subagent-driven-development

Dispatch fresh subagents for isolated implementation tasks with two-stage reviews.

4|1|Updated Nov 1, 2025
One-click install
npx skills add https://github.com/xtrm-dev/specialists --skill subagent-driven-development-xtrm-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/xtrm-dev/specialists/tree/main/.xtrm/skills/optional/architecture-design/subagent-driven-development
Command: npx skills add https://github.com/xtrm-dev/specialists --skill subagent-driven-development-xtrm-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you execute implementation plans without polluting your main session with task-level context, so you can coordinate work cleanly and keep momentum on complex changes.

Core Features & Use Cases

  • Fresh subagent per task: Dispatch a dedicated implementer for each independent task so work stays isolated and focused.
  • Two-stage review loop: Validate every change with a spec compliance review first, then a code quality review.
  • TDD-friendly execution: Guide subagents to implement, test, self-review, and fix issues before handing work back.
  • Best for plan execution: Use it when you already have a plan and want reliable, checkpointed delivery across multiple tasks.

Quick Start

Use this Skill to execute the current implementation plan by assigning each independent task to a fresh subagent and reviewing the result in two stages before marking it complete.

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 implementation tasks without polluting my main session context?

You can execute implementation plans by dispatching a fresh subagent for each task. This isolates task-level context, keeping your main session clean while coordinating complex changes across independent tasks.

What is the best way to ensure focused code review during plan execution?

Structured review checkpoints ensure focused code review during plan execution. After a subagent implements a task, the work passes through a spec compliance review and then a code quality review before completion.

Can I use TDD-friendly workflows with isolated subagents?

Yes, subagent workflows support TDD-friendly execution. The dedicated implementer is guided to implement, test, self-review, and fix issues before handing the completed work back for checkpoint validation.

How do subagents handle independent implementation tasks in a same-session workflow?

Subagents handle independent tasks by dispatching a fresh implementer for each item. The coordinator manages the review order, ensuring spec compliance and code quality are validated before marking each task complete.

When should I use a two-stage review loop for implementation plans?

Use a two-stage review loop when executing implementation plans that require reliable, checkpointed delivery. It validates every change first against the spec, then for code quality, ensuring focused implementation across multiple independent tasks.