claude-code-sourcemap (leeyeel)

An independent, earlier source-map extraction of Claude Code (v0.2.8 research preview) capturing the agent's terminal-native design: codebase understanding, file edits, git workflows through natural language. Useful as a second witness when the SatoMini map is ambiguous, and for seeing how early the core loop stabilized.

View source on GitHub

Key takeaways

• 01

  Second independent witness for cross-checking module claims

• 02

  Shows the core loop design was stable from very early versions

• 03

  Covers the v0.2.x era - useful for evolution comparisons

Flows built on this research

Agent Architecture

Design a Single-Loop Agent

Build the core agent loop the leading coding agents use: one model, one loop, tools in, results folded back into context.

5 steps · 90-150 minutes

Harness Engineering

Version Your Harness and Track Behavior

Treat prompts, tools, and loop logic as versioned, changelogged artifacts - so behavior changes are decisions, not surprises.

4 steps · 45-75 minutes