subagent-driven-development

Execute development plans by dispatching AI subagents for each task.

Updated Feb 14, 2026
One-click install
npx skills add https://github.com/musuj/telegram --skill subagent-driven-development-musuj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/musuj/telegram/tree/main/.agent/skills/subagent-driven-development
Command: npx skills add https://github.com/musuj/telegram --skill subagent-driven-development-musuj

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the development process by breaking down implementation plans into independent tasks, each handled by a dedicated AI subagent with rigorous review stages.

Core Features & Use Cases

  • Task Decomposition: Automatically breaks down a development plan into manageable, independent tasks.
  • Dedicated Subagents: Assigns a fresh AI subagent for each task to prevent context pollution.
  • Two-Stage Review: Implements a spec compliance review followed by a code quality review for each task.
  • Iterative Refinement: Manages loops for fixing issues identified during reviews.
  • Use Case: Implementing a new feature from a detailed plan, ensuring each part is spec-compliant and high-quality before moving to the next.

Quick Start

Use the subagent-driven-development skill to execute the implementation plan outlined in the attached file '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 task execution from a development plan using AI subagents?

You can automate task execution by breaking down a development plan into independent tasks and dispatching a dedicated AI subagent for each one. This approach manages autonomous development workflows within a single session.

What is the best way to prevent context pollution when implementing features with AI?

The best way to prevent context pollution is assigning a fresh AI subagent to each independent task. This ensures clean context for every step, followed by a two-stage spec compliance and code quality review.

How does a two-stage review process work for AI-generated code?

A two-stage review process for AI-generated code first checks spec compliance, then evaluates code quality. It manages iterative refinement loops to fix any identified issues before moving to the next task.

Can I use agile development workflows to break down a feature plan into independent tasks?

Yes, you can use autonomous workflows to break down a feature plan into independent tasks. Each task is handled by a dedicated subagent, ensuring rigorous spec compliance and code quality through iterative reviews.

Do I need a detailed implementation plan before starting subagent-driven development?

Yes, you need a detailed implementation plan to start subagent-driven development. The Skill executes the development plan by dispatching independent AI subagents for each task outlined in the provided plan file.

Why should I use dedicated subagents for task automation instead of a single AI session?

You should use dedicated subagents for task automation to prevent context pollution across independent tasks. It ensures rigorous spec compliance and code quality through a two-stage review process for each part.