subagent-driven-development

Coordinate independent subagents to execute implementation plans with two-stage reviews.

Updated May 25, 2026

Search Tags:#automation #planning #development #subagent #ai-agent #two-stage-review #task-dispatch

Ready to run

npx skills add https://github.com/Chieji/my-skills --skill subagent-driven-development-chieji

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Chieji/my-skills/tree/main/subagent-driven-development
Command: npx skills add https://github.com/Chieji/my-skills --skill subagent-driven-development-chieji

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinate independent subagents to execute implementation plans within the same session.

Core Features & Use Cases

Fresh-subagent orchestration: dispatch a new subagent per task to avoid context pollution.
Two-stage review: enforce spec compliance first, then code quality review for each task.
Structured workflow: handles per-task questions, self-reviews, and iterative improvements, suitable for complex plan execution within a single session.

Quick Start

Dispatch a plan, then let the system allocate a fresh subagent per task and run spec and quality reviews for each one.

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 dispatch for independent development plans using AI agents?▼

To automate task dispatch for development plans, this Skill coordinates fresh independent subagents to execute isolated tasks within the same session, ensuring context pollution is avoided. It allocates a new subagent per task for rapid outcomes.

What is a two-stage review process for AI agent code generation?▼

A two-stage review process enforces spec compliance first, then evaluates code quality for each task completed by an implementer subagent. This structured workflow ensures automated completion signaling after iterative improvements.

How do I execute independent implementation tasks without context pollution across subagents?▼

You can execute independent implementation tasks without context pollution by orchestrating fresh subagents per task. This approach dispatches a new isolated subagent for each action, preventing cross-task interference within the same session.

Can I use subagent orchestration for complex plan execution within a single session?▼

Yes, you can use subagent orchestration for complex plan execution within a single session. The system handles per-task questions, self-reviews, and iterative improvements, making it suitable for managing structured multi-task workflows.

When should I not use fresh subagents for task dispatch in software development?▼

You should not use fresh subagents for task dispatch when tasks are highly interdependent rather than mostly independent. The system is designed for isolated execution and a structured two-stage review process, which may not suit tightly coupled workflows.