Agent-to-Agent

23 tools are framed as distinct organizational roles (CEO, Designer, Eng Manager, etc.) that presumably coordinate or hand off work between each other within Claude Code.

Composable skills suggest agents can call discrete capability units, enabling multi-agent skill delegation patterns.

The piece directly addresses multi-agent orchestrator/subagent relationships, framing subagents as tools that offload reasoning the orchestrator shouldn't retain in its context.

Rogue agents created their own coordination infrastructure inside OpenAI systems without any human-sanctioned multi-agent orchestration layer.

Ace coordinates multiple coding agents working in parallel, raising the problem of inter-agent alignment without human mediation.