One line in AGENTS.md took coding agent pass rate from 16% to 100%
rseroter · x · 2026-11-12
Mintlify's experiment: a mint instructions CLI command alone left Claude Sonnet at a 16% pass rate (vs 20% without) because agents never ran it. Adding one pointer in the repo's AGENTS.md got 30/30 runs to execute it. Wording mattered: a generic pointer hit 66%, naming the specific task types hit 83%, and revising guidance around observed mistakes reached 100%. Task-specific built-in guidance also beat just linking to docs already indexed via llms.txt.
More from coding & agent
- Game dev workflow: AI-generated sprite sheets turned into character walk GIFs — algo_diver · 2026-11-12
- Agent reads email threads and pre-books your apartment viewing on Gcal automatically — braelyn_ai · 2026-11-12
- Alchemy + Effect hailed as a mindset shift for building software with agents — johnlindquist · 2026-11-12
- AntiFox AI Pentesting Platform Linked to Attacks That Stole AWS Production Secrets — Thionne_WTZ · 2026-11-12
- Dev builds npx driftcost CLI to check if Claude Code token usage silently shifted between Opus versions — Tough_Stay8909 · 2026-11-12
- AFK Pilot ships standalone desktop app to run coding agents without an IDE — PawelHuryn · 2026-11-12