back to writing
Tag: instruction-quality
3 posts
- The State of AGENTS.md: Scoring the Agent-Makers' Own InstructionsI scored the AGENTS.md files of the 16 biggest AI agent repos with a deterministic engine. ~1.46M combined stars, zero A grades, and the repo that popularized the convention ranks 13th of 16.
- Scoring My Own MCP ContributionA CLAUDE.md I wrote was merged into modelcontextprotocol/servers. My own scorer returned 59.2/100. Where it was right, where it was structurally unfair, and what the gap to 80 would cost.
- The blindspot, fixedEarlier today I published a self-audit that named a blindspot in schliff. Hours later, the fix is up as a PR. The same CLAUDE.md now scores 61.0 instead of 59.2.