subagent-dev

Coordinate isolated subagents for implementation tasks with two-stage reviews.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/mengdehong/opencode-dotfiles --skill subagent-dev-mengdehong
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-dev
Source: https://github.com/mengdehong/opencode-dotfiles/tree/main/skills/subagent-dev
Command: npx skills add https://github.com/mengdehong/opencode-dotfiles --skill subagent-dev-mengdehong

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinated per-task execution by dispatching fresh subagents for each task, preserving isolated context and enabling deterministic two-stage reviews to improve quality and speed.

Core Features & Use Cases

  • Fresh per-task subagents to prevent context bleed and keep implementations focused
  • Two-stage reviews after each task: requirements/design compliance, then code quality review
  • Structured per-task workflow with automatic tracking, reporting, and task completion
  • Standardized prompts and templates for implementer, spec-reviewer, and code-quality-reviewer to ensure consistency

Quick Start

Initiate per-task subagent execution for a given task and run the two-stage review workflow.

Frequently Asked Questions about subagent-dev

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent context bleed when dispatching multiple isolated subagents for development tasks?

Isolated subagent orchestration dispatches a fresh subagent for each implementation task to prevent context bleed. This approach preserves per-task context isolation, ensuring implementations remain focused without interference from previous task data within a single session.

What is two-stage code review and how does it work for task dispatch workflows?

Two-stage code review executes sequential checks after each task dispatch: a spec-reviewer verifies requirements and design compliance, followed by a code-quality-reviewer assessing implementation standards. This deterministic process improves quality within isolated subagent workflows.

How to automate test-driven development checks with subagent task tracking?

Automate test-driven checks by initiating per-task subagent execution within a single session. The workflow coordinates isolated subagents to run implementation tasks, automatically tracking completion and applying test-driven checks before triggering structured two-stage reviews.

Can I use custom dispatch prompts for individual subagents in a multi-step task?

Yes, the subagent orchestration supports custom per-task dispatch prompts for individual subagents. It provides standardized prompts and templates for implementer, spec-reviewer, and code-quality-reviewer roles to ensure consistency across multi-step tasks.

When should I use isolated subagent orchestration instead of a single continuous session?

Use isolated subagent orchestration for multi-step tasks requiring strict context isolation, test-driven checks, and coordinated reviews. If your development workflow needs per-task context separation and deterministic two-stage reviews to improve quality, this approach is necessary.