subagent-driven-development

Orchestrate tasks with fresh subagents and automated two-stage reviews within one session.

7|1|Updated Feb 1, 2026

Search Tags:#automation #workflow #planning #testing #development #subagent #code-review

Ready to run

npx skills add https://github.com/cloudfieldcz/cf-powers --skill subagent-driven-development-cloudfieldcz

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates end-to-end task execution by deploying fresh subagents to handle individual tasks within a single session, ensuring isolation and fast iteration through structured two-stage reviews.

Core Features & Use Cases

Fresh subagent per task to ensure isolation and reduce context pollution.
Two-stage reviews after each task: specification compliance followed by code quality.
In-session orchestration of multi-task plans with automatic handoffs to reviewers.
Suitable for end-to-end feature work parsed from a central plan.

Quick Start

Load a plan file and begin executing tasks with per-task subagents.

Frequently Asked Questions about subagent-driven-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I orchestrate multi-task development without context pollution in a single session?▼

A fresh subagent is deployed for each individual task to ensure isolation and prevent context pollution, orchestrating multi-task execution within a single session.

What is the best way to automate code review and specification compliance for structured feature work?▼

Automated two-stage reviews handle specification compliance and code quality after each task, applying to structured feature work parsed from a central plan with automatic handoffs to reviewers.

How do I manage inter-task dependencies when executing a multi-task development plan?▼

Managing inter-task dependencies is handled through in-session orchestration, coordinating independent task execution and automated handoffs between subagents from a single loaded plan file.

Can I execute structured feature work from a central plan using independent task agents?▼

Yes, structured feature work from a central plan can be executed by deploying independent task agents per task, enabling isolated execution and two-stage reviews without context pollution.

When should I use subagent orchestration for end-to-end task execution?▼

Subagent orchestration is suited for end-to-end feature work requiring isolated task execution, inter-task dependency management, and automated two-stage reviews to maintain code quality without context pollution.