subagent-development

Dispatch a fresh subagent per task and run two-stage reviews.

4|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/rbaumier/skills --skill subagent-development-rbaumier
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-development
Source: https://github.com/rbaumier/skills/tree/main/subagent-development
Command: npx skills add https://github.com/rbaumier/skills --skill subagent-development-rbaumier

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Subagent-driven development helps teams execute complex implementation plans by delegating each task to a fresh subagent, ensuring isolation and focused progress while preserving a global coordination context.

Core Features & Use Cases

  • Fresh subagent per task to avoid context leakage and enable parallel progress
  • Two-stage reviews (spec compliance first, then code quality) to ensure high quality
  • Built-in plan validation, task dependency ordering, and optional research phase for unfamiliar domains

Quick Start

Dispatch an implementation plan that assigns each task to a new subagent and runs the per-task reviews to ensure spec compliance and code quality.

Frequently Asked Questions about subagent-development

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

FAQPage Schema
How do I automate implementation plan execution with isolated subagents?

Automating implementation plan execution is achieved by dispatching a fresh subagent for each task. This approach ensures isolation and focused progress while preserving a global coordination context to manage dependencies.

What is the two-stage review process for subagent task orchestration?

The two-stage review process for task orchestration evaluates spec compliance first, then code quality. This mechanism ensures high-quality output from dispatched subagents by systematically validating functional requirements before reviewing implementation standards.

How do I manage task dependencies and validation in subagent-driven development?

Managing task dependencies and validation in subagent-driven development relies on built-in plan validation gates. These gates order task execution and allow optional research phases to clarify unfamiliar domains before dispatching subagents.

Can I use plan dispatch for multiple independent tasks in a single session?

Plan dispatch is specifically designed for plans containing multiple independent tasks in a single session. It delegates each task to a fresh subagent to avoid context leakage and enable parallel progress across the workflow.

Does subagent development work with finishing and branch workflows?

Subagent development supports finishing and branch workflows to manage task scope and integration. These workflows ensure that executed tasks are properly scoped and merged back into the main coordination context after completion.

Why should I use fresh subagents for each task instead of a single agent?

Using fresh subagents for each task avoids context leakage and enables parallel progress. A single agent accumulates context over time, whereas fresh subagents maintain focused isolation while a global context coordinates the overall plan.