subagent-driven-development

Dispatch subagents per task with sequential spec and quality reviews.

8|1|Updated Mar 1, 2026

Search Tags:#tdd #code review #git workflow #subagents #spec compliance #implementation plans

Ready to run

npx skills add https://github.com/JoeCP17/LLM-Dot-files --skill subagent-driven-development-joecp17

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/JoeCP17/LLM-Dot-files/tree/main/claude/skills/superpowers/subagent-driven-development
Command: npx skills add https://github.com/JoeCP17/LLM-Dot-files --skill subagent-driven-development-joecp17

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-driven development eliminates slow, error-prone implementation cycles by breaking an execution plan into independent tasks and running each through a tight implementer → spec review → quality review loop.

Core Features & Use Cases

Fresh implementer per task: dispatches a dedicated implementer subagent for each task to avoid cross-task context confusion.
Two-stage review checkpoint: performs spec compliance review first, then code quality review, preventing both missing requirements and unwanted extras.
Iteration-safe completion: loops reviewer feedback into fixes until both spec and quality are approved, then records completion and proceeds.

Quick Start

Use this skill when you have an implementation plan with mostly independent tasks and you want to execute them in the current session using subagents with mandatory two-stage reviews per task.

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 parallel subagents?▼

To execute an implementation plan with parallel subagents, this skill dispatches a fresh implementer per task and enforces sequential spec compliance and code-quality reviews, looping fixes until both approve before proceeding to a final code review.

What is subagent-driven development and how does it work?▼

Subagent-driven development is a plan execution method that breaks an implementation plan into independent tasks, running each through a tight implementer, spec review, and quality review loop to eliminate slow, error-prone cycles and avoid cross-task context confusion.

How do I enforce spec compliance during code generation?▼

You enforce spec compliance during code generation by applying a two-stage review checkpoint that performs a dedicated spec compliance review first to catch missing requirements, followed by a code quality review to prevent unwanted extras.

Can I use subagent-driven development for iterative TDD improvements?▼

Yes, you can use this approach for iterative test-driven development improvements because it is explicitly designed for contexts where iterative improvements are expected, looping reviewer feedback into fixes until both spec and quality reviews grant approval.

When should I not use subagents for implementation plans?▼

You should not use subagents for implementation plans when your tasks are heavily interdependent, as this method applies specifically to executing plans where tasks are largely independent and can be dispatched to fresh implementers without cross-task context confusion.

What's the best way to automate code review in a git workflow?▼

The best way to automate code review in a git workflow here is to run a two-stage review per task and conclude with a final code review for the entire implementation, ensuring both spec compliance and code quality are validated before completion.