Andrej Karpathy's CLAUDE.md Quietly Doubles to Ten Rules — Adds a 'Self-Check Protocol' for Agentic Coding Loops

TechTimes·high signal

A document attributed to Karpathy circulating on X this week expands the famous four-rule community CLAUDE.md template to ten, adding rules for verification-before-fixing, debugging discipline, dependency hygiene, and named failure modes that agent loops should self-recognize. One builder writeup claims the additions cut Claude Code's error rate from 41% to 11%. For builders, the shift is from 'prompt better' to 'engineer the loop' — the rules are guardrails for autonomous agents, not just style hints.