subagent-driven-development

Dispatch a fresh subagent per task with two-stage spec and code-quality reviews.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/sachio222/based-stack --skill subagent-driven-development-sachio222
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/sachio222/based-stack/tree/main/subagent-driven-development
Command: npx skills add https://github.com/sachio222/based-stack --skill subagent-driven-development-sachio222

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-driven development solves the challenge of executing implementation plans with independent tasks in a single session by ensuring isolated context and staged reviews.

Core Features & Use Cases

  • Fresh subagent per task to avoid context pollution
  • Two-stage review: spec compliance then code quality
  • Clear per-task development workflow with review loops
  • Structured prompts for implementers, spec reviewers, and code-quality reviewers

Quick Start

Dispatch an implementer subagent for the first task and follow the per-task review loop to complete tasks sequentially.

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 independent implementation tasks without context pollution?

To prevent context pollution during development, dispatch a fresh subagent for each independent task. This approach isolates context and enforces staged reviews to maintain code quality throughout the session.

What is the two-stage review process for subagent task dispatch?

The two-stage review process evaluates spec compliance first, then checks code quality. This review loop runs after each task is executed by an implementer subagent to ensure structured outputs meet requirements.

How do I set up a subagent-driven development workflow?

Setting up this workflow requires explicit prompts and templates for implementers, spec reviewers, and code-quality reviewers. Dispatch an implementer subagent for the first task and follow the per-task review loop sequentially.

Does subagent-driven development work for tasks with shared dependencies?

Subagent-driven development is designed for sessions with independent tasks. It requires isolated context for each task, making it unsuitable for tasks that share heavy dependencies or require overlapping execution contexts.

Why use fresh subagents for code quality and spec compliance instead of a single agent?

Using fresh subagents for code quality and spec compliance prevents context accumulation from previous tasks. This isolation ensures unbiased reviews and maintains strict adherence to defined execution workflows and templates.