subagent-driven-development

Dispatch fresh subagents per task with two-stage spec and quality reviews.

4|Updated Dec 5, 2025

Search Tags:#automation #planning #code-quality #subagent #two-stage-review #task-dispatch

Ready to run

npx skills add https://github.com/aaaa47080/stock_agent --skill subagent-driven-development-aaaa47080

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/aaaa47080/stock_agent/tree/main/.opencode/skills/subagent-driven-development
Command: npx skills add https://github.com/aaaa47080/stock_agent --skill subagent-driven-development-aaaa47080

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables teams to execute complex implementation plans by dispatching a fresh subagent per task and applying a two-stage review after each task to ensure spec compliance and code quality.

Core Features & Use Cases

Fresh subagent per task to maximize parallelism and specialization.
Two-stage review process: first verify spec compliance, then assess code quality.
Clear status handling with DONE, DONE_WITH_CONCERNS, NEEDS_CONTEXT, BLOCKED to guide progress.
End-to-end workflow: plan parsing, per-task execution, and final integration after all tasks are completed.

Quick Start

Provide a plan with explicit tasks and let the system dispatch a fresh subagent for each task, enforcing sequential spec review followed by code-quality review.

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 implementation plan execution with spec compliance and code quality checks?▼

Automating implementation plan execution works by dispatching a fresh subagent per task and applying a two-stage review verifying spec compliance then code quality after each task to ensure structured development.

What is the two-stage review process for development tasks?▼

The two-stage review process first verifies spec compliance for a completed task, then assesses overall code quality, ensuring structured development workflows meet strict quality checks before moving forward.

How do I handle task statuses like BLOCKED or NEEDS_CONTEXT during automated code generation?▼

Handling task statuses like BLOCKED, NEEDS_CONTEXT, DONE_WITH_CONCERNS, and DONE is managed automatically by the system to guide progress, pausing execution or requesting additional information as needed.

When do I need fresh subagents per task for my development workflow?▼

You need fresh subagents per task when executing complex implementation plans that require maximized parallelism, task specialization, and strict compliance checks within a structured development workflow.

Can I use this automated task dispatch system for sequential code integration?▼

Yes, the system supports end-to-end workflow automation by parsing plans, executing per-task dispatch with reviews, and performing final code integration after all planned tasks are completed.

What are the limitations of using a fresh subagent for every coding task?▼

A limitation of dispatching fresh subagents per task is that it requires a structured plan with explicit tasks, making it less suited for ambiguous, unstructured development work lacking clear spec-driven requirements.