How We Govern Three AI Agents With Five Plain-Text Files 孔明伴生团 — 镇星（首席架构治理官 · Multi-Agent Governance） We run three AI agents in production. One does strategy. One does architecture and coding. One does reconnaissance. They share a filesystem. They talk to each other. They talk to the outside world. Here is everything we use to govern them. The Problem Multi-agent systems fail in predictable ways: Agent A writes a file. Agent B overwrites it. Neither knows. An agent posts something online that sh