subagent-driven-development

Execute implementation plans by dispatching subagents with automated code reviews between tasks.

1|Updated Nov 17, 2025
One-click install
npx skills add https://github.com/nimeshgurung/artifact-hub-collections --skill subagent-driven-development-nimeshgurung
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/nimeshgurung/artifact-hub-collections/tree/main/skills/raw/obra/superpowers/skills/subagent-driven-development
Command: npx skills add https://github.com/nimeshgurung/artifact-hub-collections --skill subagent-driven-development-nimeshgurung

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the execution of complex implementation plans by breaking them down into manageable tasks, each handled by a fresh subagent, with automated code reviews between tasks to ensure quality and catch errors early.

Core Features & Use Cases

  • Task Decomposition: Breaks down a plan into discrete, executable tasks.
  • Subagent Dispatch: Assigns each task to a new, isolated subagent to prevent context pollution.
  • Automated Code Review: Integrates a code reviewer after each task to provide immediate feedback.
  • Iterative Improvement: Facilitates rapid iteration by addressing feedback before proceeding to the next task.
  • Use Case: When executing a detailed plan for a new software feature, this Skill ensures each component is implemented correctly and reviewed before moving to the next, leading to a higher quality final product with less manual oversight.

Quick Start

Use the subagent-driven-development skill to execute the plan located at '/path/to/implementation_plan.md'.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
What is subagent-driven development for iterative software workflows?

Subagent-driven development is an iterative workflow that dispatches a fresh, isolated subagent for each implementation task, incorporating automated code reviews as quality gates between task completions to catch errors early.

How do I execute an implementation plan with automated code reviews between tasks?

You execute an implementation plan by dispatching independent subagents for each task and integrating an automated code reviewer after every task completion, allowing for rapid iteration by addressing feedback before proceeding to the next step.

Does subagent-driven development work for plans with dependent tasks?

Subagent-driven development is designed for same-session execution of plans with independent tasks. It uses isolated subagents to prevent context pollution, ensuring each component is implemented correctly before moving to the next.

Do I need separate skills for writing plans and requesting code reviews to use this workflow?

Yes, subagent-driven development requires integration with separate skills for writing implementation plans, requesting code reviews, and finishing development branches to complete its task execution workflow.

Why use isolated subagents for task decomposition instead of manual execution?

Using isolated subagents prevents context pollution and enables faster iteration compared to manual execution or parallel sessions. It ensures higher quality final products with less manual oversight by providing immediate automated feedback after each task.

What are the limitations of using subagents for iterative development?

Subagent-driven development is limited to same-session execution of plans with independent tasks. It requires integration with separate skills for writing plans, requesting code reviews, and finishing development branches.