Subagent-Driven Development FAQs

Question 1

How does this differ from standard plan execution?

Accepted Answer

Unlike standard execution, this skill uses fresh subagents for every individual task to prevent context pollution and enforces a strict two-stage review process—spec compliance followed by code quality—for every change.

Question 2

Why are there two separate review stages?

Accepted Answer

The first stage ensures the implementation exactly matches the requirements (spec compliance), while the second ensures the code is maintainable and adheres to best practices (code quality).

Question 3

Can I use this for parallel task execution?

Accepted Answer

This skill is optimized for sequential execution within the same session to avoid file conflicts and ensure a clean, cohesive development history on a single branch.

Question 4

What happens if a subagent fails a review?

Accepted Answer

If a reviewer finds issues, the implementer subagent is tasked with fixing them and must pass through the review cycle again before the task can be marked as complete.

Question 5

Does this require manual intervention between tasks?

Accepted Answer

While the system allows you to answer clarifying questions from subagents, the workflow is designed to handle implementation, testing, and reviews automatically until each task is fully approved.

Subagent-Driven Development

主要功能

使用场景

Subagent-Driven Development

主要功能

使用场景