subagent-driven-development

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

9|Updated Aug 12, 2025
One-click install
npx skills add https://github.com/shekohex/dotai --skill subagent-driven-development-shekohex
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/shekohex/dotai/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/shekohex/dotai --skill subagent-driven-development-shekohex

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the development process by enabling rapid iteration on tasks within a single session, ensuring quality through automated code reviews between each step.

Core Features & Use Cases

  • Task-by-Task Execution: Implements a plan by assigning each task to a fresh subagent, preventing context pollution.
  • Automated Code Reviews: Integrates a code reviewer after each task to catch issues early.
  • Fast Iteration: Minimizes context switching and human-in-the-loop delays for quicker development cycles.
  • Use Case: Developing a new feature where the plan has several independent sub-tasks. This Skill allows you to execute each sub-task, get immediate feedback, and fix issues before moving to the next, all within the same AI session.

Quick Start

Use the subagent-driven-development skill to execute the plan located at /path/to/your/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 reviews between development tasks in a single session?

Task execution is managed by assigning each independent task to a fresh subagent within the current session. This prevents context pollution and ensures fast iteration cycles while maintaining development quality.

How does subagent-driven development prevent context pollution during feature implementation?

Subagent-driven development prevents context pollution by assigning each independent task to a fresh subagent. This isolates the execution environment, ensuring fast iteration cycles without residual context affecting subsequent development steps.

Can I execute an implementation plan with multiple independent sub-tasks using automated reviews?

Yes, you can execute an implementation plan by dispatching its independent sub-tasks to fresh subagents. Automated code reviews are integrated between tasks to ensure quality, catch issues early, and enable fast iteration within the same session.

Does test-driven development work with rapid subagent task execution?

Test-driven development principles are required when subagents execute tasks. This ensures quality is maintained during rapid development cycles, and automated code reviews validate the test-driven output before proceeding to the next task.

What are the limitations of using fresh subagents for continuous integration and development workflows?

A limitation of using fresh subagents is that each task must be highly independent to avoid context loss between steps. Complex, highly interdependent tasks may not benefit from this isolated execution and rapid iteration approach.