使用PRD进行规划并将任务委托给成本更低的代理
Plan with PRDs and delegate tasks to cheaper agents
完成Claude Code，Claude。一位开发者使用高级代理编写PRD，将其拆分为任务列表，并将工作委托给生产流程中的成本更低的代理.
做了什么
The commenter described an internal setup with two systems: a task-based workflow that enforces TDD and can run multi-agent flows with git trees, plus persistent memory with hooks and house-style rules. Their day-to-day process is to work with a high-level agent like Opus to create a PRD, break it into a task list, and then hand implementation work to cheaper agents; they also said they are building their own Python orchestrator to call Haiku or other agents by API.
效果如何
The source gives no hard performance numbers or business results. It frames the approach as an actively evolving internal workflow rather than a finished system, with the user still building the harness around it.
值得注意
The practical catch is that this depends on custom infrastructure the commenter created, including task enforcement, persistent memory, and an in-progress orchestrator.
试试这个 Prompt
I want to build [feature or project] in [repo path]. First write a short PRD covering goals, scope, and acceptance criteria, then split it into small, independent tasks in a TASKS.md file with clear done criteria for each. Stop and show me the PRD and task list so I can review it before anything is implemented, so I can hand the tasks to a cheaper model.