subagent-driven-development

Name: subagent-driven-development
Availability: InStock
Author: darkmatter

Dispatch fresh subagents for implementation tasks with two-stage review.

1|Updated Apr 27, 2026

Search Tags:#workflow #tdd #code review #implementation #subagents #task planning

Ready to run

npx skills add https://github.com/darkmatter/skills --skill subagent-driven-development-darkmatter

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/darkmatter/skills/tree/main/docs/00-inbox/skills/subagent-driven-development
Command: npx skills add https://github.com/darkmatter/skills --skill subagent-driven-development-darkmatter

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you execute an implementation plan without losing focus by splitting work into isolated subagent tasks and enforcing a review loop after each task.

Core Features & Use Cases

Dispatches a fresh implementer subagent for every task so context stays clean and tasks can be worked independently.
Adds two quality gates after implementation: spec compliance review first, then code quality review.
Handles question-asking, rework, and blocker escalation so the controller can keep moving without guessing.
Useful when you already have a clear plan and need to deliver multiple related code changes in the same session.

Quick Start

Use the subagent-driven-development skill to carry out the current implementation plan by assigning each task to a fresh subagent and reviewing it in the required order.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema

How do I execute a multi-step implementation plan without losing context?▼

Subagent-driven development splits implementation plans into isolated tasks, dispatching a fresh subagent for each task to keep context clean and maintain focus throughout sequential execution.

What is two-stage code review in subagent workflows?▼

Two-stage review enforces spec compliance first, then code quality, after each subagent implementation task. This sequential oversight ensures the controller validates deliverables without guessing or losing track of progress.

How do I handle blockers and questions during task planning and implementation?▼

The workflow handles question-asking, rework, and blocker escalation so the controller can keep moving. It routes questions back to the controller instead of having subagents guess, ensuring spec compliance is maintained.

Can I use subagent-driven development for bug fixes and feature work in the same session?▼

Yes, it applies to same-session execution of implementation plans, especially multi-step feature work, bug fixes, and other changes that benefit from isolated context and sequential oversight across independent tasks.

Do I need a clear implementation plan before using subagent task dispatch?▼

Yes, this workflow is most useful when you already have a clear plan and need to deliver multiple related code changes in the same session, assigning each task to a fresh subagent with enforced review.

What's the best way to track todos across independent subagent implementation tasks?▼

The workflow requires todo tracking alongside per-task implementer dispatch and two-stage review, ensuring the controller maintains visibility over task completion and escalation handling throughout the implementation plan.