4 @@ MIT
**模型即代理。这就是全部秘密。** **模型即代理。这就是全部秘密。**
[@baicai003](https://x.com/baicai003) [@baicai003](https://x.com/baicai003) | [shareAI Lab](https://github.com/shareAI-lab)