Claude Code Engingeering EN

The Claude Code Operating Model — Code Examples

Companion repository for **_The Claude Code Operating Model_** (Packt, 2026) by **Jia Huang** — *Build scalable AI coding systems with Skills, MCP, Hooks, agent orchestration, and SDK patterns.*

Every chapter has a directory here. The code is runnable, and it reflects the **corrected** APIs as of publication — where the printed text and the current SDK disagree, this repository is right.

Setup

# Prerequisites: Node.js 20+, Python 3.10+, Git
npm install -g @anthropic-ai/claude-code
claude --version

export ANTHROPIC_API_KEY=sk-ant-...   # or sign in with a Claude subscription

git clone https://github.com/huangjia2019/claude-code-engingeering-EN.git
cd claude-code-engingeering-EN

Chapters

Chapter	Directory	What you'll run
1 · A Broad Perspective	`ch01-overview/`	Setup check; the four-layer Harness map
2 · Learning from the Past	`ch02-memory/`	CLAUDE.md before/after on a real project
3 · Teaching to Fish	`ch03-skills/`	Three Skills; progressive disclosure measured in tokens
4 · Divide and Conquer	`ch04-subagents/`	Serial bug-fix pipeline; parallel multi-lens review
5 · From Guidelines to Guardrails	`ch05-hooks/`	A hook that blocks rm -rf; a hook that auto-formats
6 · Connecting Everything	`ch06-mcp/`	.mcp.json scopes; a custom MCP server
7 · Headless Mode and CI/CD	`ch07-headless-cicd/`	GitHub Actions, GitLab CI, Jenkins
8 · Agent SDK	`ch08-agent-sdk/`	Custom tools, structured output, a FastAPI service
9 · The Plugin Ecosystem	`ch09-plugins/`	An installable plugin; a private marketplace
10 · From Individual to Team	`ch10-team-practices/`	Layered CLAUDE.md, permissions, cost, audit

Workshop

[`workshop/`](wo