subagent-driven-development

Dispatch isolated subagents to execute implementation plans with two-stage reviews.

4|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/oabdelmaksoud/Openclaw-skills-Compilations --skill subagent-driven-development-oabdelmaksoud
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/oabdelmaksoud/Openclaw-skills-Compilations/tree/main/subagent-driven-development
Command: npx skills add https://github.com/oabdelmaksoud/Openclaw-skills-Compilations --skill subagent-driven-development-oabdelmaksoud

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Executes implementation plans by dispatching a fresh subagent per task, with a two-stage review workflow to ensure spec alignment and code quality, while preventing context pollution.

Core Features & Use Cases

  • Fresh subagent per task to avoid cross-task context leakage
  • Two-stage review after each task: spec compliance, then code quality
  • End-to-end execution flow including final code review and finishing-a-development-branch

Quick Start

Dispatch a plan to this skill to run per-task implementations with isolated subagents and iterative reviews.

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 with isolated subagents to prevent context pollution?

You can dispatch your implementation plan to dedicated subagents, which assigns a fresh subagent per task to prevent cross-task context leakage and maintain execution isolation.

What is a two-stage code review workflow for plan execution?

A two-stage code review workflow checks spec compliance first, then evaluates code quality after each task, concluding with a final overall review to ensure alignment and quality.

How do I automate task dispatching and code review for a development branch?

Automate task dispatching by sending your plan to this skill, which runs per-task implementations with isolated subagents and iterative reviews, concluding with the finishing-a-development-branch workflow.

Does subagent-driven development require specific workflow templates to finish a branch?

Yes, it requires using the finishing-a-development-branch workflow along with its associated prompts and templates found in the references to properly conclude the execution.

What's the best way to avoid cross-task context leakage during automated code implementation?

The best way to avoid context leakage is orchestrating tasks with fresh subagents, ensuring each task is handled by an isolated subagent followed by spec compliance and code quality reviews.