https://github.com/aimasteracc/inside-claude-code
Reverse-engineering Claude Code's prompt architecture — free chapters + agent-engineering field guide
https://github.com/aimasteracc/inside-claude-code
agent-engineering agentic ai-agents claude-code llm prompt-engineering
Last synced: 17 days ago
JSON representation
Reverse-engineering Claude Code's prompt architecture — free chapters + agent-engineering field guide
- Host: GitHub
- URL: https://github.com/aimasteracc/inside-claude-code
- Owner: aimasteracc
- License: other
- Created: 2026-06-03T19:48:18.000Z (21 days ago)
- Default Branch: main
- Last Pushed: 2026-06-03T21:16:42.000Z (21 days ago)
- Last Synced: 2026-06-03T21:18:39.767Z (21 days ago)
- Topics: agent-engineering, agentic, ai-agents, claude-code, llm, prompt-engineering
- Size: 55.7 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# Inside Claude Code
### A Reverse-Engineering Field Guide to Agent Engineering
**12 prompt-design patterns · 7 agent failure modes · the internal mechanics behind the world's leading agentic coding tool, inferred from how it behaves.**
**🌍 English · 简体中文 · 日本語 — all three editions included.**
[**💖 Sponsor $25 to unlock the full book + toolkit**](https://github.com/sponsors/aimasteracc?frequency=one-time) · [Read 2 free chapters ↓](#-read-free)
*Sponsor the **$25 Inside Claude Code** tier — you get the full book (EN + 中文 + 日本語 PDF) + toolkit, delivered within hours.*
> 📘 **The full book ships through GitHub Sponsors.** Read the two free chapters below, then [**sponsor the $25 *Inside Claude Code* tier**](https://github.com/sponsors/aimasteracc?frequency=one-time) to unlock all 10 chapters + the toolkit. ⭐ Star the repo too.
---
## Why this exists
Everyone is building agents. Almost no one has taken apart one that actually works.
Claude Code is the reference implementation of the autonomous coding agent — it runs for hours, edits dozens of files, tests its own work, and ships. Underneath it is a body of hard-won engineering: a prompt layer built as **many small, single-purpose units** rather than one block, a precise request-assembly pipeline, a context engine that survives long sessions, and a set of guardrails where **the majority of the instructions describe what the agent must *not* do.**
This book reverse-engineers that machine and hands you the patterns — organized, translated into plain English, and turned into things you can paste into your own agent today.
> If you've ever watched an autonomous agent confidently declare a half-finished task "complete," there is a known fix for that. It's in Chapter 6.
## Who it's for
- Engineers **building agents** on the Claude or OpenAI APIs who want production-grade patterns, not blog-post platitudes.
- **Power users** of Claude Code / Cursor who want to understand — and bend — the tool they live in.
- Anyone shipping LLM features who is tired of agents that stub out work, inflate their own grades, or panic near the context limit.
## What's inside
**60+ pages · ~14,000 words · 10 chapters · a copy-paste toolkit.**
| # | Chapter | You walk away with |
|---|---------|--------------------|
| 1 | The Five-Layer Prompt Architecture | Why a great agent's prompt is a *filesystem*, not a string |
| 2 | The Prompt Loading Flow | How one message becomes an API request — and where the cache boundary stops you re-billing the whole static prompt every turn |
| 3 | Twelve Patterns I — Behavior & Architecture | Constraint-first, single-responsibility, event-driven, cognitive boundaries, delegation, progressive safety |
| 4 | Twelve Patterns II — Runtime & Knowledge | Compaction, output efficiency, mode switching, the memory trinity, skillification, observability |
| 5 | Print Mode & Autonomous Loops | Signal handling, the auto-compaction threshold, designing a headless loop that won't wedge |
| 6 | The Seven Agent Failure Modes | Each failure, its root cause, and the *verified* fix |
| 7 | Sub-agents & Layered Delegation | The isolation contract — and the messaging asymmetry that silently kills most multi-agent setups |
| 8 | The Autonomous Development Pipeline | A full prompt-to-verified-build loop with an expert-review panel |
| 9 | Designing Your Own Harness | The whole book reduced to five buildable subsystems |
| 10 | The Checklist & Templates | A pre-flight checklist + paste-ready templates |
### The toolkit (ships with the book)
- 🗂️ **`CLAUDE.md.template`** — a constraint-first operating-rules file for any repo
- 🤖 **`subagent-prompt.template.md`** — brief sub-agents so they don't silently fail
- 🔄 **`context-handoff.template.md`** — survive a context reset without losing the thread
- 📄 **Patterns cheat sheet** (1 page) + **Failure-modes checklist** (1 page) — print and pin
## A taste — the 7 ways autonomous agents fail
Every chapter is this concrete. Chapter 6 names all seven failure modes and gives each a *verified* fix. The modes:
1. **One-shot impulse** — does everything at once, exhausts context, leaves fragments
2. **Premature "done"** — declares victory with most of the work unfinished
3. **Context anxiety** — rushes to wrap up near the context limit, with capacity to spare
4. **Self-evaluation inflation** — grades its own broken work 9/10
5. **Skipping E2E** — unit tests pass; the actual button does nothing
6. **Stub-ification** — the UI looks complete; the interactions are hollow
7. **Spec cascade** — a planner's one wrong detail poisons everything downstream
You've probably met at least three. The fixes are in the book.
No email required. Read the first two chapters right here:
- [**Introduction — Why Take a Coding Agent Apart?**](book/00-introduction.md)
- [**Chapter 1 — The Five-Layer Prompt Architecture**](book/01-five-layer-architecture.md)
- [**Chapter 2 — The Prompt Loading Flow**](book/02-prompt-loading-flow.md)
**🇨🇳 简体中文免费试读：** [引言](book-zh/00-introduction.md) · [第 1 章 · 五层提示词架构](book-zh/01-five-layer-architecture.md) · [第 2 章 · Prompt 加载流程](book-zh/02-prompt-loading-flow.md)
**🇯🇵 日本語 無料サンプル：** [はじめに](book-ja/00-introduction.md) · [第1章 · 5層アーキテクチャ](book-ja/01-five-layer-architecture.md) · [第2章 · プロンプト読み込みフロー](book-ja/02-prompt-loading-flow.md)
If the mechanism-level depth is what you've been looking for, the other eight chapters and the toolkit are one click away.
### [💖 Sponsor $25 to unlock the full book + toolkit](https://github.com/sponsors/aimasteracc?frequency=one-time)
*Sponsor the **$25 Inside Claude Code** tier → you get a private-repo invite with the full PDF (3 languages) + toolkit, usually within hours.*
## Why trust it
These patterns were distilled from **careful observation of how Claude Code behaves**, inference about the request pipeline that behavior implies, and Anthropic's own **published** guidance on long-running agent harnesses. It is independent analysis and commentary on observed behavior — it describes patterns in original words and does **not** reproduce any proprietary source code or prompt text.
## FAQ
**Is this just the Claude Code docs?** No. The docs tell you how to *use* the tool. This book reverse-engineers how it's *built*, and turns that into patterns for your own agents.
**I don't use Claude Code — is it still useful?** Yes. The patterns are model- and tool-agnostic. Chapters 3, 4, 6, 7, and 9 apply to any agent on any API.
**What format?** A PDF plus the raw Markdown, and the toolkit files. Yours forever, free updates.
**How do I get it after sponsoring?** Sponsor the **$25** *Inside Claude Code* tier on [GitHub Sponsors](https://github.com/sponsors/aimasteracc?frequency=one-time); you'll get an invite to the private repo with the full PDF + toolkit (usually within a few hours). Any tier at or above the book tier works.
**Not happy?** Message me and I'll make it right.
## License
The two free preview chapters and the README are shared for evaluation. The full book and toolkit are commercial — please don't redistribute. © 2026. All rights reserved.
*Study the machine that works, and you stop guessing at the one you're building.*