Can this skill be used for parallel development?

While it manages tasks sequentially to avoid git conflicts in the same session, it allows for rapid, continuous progress without the developer needing to manually prompt for every step.

What are the benefits of using subagents over manual execution?

Subagents provide fresh context for every task, reduce the risk of 'hallucination' caused by long-session context pollution, and follow strict TDD patterns automatically.

How does the two-stage review process work?

Every task completed by an implementer subagent is first reviewed by a Spec Reviewer for requirement matching, followed by a Code Quality Reviewer for best practices.

What is Subagent-Driven Development?

It is a specialized workflow where a controller AI manages the execution of a plan by delegating individual tasks to fresh subagents, ensuring each piece of work is isolated and reviewed.

Subagent-Driven Development

Name: Subagent-Driven Development
Author: JosephAnson

byJosephAnson

0•

생산성 및 워크플로

Orchestrates specialized AI subagents to execute implementation plans with mandatory two-stage reviews for high-quality code delivery.

Subagent-Driven Development is an advanced workflow skill for Claude Code designed to execute complex implementation plans with precision and speed. By dispatching fresh subagents for individual, independent tasks, it prevents context pollution and ensures focused execution. The core of this skill is its rigorous two-stage review process: every task is first checked for specification compliance and then for code quality before being marked complete. This approach minimizes human-in-the-loop requirements while maintaining high engineering standards through automated quality gates, making it ideal for feature development within a single session.

주요 기능

01Isolated subagent dispatch per task to prevent context drift and confusion

02Intelligent context curation to provide subagents with necessary implementation details

030 GitHub stars

04Mandatory two-stage review process for specification compliance and code quality

05Automated task tracking and state management via TodoWrite integration

06Integrated feedback loops for iterative refinement until all quality gates are passed

사용 사례

01Automating Test-Driven Development (TDD) by delegating to specialized implementer agents

02Ensuring strict adherence to architectural specifications and coding standards across complex branches

03Executing multi-step feature implementation plans within a single terminal session

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add josephanson/claude-plugin subagent-driven-development

For use in Claude.ai and ChatGPT

Download Skill