drivelineresearch

Set up, resume, inspect, or pause a measured experiment loop in Claude Code or Codex. Use when asked to run autoresearch or iteratively optimize a named benchmark. Reviewing this plugin alone does not start an experiment loop.

Run a non-trivial planning task through a layered ensemble of frontier models from distinct labs (proposers Gemini 4 Argon high + Grok 4.7 + GPT-6 Luna; refiners DeepSeek V4.1 Flash + Claude Opus 5.5 high) before producing a final implementation plan. The…