Genetic exploration of solution spaces for AI coding agents (Claude Code, Gemini CLI, GitHub Copilot, OpenCode) — gather a verifiable objective, evolve variants, apply the winner.
Skill Claude CodeCodex
Apply phase of an agent evolution — diff the winner workspace against the live repo, get explicit user confirmation, copy files in, optionally re-run gates against the live tree. Writes applied. Requires winner set by /run-agent-evolution.
Skill Claude CodeCodex
Capture phase of an agent evolution — discuss the objective, gates, rubric, scope, and budget; write .agents/evolutions/ - /{evolution.yaml, EVOLUTION.md} only on explicit user agreement. Pairs with /run-agent-evolution (next) and /apply-agent-evolution (later).
Skill Claude CodeCodex
Run phase of an agent evolution — plan a batch of up to budget.parallel variants, dispatch sub-agents in parallel to materialize and evaluate them, learn from results, repeat until budget / wall-clock / plateau. Writes winner on a clean stop. Requires an evolution captured via /new-agent-evolution…