Fast, robust, configurable agent evals
Latest release v0.5.6 · 22 May 2026
3 files for Claude Code and Codex: agent-definition-creator, suite-converter, suite-creator .
.agents/skills/agent-definition-creator/SKILL.md A 75 tok .agents/skills/suite-converter/SKILL.md A 61 tok .agents/skills/suite-creator/SKILL.md A 59 tok These files are Margin-Lab/evals's own configuration — they tell Claude Code and Codex 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.