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 3.1 Pro high + Grok 4.5 + GPT-5.6 Luna; refiners qwen3.8-max-preview + DeepSeek V4 Pro + Claude Opus 5 high) before producing a final…