A comprehensive synthesis of the claude-code-from-source project (and companion site claude-code-from-source.com ) — distilled into core principles, techniques, and actionable guidelines for builders who want to ship a coding agent of comparable quality. The source repo is a 18-chapter educational reverse-engineering of Claude Code derived from npm source maps. No proprietary code is reproduced — only architectural pseudocode and design rationale. This guide does the same. Table of Contents 💡 TL;DR — the whole agent in one mental picture 🎯 What you are actually building 🧱 The six core abstractions 📦 State: two tiers, one source of truth ⚙️ The agent loop: AsyncGenerator as control plane 🔧 Tools: self-describing, fail-closed, parameterized ⚡ Concurrency and speculative execution 🔒 Permissions: modes, rules, and bubbling 🗜️ Context engineering: the 4-layer compression pipeline 🌐 The API layer: prompt caching as architecture 🤖 Sub-agents and fork agents 🕸️ Multi-agent coordination patterns 🧠 Memory:…