We added @karpathy -inspired coding rules from @jiayuan_jy to AGENTS.md and ran 40 @openclaw PRs through three coding agents. The result: Code quality was basically unchanged, but the agents got there with less work. Fewer tool calls, lower time and cost.

The setup: ✔️40 hand-selected PRs from OpenClaw, mid-complexity (100–300 LOC excluding tests) ✔️ Three runners: Auggie on Opus 4.7, Claude Code on Opus 4.7, Codex on GPT-5.4 ✔️ Two variants per PR: baseline AGENTS.md (~18K chars) vs. AGENTS-karpathy.md (~20.5K chars) ✔️ 6 runs per config, total 18 repeats per individual PR ✔️Scored by an LLM judge on completeness, correctness, best practices, code reuse, and unsolicited documentation

@augmentcode @karpathy @jiayuan_jy @openclaw Interesting! I am curious to see the exact content of that AGENTS.md file 👀 Where can I find it ?

From deep questions to stunning visuals - Grok does it all. Sign up and start imagining instantly.