subagent-driven-development

Dispatch fresh subagents per task with two-stage review and merge.

Updated Dec 15, 2025
One-click install
npx skills add https://github.com/scruffydan/AI-Agents --skill subagent-driven-development-scruffydan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/scruffydan/AI-Agents/tree/main/source/skills/subagent-driven-development
Command: npx skills add https://github.com/scruffydan/AI-Agents --skill subagent-driven-development-scruffydan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates execution of implementation plans by dispatching a fresh subagent per task and applying a two-stage review.

Core Features & Use Cases

  • Fresh subagent per task isolates context and accelerates iterative development.
  • Two-stage review after each task ensures spec compliance and code quality.
  • Use Case: When you have a plan with multiple independent tasks, this Skill orchestrates them in a single session with auditable progress.

Quick Start

Use the subagent-driven-development skill to dispatch the first task from your plan and observe the per-task workflow.

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 implementation plan execution with per-task subagents?

Automating implementation plan execution with per-task subagents involves dispatching a fresh subagent for each task and applying a two-stage review for spec compliance and code quality. This orchestrates independent tasks sequentially with auditable progress.

What is subagent-driven development workflow for sequential tasks?

Subagent-driven development workflow is an orchestration method that isolates context by dispatching a fresh subagent per task. It enforces a defined workflow with per-task implementers and reviewer subagents, finishing with a final merge step.

Can I run independent development tasks sequentially with automated code review?

Yes, you can run independent development tasks sequentially with automated code review. This skill orchestrates tasks in a single session, applying automatic spec compliance and code-quality checks after each task completes.

How does prompt-driven subagent orchestration maintain code quality?

Prompt-driven subagent orchestration maintains code quality by applying a two-stage review after each task. Fresh subagents isolate context for implementation, while reviewer subagents enforce spec compliance before the final merge step.

What's the best way to orchestrate independent implementation plans sequentially?

The best way to orchestrate independent implementation plans sequentially is using a skill that dispatches fresh subagents per task. This approach isolates context, accelerates iterative development, and ensures automatic spec compliance checks.

When should I not use subagent-driven development for task execution?

You should not use subagent-driven development for task execution when tasks are highly interdependent. This skill is designed for sessions where tasks are mostly independent and must run sequentially with isolated context.