Lint, benchmark, and score your AI coding instructions. Stop guessing, start measuring.
Latest release v0.8.14 · 6 Apr 2026
3 files for Claude Code and GitHub Copilot: agenteval CLAUDE.md, agenteval copilot-instructions.md, agenteval backend.instructions.md — 1,309 tokens loaded in every session.
CLAUDE.md C 1,086 tok demo/.github/copilot-instructions.md A 110 tok demo/.github/instructions/backend.instructions.md A 113 tok These files are lukasmetzler/agenteval's own configuration — they tell Claude Code and GitHub Copilot how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.