subagent-driven-development

Dispatch parallel subagents for implementation and refactoring tasks with two-stage review.

2|7|Updated Jun 19, 2026
One-click install
npx skills add https://github.com/humanerd-drew/opencode-drewgent --skill subagent-driven-development-humanerd-drew
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/humanerd-drew/opencode-drewgent/tree/main/skills/software-development/subagent-driven-development
Command: npx skills add https://github.com/humanerd-drew/opencode-drewgent --skill subagent-driven-development-humanerd-drew

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of efficiently managing parallel development tasks by utilizing subagents for implementation and refactoring, ensuring high-quality code with automated review processes.

Core Features & Use Cases

  • Subagent Dispatch: Assigns fresh subagents for each task, ensuring clear context and reducing confusion.
  • Two-Stage Review: Includes both specification and quality assurance reviews for each task.
  • Automated Review Process: Catches issues early and maintains consistent quality checks.
  • Use Case: Ideal for large projects with many independent tasks where maintaining quality and specification compliance is crucial.

Quick Start

Dispatch a subagent for a new development task by running the command: skill("delegate_task", "Task spec", "File paths", "TDD instructions").

Frequently Asked Questions about subagent-driven-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I manage parallel development tasks without losing code review quality?

Parallel development tasks can be managed by dispatching fresh subagents for each implementation and refactoring task, ensuring clear context and running two-stage specification and quality assurance reviews to maintain high code quality.

What is the best way to automate code reviews for multiple independent software development tasks?

Automating code reviews for independent tasks is best handled by using a two-stage review process that assigns fresh subagents to each task, catching specification and quality issues early through automated batch delegation and consistent checks.

How do I dispatch a subagent for a new refactoring task?

To dispatch a subagent for refactoring, run the delegate_task command and provide clear task specifications, exact file paths, and TDD instructions to ensure the subagent has the context needed for high-quality implementation.

When should I use wave-based batch delegation for software development?

Wave-based batch delegation should be used for large projects with many independent implementation tasks where maintaining specification compliance and code quality across parallel subagents is crucial.

What specifications do I need to provide before dispatching a subagent for implementation?

Before dispatching a subagent for implementation, you need to provide clear task specifications, exact file paths, and TDD instructions to ensure the subagent executes the development task with high quality and efficiency.