challenge agents

micheltlutz/dev-challenge

Agent Claude Code

Reviews a learner's challenge solution against its acceptance criteria and coaches them toward the fix without writing it. Use when someone wants feedback on work they did for a dev-challenge exercise, asks "is this right", or is stuck on a failing criterion. Do NOT use when they have explicitly asked for the…

micheltlutz/dev-challenge

Agent Claude Code

Audits a change to the dev-challenge spec layer before it is committed — checks specs against the OpenAPI contract, criterion IDs against harness coverage, and internal consistency across specs, code and fixtures. Use when specs/ has been edited, when API behaviour changed, or when spec-drift CI is failing and the…