Does this skill support Test-Driven Development (TDD)?

Yes, the workflow explicitly instructs implementation subagents to follow TDD practices, ensuring every task is verified by tests before passing to the review stage.

What is Subagent-Driven Development?

It is a specialized Claude Code workflow that dispatches independent subagents to execute specific tasks from a plan, followed by structured, multi-stage quality reviews.

Why use subagents instead of one long session?

Subagents provide a fresh, clean context for each task. This prevents 'context pollution' or confusion that can accumulate during long, complex chat histories, leading to more accurate code.

How does the two-stage review process work?

Every task is first reviewed by a subagent for 'Spec Compliance' to ensure all requirements are met, and then by a 'Code Quality' subagent to ensure the implementation is clean and maintainable.

Subagent-Driven Development

Name: Subagent-Driven Development
Author: pur3v4d3r

bypur3v4d3r

•

Productivity & Workflow

Executes complex implementation plans by dispatching specialized subagents for per-task execution and two-stage quality reviews.

Subagent-Driven Development is a sophisticated workflow skill designed for Claude Code to execute multi-step implementation plans within a single session. It operates by breaking down plans into independent tasks and dispatching a fresh 'implementer' subagent for each, followed by a rigorous two-stage review process: first for specification compliance and then for code quality. This method eliminates context pollution, ensures high-quality output through automated feedback loops, and accelerates development by maintaining a continuous workflow without the need for manual handoffs or context switching.

Key Features

01Same-session execution for rapid iteration and zero context-switch overhead

021 GitHub stars

03Two-stage review protocol (Specification Compliance then Code Quality)

04Integrated Test-Driven Development (TDD) for every subtask

05Fresh subagent isolation per task to prevent context pollution

06Automated task tracking and progress management via TodoWrite

Use Cases

01Orchestrating complex refactoring tasks that require isolated execution and review

02Executing multi-step feature plans with independent technical requirements

03Maintaining high code standards through automated multi-stage quality gates

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add pur3v4d3r/pur3-pkb-codebase subagent-driven-development

For use in Claude.ai and ChatGPT

Download Skill