subagent-driven-development

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

Updated Apr 14, 2026
One-click install
npx skills add https://github.com/gerald-ica/opencode-config-snapshot --skill subagent-driven-development-gerald-ica
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/gerald-ica/opencode-config-snapshot/tree/main/opencode/skills/subagent-driven-development
Command: npx skills add https://github.com/gerald-ica/opencode-config-snapshot --skill subagent-driven-development-gerald-ica

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-driven development enables executing implementation plans by dispatching independent subagents per task, maintaining clean context and enabling rapid iteration with built-in guardrails.

Core Features & Use Cases

  • Fresh subagent per task to avoid context leakage and enable parallel handling
  • Two-stage review after each task: spec compliance review, then code quality review
  • Structured per-task workflow including plan extraction, implementation, testing, and self-review
  • Supports both same-session and multi-task scenarios with clear completion criteria

Quick Start

Dispatch a dedicated implementer subagent for each task in your plan and apply a two-stage review after every task until all tasks are 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 an implementation plan while avoiding context leakage between tasks?

Subagent-driven development dispatches a fresh subagent per task to maintain isolated context. This enables rapid iteration and parallel handling while preventing context leakage across independent implementation tasks.

What is the best way to automate spec compliance and code quality reviews during development?

Automated two-stage reviews use dedicated subagents to check spec compliance first, then code quality. This systematic review process runs after each task implementation to ensure explicit checkpoints are met before completion.

How do I structure a workflow for independent implementation tasks that require fast iteration?

Structure workflows by extracting plans, dispatching dedicated implementer subagents per task, running tests, and performing iterative self-reviews. This supports both same-session and multi-task scenarios with clear completion criteria.

Can I use subagent dispatch for same-session development workflows with multiple independent tasks?

Yes, subagent dispatch supports same-session workflows with multiple independent tasks. Each task receives a fresh subagent with isolated context, followed by a two-stage review process to ensure spec compliance and code quality.

Why does my development workflow need two-stage reviews with fresh subagents?

Two-stage reviews with fresh subagents prevent context contamination and provide systematic guardrails. The spec-compliance review verifies requirements, while the code-quality review ensures standards before marking tasks complete.

When should I not use subagent-driven development for task execution?

Subagent-driven development is not suited for tasks requiring shared context or sequential dependencies. It is designed for in-session workflows with independent tasks that benefit from isolated context and explicit checkpoints.