subagent-driven-development

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

Updated Jan 12, 2026
One-click install
npx skills add https://github.com/Suara17/guanlan-sina --skill subagent-driven-development-suara17
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Suara17/guanlan-sina/tree/main/.opencode/skills/subagent-driven-development
Command: npx skills add https://github.com/Suara17/guanlan-sina --skill subagent-driven-development-suara17

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill orchestrates plan execution by dispatching fresh subagents per task with a two-stage review after each task.

Core Features & Use Cases

  • Fresh per-task subagents ensure isolated context and parallel-safe execution.
  • Two-stage review after each task: spec compliance, then code quality.
  • Self-review, commits, and automated task tracking to maintain traceability.
  • Works within the current session to reduce context switching and maintain continuity.

Quick Start

Start by presenting the plan and triggering the per-task workflow. Dispatch an implementer subagent for each task with the full task text and context, then run the spec compliance reviewer, followed by the code quality reviewer, and finally mark each task complete before proceeding to the next.

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 task plan execution with per-task subagent orchestration?

Subagent orchestration automates plan execution by dispatching fresh subagents per task with a two-stage review after each task. It works within the current session to maintain continuity and reduce context switching for rapid feedback.

What is a two-stage review workflow for subagent task execution?

A two-stage review workflow in subagent task execution runs a spec compliance reviewer followed by a code quality reviewer after each task is implemented. This ensures isolated context validation before marking each task complete.

Can I use fresh subagents for sequential and independent task plans?

Yes, fresh per-task subagents are designed for sequential or near-sequential task plans where tasks are largely independent. They ensure isolated context and parallel-safe execution within the current session.

How do I start a per-task subagent workflow for plan execution?

To start per-task subagent plan execution, present the plan and trigger the workflow by dispatching an implementer subagent for each task, then run spec compliance and code quality reviewers, and mark each task complete before proceeding.

Does subagent-driven plan execution require external dependencies or components?

No, subagent-driven plan execution requires no external dependencies or components. It operates entirely within the current session using self-reviews, commits, and automated task tracking to maintain traceability.