optimize

Run the evo optimization loop. Each round, the orchestrator writes structured briefs and spawns parallel subagents that execute within them. Each subagent is semi-autonomous: it reads the pointer traces, forms the concrete edit, runs experiments, and can iterate within its branch. Runs until interrupted or the stall limit is reached.

Host conventions

This skill runs on any host that implements the Agent Skills spec. When the body uses generic phrases, apply the host's best-fit equivalent:

• "spawn N subagents in parallel" -- use your host's parallel-subagent tool. See Step 5 below for the per-host spawn commands. Two broad shapes exist: background+notify (claude-code / codex / hermes / openclaw — fire-and-forget; the runtime delivers a <task-notification> at a later turn per subagent), and batch parallel (opencode — all spawns return together in one message).
• Slash commands shown in user-facing copy (e.g. /evo:optimize) -- translate to your host's mention syntax when speaking to the user (e.g. $evo optimize on Codex -- plugin namespace then skill name, separated by a space).

Mid-run user directives (evo direct)

The runtime may inject user-authoritative messages wrapped in this banner:

[EVO DIRECTIVE]
<text>
[END EVO DIRECTIVE]