subagent-driven-development

Coordinates isolated subagent executions with two-stage spec and quality review gates for software delivery tasks.

Updated Oct 16, 2025
One-click install
npx skills add https://github.com/Axeloooo/TheDataBay --skill subagent-driven-development-axeloooo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Axeloooo/TheDataBay/tree/main/.agents/skills/subagent-driven-development
Command: npx skills add https://github.com/Axeloooo/TheDataBay --skill subagent-driven-development-axeloooo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you execute an implementation plan reliably by breaking work into focused subagent tasks and enforcing two-stage review after each task.

Core Features & Use Cases

  • Fresh subagents per task to prevent context pollution and keep implementations focused.
  • Two-stage review per task: first verify spec compliance, then run a code-quality gate.
  • Adaptive handling of subagent status (DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, BLOCKED) to ensure fast iteration without silently skipping problems.
  • Role-appropriate model selection to balance cost, speed, and correctness across mechanical, integration, and design/review work.
  • Common execution workflow suitable for multi-task development plans where tasks are mostly independent but still require coordination.

Quick Start

Ask the AI to dispatch subagent implementers for each plan task and require a spec compliance review followed by a code quality review after every task.

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 multi-step code review for independent software delivery tasks?

Automate multi-step code review by dispatching isolated subagents for each task and enforcing a two-stage review gate that checks spec compliance before code quality. This ensures fast iteration while keeping implementations aligned to the original specification.

What is subagent-driven development and when should I use it for task planning?

Subagent-driven development coordinates isolated subagent executions to implement multi-step plans. Use it when software delivery tasks are mostly independent but must remain aligned to an explicit specification within the same development session to prevent context pollution.

How do I handle subagent execution status like BLOCKED or NEEDS_CONTEXT?

Handle subagent status adaptively by processing DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, and BLOCKED states. This explicit status handling ensures fast iteration without silently skipping problems, requiring fresh context per subagent to maintain focus.

Can I balance model selection by task complexity during workflow automation?

Yes, you can apply role-appropriate model selection to balance cost, speed, and correctness across mechanical, integration, and design or review work. This allows the subagent workflow to match the computational requirements of each specific task.

Does two-stage spec compliance review work with TDD workflows?

Yes, the two-stage review gate supports TDD workflows by verifying spec compliance first, then running a code-quality gate. This ordering ensures the implementation meets the explicit specification before evaluating the test-driven code quality.

What are the limitations of using fresh subagents per task in software delivery?

Fresh subagents per task prevent context pollution but require tasks to be mostly independent. If your software delivery tasks have heavy interdependencies, coordinating isolated subagent executions within the same development session may limit the workflow efficiency.