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. Two delivery shapes:
  • Background+notify (claude-code / codex / hermes / openclaw): fire-and-forget; the runtime delivers a completion notification at a later turn when each subagent finishes. Per host: claude-code -> wrap each spawn in Bash(run_in_background=true) so the runtime notifies on completion; codex -> non-blocking subagent; hermes -> terminal(background=true); openclaw -> sessions_spawn deliver:false.
  • Batch parallel (opencode): fire N task calls in ONE assistant message; they run concurrently in child sessions; all tool_results return together when the slowest finishes. Plan all parallel work (including non-task tools) in that one message — opencode cannot interleave reasoning across turns while subagents run. Respect the host's concurrency cap; batch if N exceeds it.
• 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).
• evo dispatch (optimization subagents only, host-specific). On claude-code, the optimization subagents in step 5 are launched via evo dispatch run wrapped in Bash(run_in_background=true) — the dispatch blocks until its child finishes, the bash tool runs in the background, and the runtime delivers a completion notification per subagent at later turn boundaries. This shares an explorer's KV cache across siblings of the same parent (~99% prefix reuse). On every other host (codex, opencode, openclaw, hermes, generic), evo dispatch is unsupported and exits 2 with guidance -- step 5 stays on the host's parallel-Task primitive there. The scan sub-agents in step 3 always use the host's parallel-Task tool regardless of host (they don't allocate experiments, so fork-cache doesn't apply).

Configuration

These defaults can be overridden via arguments: /optimize [subagents=N] [budget=N] [stall=N]