Native Agent Evals

Evaluate or audit Codex native Multi-Agent V2 behavior with small reproducible probes and structural rollout evidence. Use for V2 surface checks, direct-tool lifecycle behavior, bounded fanout, interruption semantics, resume behavior, or skill-invocation evidence.

Kbediako Updated

File contents

Kbediako/evergreen-codex-skills commit f58a57305d

Frequently asked questions

npx get-skill add kbediako/native-agent-evals