Summary

Preface

---

Part I: Architecture — How Claude Code Works

• Chapter 1: The Full Tech Stack of an AI Coding Agent
• Chapter 2: Tool System — 40+ Tools as the Model's Hands
• Chapter 3: Agent Loop — The Full Lifecycle from User Input to Model Response
• Chapter 4: Tool Execution Orchestration — Permissions, Concurrency, Streaming, and Interrupts
• Chapter 4b: Plan Mode — From "Act First, Ask Later" to "Look Before You Leap"

---

Part II: Prompt Engineering — System Prompts as the Control Plane

• Chapter 5: System Prompt Architecture
• Chapter 6: Steering Behavior Through Prompts
• Chapter 6b: API Communication Layer — Retry, Streaming, and Degradation Engineering
• Chapter 7: Model-Specific Tuning and A/B Testing
• Chapter 8: Tool Prompts as Micro-Harnesses

---

Part III: Context Management — The 200K Token Arena

• Chapter 9: Automatic Compaction — When and How Context Gets Compressed
• Chapter 10: File State Preservation After Compaction
• Chapter 11: Micro-Compaction — Precise Context Pruning
• Chapter 12: Token Budgeting Strategies

---

Part IV: Prompt Caching — The Hidden Cost Optimizer

• Chapter 13: Cache Architecture and Breakpoint Design
• Chapter 14: Cache Break Detection System
• Chapter 15: Cache Optimization Patterns

---

Part V: Safety and Permissions — Defense in Depth

• Chapter 16: Permission System
• Chapter 17: YOLO Classifier
• Chapter 17b: Prompt Injection Defense — From Unicode Sanitization to Defense in Depth
• Chapter 18: Hooks — User-Defined Interception Points
• Chapter 18b: Sandbox System — Multi-Platform Isolation from Seatbelt to Bubblewrap
• Chapter 19: CLAUDE.md — User Instructions as an Override Layer

---

Part VI: Advanced Subsystems

• Chapter 20: Agent Spawning and Orchestration
• Chapter 20b: Teams and Multi-Process Collaboration
• Chapter 20c: Ultraplan — Remote Multi-Agent Planning
• Chapter 21: Effort, Fast Mode, and Thinking
• Chapter 22: Skills System — From Built-In to User-Defined
• Chapter 22b: Plugin System — From Packaging to Marketplace Extension Engineering
• Chapter 23: The Unreleased Feature Pipeline — The Roadmap Behind 89 Feature Flags
• Chapter 24: Cross-Session Memory — From Forgetfulness to Persistent Learning

---

Part VII: Lessons for AI Agent Builders

• Chapter 25: Harness Engineering Principles
• Chapter 26: Context Management as a Core Capability
• Chapter 27: Production-Grade AI Coding Patterns
• Chapter 28: Where Claude Code Falls Short
• Chapter 29: Observability Engineering — From logEvent to Production-Grade Telemetry
• Chapter 30: Build Your Own AI Agent — From Claude Code Patterns to Practice

---

Appendix

• Appendix A: Key File Index
• Appendix B: Environment Variable Reference
• Appendix C: Glossary
• Appendix D: Full List of 89 Feature Flags
• Appendix E: Version Evolution Log
• Appendix F: End-to-End Case Traces
• Appendix G: Authentication & Subscription System