subagent-driven-development

Dispatch subagents to execute implementation plans with two-stage reviews.

Updated Mar 5, 2026
One-click install
npx skills add https://github.com/Himanshu040604/codex-skills-setup --skill subagent-driven-development-himanshu040604
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Himanshu040604/codex-skills-setup/tree/main/assets/codex/skills/claude-import/skills/plugins/superpowers%40claude-plugins-official/skills/subagent-driven-development
Command: npx skills add https://github.com/Himanshu040604/codex-skills-setup --skill subagent-driven-development-himanshu040604

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the development process by breaking down implementation plans into independent tasks, each handled by a dedicated subagent with a rigorous two-stage review process, ensuring high quality and rapid iteration.

Core Features & Use Cases

  • Task Decomposition: Automatically breaks down a development plan into manageable, independent tasks.
  • Subagent Dispatch: Assigns a fresh subagent to each task for focused implementation.
  • Two-Stage Review: Implements a spec compliance review followed by a code quality review for each task.
  • Use Case: When you have a complex feature to build, this skill ensures each part is implemented correctly and efficiently, with automated checks at each step, preventing bugs and scope creep.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at ./plans/feature-x.md.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I automate complex feature implementation using subagents?

To automate complex feature implementation using subagents, the skill decomposes your development plan into independent tasks, dispatching a dedicated subagent to execute each one for focused implementation.

What is the two-stage code review process for iterative development?

The two-stage code review process for iterative development evaluates spec compliance first, then assesses code quality. These automated checks run after each subagent completes its assigned task to prevent bugs and scope creep.

How do I execute a development plan step by step with automated task management?

To execute a development plan step by step, point the skill to your plan file. It automatically breaks down the plan, dispatches subagents for each task, and runs automated reviews to facilitate iterative development.

Can I use subagent-driven development for large scope feature builds?

You can use subagent-driven development for large scope feature builds. It specifically targets complex features by assigning fresh subagents to manageable tasks, preventing scope creep through focused execution and automated checks.

What is the best way to prevent scope creep during iterative development?

The best way to prevent scope creep during iterative development is to use a two-stage review process. Checking spec compliance and code quality after each subagent task ensures high-quality code and maintains focused implementation.