subagent-driven-development

Execute implementation plans with independent subagents and two-stage reviews.

1|Updated Feb 18, 2026

Search Tags:#code review #development workflow #task execution #subagent #autonomous

Ready to run

npx skills add https://github.com/LiGoldragon/Mentci-AI --skill subagent-driven-development-ligoldragon

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/LiGoldragon/Mentci-AI/tree/main/.pi/skills/subagent-driven-development
Command: npx skills add https://github.com/LiGoldragon/Mentci-AI --skill subagent-driven-development-ligoldragon

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates implementation plan execution by dispatching independent subagents for each task, ensuring each step is reviewed for spec compliance and code quality before moving on.

Core Features & Use Cases

Subagent per task: Breaks down plans into manageable units executed by specialized agents.
Two-stage review: Ensures each task meets requirements and coding standards.
Use Case: Streamlines collaborative coding by parallelizing independent implementation tasks while maintaining quality control through structured reviews.

Quick Start

Initiate subagent-driven development by stating "Use the subagent-driven-development skill to execute this plan."

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 for a development workflow?▼

You can automate task execution by dispatching independent subagents for each task in a plan, followed by a two-stage review for spec compliance and code quality within your current session.

What is the best way to ensure code quality when parallelizing implementation tasks?▼

To ensure code quality during parallel task execution, apply a two-stage review process that checks each independent subagent's output for spec compliance and coding standards before moving on.

How does a subagent handle task decomposition during development?▼

A subagent handles task decomposition by taking a pre-defined implementation plan and executing each manageable unit independently, ensuring structured reviews occur after every individual task.

Do I need a pre-defined plan to start autonomous code review and execution?▼

Yes, you need a pre-defined plan and existing state before starting autonomous execution, because the subagents rely on these inputs to break down tasks and perform spec compliance checks.

Can I use autonomous subagents for collaborative coding sessions?▼

Yes, you can use autonomous subagents for collaborative coding by parallelizing independent implementation tasks while maintaining quality control through structured two-stage reviews.

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

You should not use subagent-driven development if you lack a pre-defined plan and current state, as the workflow requires these inputs to decompose tasks and execute two-stage reviews.