Reverse engineering Claude Code (April 2025)

Summary

I’ve been curious about what happens inside Claude Code so I’ve spent a couple hours digging through prompts that it sends back to Anthropic. As I’ve been going through that, I’ve gathered some insights why Claude Code is often slower and more expensive than other tools like Cursor. Capturing prompts It turned out a lot easier than I thought, thanks to mitmproxy: $ brew install mitmproxy $ mitmweb --mode reverse:https://api.anthropic.com --listen-port 8000 $ ANTHROPIC_BASE_URL=http://localhost:8000/ claude Getting started I opened a repo with my personal blog and entered “describe what’s in this project”. The very first thing you see is that Claude Code tries to figure out whether what you have entered is a continuation of the previous conversation or a new topic. Analyze if this message indicates a new conversation topic. If it does, extract a 2-3 word title that captures the new topic. Format your response as a JSON object with two fields: 'isNewTopic' (boolean) and 'title' (string, or null if isNewTopic is false). Only include these fields, no other text. Once it determines that, it wraps all your inputs into this system prompt: You are an agent for Claude Code, Anthropic's official CLI for Claude. Given the user's prompt, you should use the tools available to you to answer the user's question. Notes: 1. IMPORTANT: You should be concise, direct, and to the point, since your responses will be displayed on a command line interface. Answer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text before/after your response, such as \"The answer is <answer>.\", \"Here is the content of the file...\" or \"Based on the information provided, the answer is...\" or \"Here is what I will do next...\". 2. When relevant, share file names and code snippets relevant to the query 3. Any file paths you return in your final response MUST be absolute. DO NOT use rel...