jeremylongshore/intent-eval-lab

Vendor-neutral research umbrella for measuring AI plugin, agent, and MCP server quality across CLI runtimes (Claude Code, Gemini CLI, Copilot CLI, Codex CLI).

Latest release v0.3.0 — intent-eval-lab v0.3.0 · 8 Jun 2026

5 files for Claude Code, Codex and OpenCode: PreCompact, SessionStart, intent-eval-lab, intent-eval-lab AGENTS.md and 1 more — 6,428 tokens loaded in every session.

2Stars on the repository
5Files it configures its agents with
6,428Tokens loaded in every session
3Agents configured

Instructions

Settings

Hooks

These files are jeremylongshore/intent-eval-lab's own configuration — they tell Claude Code, Codex and OpenCode 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.