subagent-driven-development

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

Updated Mar 11, 2026
One-click install
npx skills add https://github.com/sartoris-digital/pi-superpowers --skill subagent-driven-development-sartoris-digital
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/sartoris-digital/pi-superpowers/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/sartoris-digital/pi-superpowers --skill subagent-driven-development-sartoris-digital

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the execution of implementation plans by intelligently dispatching specialized subagents for each task, ensuring high-quality, iterative development within a single session.

Core Features & Use Cases

  • Task Delegation: Assigns individual tasks from a plan to dedicated "implementer" subagents.
  • Two-Stage Review: Enforces rigorous quality control through sequential spec compliance and code quality reviews by separate subagents.
  • Iterative Improvement: Manages feedback loops, allowing implementer subagents to address review findings and re-submit for verification.
  • Use Case: When working on a complex feature, use this Skill to break down the implementation plan into manageable tasks, with each task being developed, reviewed for spec adherence, and then checked for code quality by specialized AI agents, ensuring a robust and well-tested outcome.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan located at ./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 automate code review and spec compliance for complex feature implementation plans?

Automating code review for implementation plans is done by dispatching a fresh subagent per task to execute a two-stage review process, verifying spec compliance and code quality iteratively within a single development session.

What is two-stage review in subagent-driven development?

Two-stage review is a quality control mechanism where separate specialized subagents sequentially perform spec compliance verification and code quality assessment on implemented tasks before final approval.

How do I execute a feature plan using subagents for iterative development?

To execute a feature plan, assign individual tasks to dedicated implementer subagents, manage their feedback loops, and route completed work through sequential spec and code quality reviews for iterative improvement.

Can I use subagent-driven development for TDD and iterative improvement?

Yes, subagent-driven development supports TDD and iterative improvement by managing feedback loops that allow implementer subagents to address review findings and re-submit tasks for verification.

Does subagent-driven development work without external dependencies?

Yes, subagent-driven development operates without external dependencies, managing task execution, spec compliance verification, and code quality assessment entirely within a single session.