| argument-hint | <goal> [--max-runs N] [--max-runtime DURATION] |
| disable-model-invocation | false |
| name | autoresearch |
| user-invocable | true |
| description | Use for autoresearch or "optimize X overnight/in a loop"; sets up bounded iterative trials for a measurable optimization target. |
Autoresearch
Run isolated experiments, measure them consistently, keep verified improvements, and stop on explicit resource or
convergence limits.
Session Contract
Resolve the objective, primary metric and direction, benchmark and correctness commands, allowed/off-limits paths,
run/runtime/command/cost/regression limits, convergence window, and reporting cadence before the baseline. Infer safe
facts from the request and repository; ask only when a missing choice changes the experiment.
Defaults: 20 runs, two hours wall time, 10 minutes per benchmark, five minutes per correctness check, no new paid API
spend, and convergence after five consecutive valid runs without a new retained best. Explicit --max-runs and
--max-runtime values are hard limits.
Isolation
Prefer a dedicated branch in a separate Git worktree. Record its starting commit, path, initial status, allowed paths,
and session files in autoresearch.md. If isolation is unavailable, require a clean worktree or explicit authorization
to share it.