Why markdown plans break when you run multiple AI agents

说明与用途

通过共享 Markdown 列表协调多个 AI 代理会导致冲突和历史丢失。解决方案是 MCP 服务器（workstream‑mcp），它提供原子声明、过期、转换验证、审查和不可变历史记录。

问题

Coordinating multiple AI coding agents via a shared markdown checklist leads to conflicts, stale claims, and lost history.

结果

Using workstream‑mcp eliminates duplicate task claims, ensures timely claim expiry, enforces legal state transitions, provides review workflow, preserves immutable history, and offers real‑time visibility, enabling reliable multi‑agent coordination.

工作流

• 1. Agent reads plan via MCP tool call
• 2. MCP claims next task using SELECT … FOR UPDATE SKIP LOCKED within a transaction
• 3. Agent performs work and updates task status
• 4. MCP enforces legal transitions and dependency rules
• 5. Review step: developer agent submits, reviewer approves or rejects
• 6. MCP records every change as an event in an append‑only log
• 7. Notifications sent through an outbox to GitHub/Slack
• 8. Dashboard displays current claims, expiries, and dependencies

证据

Most of us coordinate AI coding agents the same way: a markdown file in the repo with a checklist.

来源

Two agents pick the same item.

来源

Claims run in one Postgres transaction with SELECT … FOR UPDATE SKIP LOCKED.

来源

A test suite runs exactly that.

来源

Every change writes an event. Database triggers block updates and deletes on the event log, so the history can't be rewritten after the fact.

来源