/optimize — Autonomous Optimization v2 Run an autonomous optimization loop against any target . Two modes: - Metric mode — code targets with a shell command that produces a number (the original) - Eval mode — skills, prompts, agents, or any text target judged by LLM-as-judge binary evals The agent modifies the target, measures the result, keeps improvements, discards failures, and repeats. Inspired by Karpathy's autoresearch and extended with LLM-as-judge evaluation. Invocation Metric Mode (code targets) Eval Mode (skill/prompt/agent targets) In eval mode, the system automatically: 1. Detects…