Skip to content

Add shareAI-lab/learn-claude-code #46

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
shreyas-lyzr wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add shareAI-lab/learn-claude-code #46

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 55 additions & 0 deletions agents/shareAI-lab__learn-claude-code/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
# learn-claude-code

> **Bash is all you need** — A nano Claude Code–like agent harness, built from 0 to 1.

`learn-claude-code` is a 20-chapter, hands-on curriculum that teaches developers how to build production-grade Claude Code–style agent harnesses from first principles using the Anthropic Python SDK.

## What it does

Each of the 20 numbered chapters (`s01` → `s20`) ships a self-contained, runnable Python module that adds **exactly one new harness capability** on top of the previous one:

| Chapter | Capability |
|---------|-----------|
| s01 | Basic agent loop |
| s02 | Tool use (bash, read, write) |
| s03 | Permission governance |
| s04 | Hooks & observability |
| s05 | Todo/task tracking |
| s06 | Subagent spawning |
| s07 | Skill loading (on-demand SKILL.md) |
| s08 | Context compaction |
| s09 | Persistent memory |
| s10 | Runtime prompt assembly + caching |
| s11 | Error recovery & retries |
| s12 | Task graphs with dependency resolution |
| s13 | Background tasks |
| s14 | Cron scheduling |
| s15 | Agent teams |
| s16 | Async team protocols (mailbox) |
| s17 | Autonomous agents |
| s18 | Worktree isolation |
| s19 | MCP plugin integration |
| s20 | Comprehensive: all patterns combined |

## Key capabilities

- **Skills** — `agent-builder`, `code-review`, `mcp-builder`, `pdf`
- **Multilingual docs** — English, Chinese (中文), Japanese (日本語)
- **Zero framework dependencies** — pure Anthropic SDK + Python stdlib
- **62k+ GitHub stars** — one of the most-starred Claude Code reference repos

## Quick start

```bash
git clone https://github.com/shareAI-lab/learn-claude-code
cd learn-claude-code
pip install -r requirements.txt
cp .env.example .env # add your ANTHROPIC_API_KEY + MODEL_ID
python s01_agent_loop/code.py
```

## GitAgent Protocol

This repo ships `agent.yaml` and `SOUL.md` at the root, making it runnable on any GAP-compatible runtime (Claude Code, GitClaw, and others).

The soul: *"You are a coding agent harness — not the agent itself, but the vehicle it rides in."*
15 changes: 15 additions & 0 deletions agents/shareAI-lab__learn-claude-code/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
{
"name": "learn-claude-code",
"author": "shareAI-lab",
"description": "A 20-chapter, hands-on curriculum for building Claude Code–style agent harnesses: tools, skills, subagents, task graphs, autonomous agents, and more.",
"repository": "https://github.com/shareAI-lab/learn-claude-code",
"path": "",
"version": "1.0.0",
"category": "education",
"tags": ["claude-code", "agent-harness", "tutorial", "anthropic", "llm", "developer-tools", "python", "autonomous-agents"],
"license": "MIT",
"model": "claude-sonnet-4-6",
"adapters": ["claude-code", "system-prompt"],
"icon": false,
"banner": false
}
Loading