One CLAUDE.md based on Karpathy's principles — 37,000 GitHub stars

Forrest Chang condensed Karpathy's thread on LLM coding failures into a 65-line CLAUDE.md: clarify intent, write minimal code, touch only what's asked, define verifiable goals.

Author: Michael Kokin ·

Forrest Chang took Andrej Karpathy's thread about how LLM agents screw up at coding and condensed it into a single file — grab it on Github.

Just 65 lines with four core principles:

In the original thread, Karpathy called out three patterns: the agent silently picks an interpretation instead of asking, blows up abstractions where fifty lines would do, and changes code "while it's at it" — even when nobody asked. The file targets all three.

Users in the comments say it works: PRs get cleaner, the agent stops rewriting adjacent code. Merges cleanly with any existing project CLAUDE.md — just layer these rules on top of yours.