<aside> 💡
This entire report was generated by Claude Opus 4, with the help of almost all of the major flagship models. However, the 8000 word write-up on the process of making this report was manually written - you can always start there: Conducting smarter intelligences than me: new orchestras
I should note that this is not a true decompilation or reverse engineering attempt in any real sense, more of an homage to the wonderful work done by the Claude team. None of the examples provided are guaranteed to be in Claude Code (or directly derived/copied from source) - the primary intent is didactic value in learning new ways to orchestrate AI agents.
(Quick note: I appreciate everyone that’s pointed out hallucinations, but these were left in intentionally as artifacts of the generation process. The ‘making of’ writeup will help us understand why they happen, and to me they’re just as useful in understanding how to build agentic systems!)
If you want the most interesting read, start with Novel Components: The Innovations That Define Claude Code.
If you want the most fun read, start with An LLM's Perspective: What It's Actually Like to Receive These Instructions.
</aside>
<aside> ✉️
This project started with simple curiosity. I wanted to understand Claude Code, which to me is the best Agentic coding tool (even though the competition is close). Initially, I thought it would be straightforward—just an LLM and a few tools in a loop. I was wrong. It turned out to be far more complex, with tons of novel components I hadn't expected.
To tackle this, I worked with multiple AI subagents operating on different pieces of inference. I manually ferried questions and insights back and forth, reviewed outputs to check for hallucinations, and double-checked results.
The process involved:
What's remarkable is that this only took a day and taught me a lot. Before LLMs, this kind of analysis would have taken months—if it was possible at all. To Opus 4, who took my condensed report and transformed it into the comprehensive analysis you're about to read: thank you!
—Hrishi
</aside>
Claude Code has a number of very interesting parts:
Let’s jump in! Each heading is a link to the full section.
Why React in a terminal? What's yoga-layout doing here?
Discover the unconventional dependency choices that enable Claude Code's performance. Learn about the custom shell parser that embeds JSON in bash commands, the streaming JSON parser for partial LLM responses, and the ANR detection system borrowed from mobile development.
How messages transform through the system