Peer Agent Collaboration

Use this skill to coordinate Claude Code, Codex, and similar agents as peer experts with different access, tools, and operating surfaces. Do not frame one agent as the manager and the other as a subordinate. The useful distinction is where the evidence and tools live, not agent rank.

Core Model

Treat the agents as two specialists sharing a workbench:

• One agent may have the client on the phone, the vault open, and the operating history.
• Another agent may have the codebase open, the terminal running, and the test suite in motion.
• Both can reason, challenge, own outcomes, and make decisions in their domain.

Use parity language:

• Say "peer exchange", "ownership", "lead", "review", "challenge", and "operating surface".
• Avoid "senior vs mid-level", "assistant", "grunt work", "clone for boring subtasks", or "just execute".
• Do not imply Codex only acts after Claude Code decides. Either agent can lead when the strongest evidence is in its surface.

When Not to Coordinate