subagent-driven-development

Execute implementation plans by dispatching subagents with two-stage reviews.

4|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/heyzude/skills_for_codex --skill subagent-driven-development-heyzude
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/heyzude/skills_for_codex/tree/main/superpowers/subagent-driven-development
Command: npx skills add https://github.com/heyzude/skills_for_codex --skill subagent-driven-development-heyzude

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 fresh subagent with rigorous, multi-stage reviews to ensure both spec compliance and code quality.

Core Features & Use Cases

  • Task Decomposition: Executes implementation plans by dispatching a dedicated subagent for each task.
  • Two-Stage Review: Implements a robust review process after each task: first, spec compliance, then code quality.
  • Use Case: When you have a complex feature to build with a clear implementation plan, this Skill ensures each part is developed correctly and efficiently without manual oversight between steps.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at ./docs/plans/feature-plan.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 execute an implementation plan with automated task isolation?

You execute an implementation plan by dispatching a dedicated subagent per task, ensuring task isolation and spec adherence without manual oversight between development steps.

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

The two-stage review process evaluates each completed task first for spec compliance, then for code quality, ensuring high-quality automated subagent interactions within a single development session.

How do I ensure code quality when breaking down complex features into independent tasks?

You ensure code quality by dispatching a fresh subagent for each decomposed task, followed by a rigorous multi-stage review loop that checks both spec compliance and code quality automatically.

Can I use subagent-driven development for software workflows without manual code review?

Yes, this Skill handles software development workflows requiring high-quality iterative code generation by applying automated subagent interactions and review loops to ensure task isolation and spec adherence.

What are the limitations of using subagents for task execution in a single session?

This approach is limited to single session iterative code generation and requires a clear implementation plan upfront, meaning it does not handle initial planning or multi-session project management.