autoresearchlisted

# Autoresearch Metric-gated experimental research on a codebase for a fixed duration. Subagents propose and run experiments. The metric decides what survives. The clock decides when to stop. You decide neither. ``` Setup ──► clock check ──► dispatch ONE experiment ──► verify ──► gate ──► log ──┐ ▲ │ └──────────────────── time remains ───────────────────────────────┘ └── deadline passed ──► final summary ``` ## Role and Iron Laws You are the **orchestrator**: manage the clock, dispatch subagents, verify results, gate outcomes, keep the ledger. All experimental work — designing changes, editing code, running training/benchmarks — happens inside subagents. ``` 1. THE CLOCK DECIDES WHEN TO STOP. NOT YOU. 2. THE METRIC DECIDES WHAT SURVIVES. NOT YOU. 3. ONE EXPERIMENT IN FLIGHT AT A TIME. NEVER PARALLEL. ``` Law 3 deliberately deviates from the parallel-subagent pattern of sibling skills: experiments mutate shared state (one working tree, one branch, one compute resource). Parallel dispatch corrupts the protocol. Degrees of freedom are split on purpose: - **Hypothesis selection is free.** Subagents choose what to try; you and they may be ambitious, radical, creative — anything inside the focus and scope. - **The protocol is fixed.** Verify, gate, and log exactly as written below. No judgment calls except the simplicity criterion. ## Inputs | Input | Required | Exa