What is agenteval and how do I install it?

CLI tool for linting and evaluating AI instruction files. Curl the install script, run 'agenteval lint'.

Does agenteval work with GitHub Copilot and Cursor?

Yes, supports copilot-instructions.md, .cursorrules, CLAUDE.md, AGENTS.md, and more.

Harvests your git history for AI tasks, replays with scores on correctness, precision, efficiency, conventions.

Same model, same tasks — but a 17-point performance swing from instructions alone. We've got tests for code; why hope for the best with AI prompts?

DevTools Feed Apr 03, 2026 4 min read 12 views

Instructions impact AI coding performance more than model choice — up to 17-point gaps. 𝕏
Common issues: dead file refs, token-wasting fluff, contradictions eat context and reliability. 𝕏
Agenteval lints statically and benchmarks via git history for real-world proof. 𝕏

Published by

Ship faster. Build smarter.

#AI agent testing #AI instructions #GitHub Copilot #agenteval #claude-code

Get the best Developer Tools stories of the week in your inbox — no noise, no spam.

Originally reported by dev.to