subagent-driven-development

Dispatch fresh subagents per task with two-stage spec and code quality reviews.

1|1|Updated Feb 4, 2026
One-click install
npx skills add https://github.com/darthlinuxer/Agentic-Skills --skill subagent-driven-development-darthlinuxer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/darthlinuxer/Agentic-Skills/tree/main/subagent-driven-development
Command: npx skills add https://github.com/darthlinuxer/Agentic-Skills --skill subagent-driven-development-darthlinuxer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables teams to implement plans by delegating work to fresh subagents, ensuring spec compliance and code quality through two-stage reviews per task.

Core Features & Use Cases

  • Per-task subagents: Fresh agents are dispatched for each task to avoid context contamination and accelerate iteration.
  • Two-stage review: Each task undergoes a spec compliance review followed by a code quality review to ensure fit and quality.
  • Plan-driven execution: Works after a plan is created with writing-plans for complex, multi-step projects.
  • Prompts templates: Uses implementer, spec reviewer, and code quality reviewer prompts to automate workflow.

Quick Start

Use an existing implementation plan to dispatch per-task subagents, perform spec review, then code quality review, and log evidence before moving to the next 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 automate implementation plan execution with subagents?

Automate implementation plan execution by dispatching fresh subagents per task. Each subagent works through a structured workflow that enforces test-driven development and senior-developer patterns to ensure reliable iteration.

What is a two-stage review process for code quality and spec compliance?

A two-stage review process evaluates each task first for spec compliance and then for code quality. This sequential mechanism ensures the implementation meets requirements before assessing the structural integrity of the code.

How do I prevent context contamination when automating multi-step coding projects?

Prevent context contamination in multi-step projects by dispatching fresh subagents for each task. This isolation accelerates iteration and keeps the project context clean throughout the session.

Does subagent-driven development require an existing implementation plan?

Yes, this plan-driven execution approach requires an existing implementation plan. It is designed to execute complex, multi-step projects by delegating tasks to fresh subagents after the plan is created.

What's the best way to enforce test-driven development during automated task execution?

Enforce test-driven development during automated task execution by applying standardized prompts for implementers and reviewers. This ensures every dispatched subagent follows TDD and senior-developer patterns.

When should I not use fresh subagents for per-task automation?

Avoid using fresh subagents for simple, single-step tasks that do not require complex multi-step project orchestration. This approach targets complex workflows needing spec compliance and code quality reviews.