subagent-driven-development

Coordinate fresh-subagent implementation loops with test-first execution and gated review.

139|7|Updated May 8, 2026
One-click install
npx skills add https://github.com/arbiterForge/codeArbiter --skill subagent-driven-development-arbiterforge
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/arbiterForge/codeArbiter/tree/main/plugins/ca/skills/subagent-driven-development
Command: npx skills add https://github.com/arbiterForge/codeArbiter --skill subagent-driven-development-arbiterforge

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill prevents drift, guesswork, and unverified implementation by forcing each task through a fresh subagent, test-first execution, spec-compliance review, quality review, and fresh-run verification before acceptance.

Core Features & Use Cases

  • Fresh subagent per task: Isolates each unit of work so assumptions do not accumulate across tasks.
  • Test-first implementation: Routes every task through disciplined TDD before any code is accepted.
  • Multi-phase gating: Enforces spec review, quality review, and clean verification runs before a task can advance.
  • Plan-driven execution: Supports full sprint runs and scoped batches while preserving dependency order and checkpoints.
  • Use case: A team can hand the skill an approved plan and let it implement tasks in order while stopping automatically on blocked dependencies, unresolved confirmations, or failing verification.

Quick Start

Use the subagent-driven-development skill to execute the approved plan in dependency order with fresh subagents and gated verification.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I prevent context drift when implementing multiple tasks in a row?

To prevent context drift during implementation, use fresh subagents for each task. This approach isolates every unit of work so assumptions do not accumulate across tasks, ensuring clean execution.

What is the best way to enforce test-first execution in an automated workflow?

The best way to enforce test-first execution is routing every task through disciplined TDD before any code is accepted. This ensures multi-phase gating stops unverified changes from advancing.

How do I execute an approved sprint plan while maintaining dependency order?

You can execute an approved sprint plan by using plan-driven execution with dependency-ordered task selection. The system automatically stops on blocked dependencies, unresolved confirmations, or failing verification.

Does multi-phase gating require spec-compliance and quality reviews before completion?

Yes, multi-phase gating enforces spec-compliance review, quality review, and clean verification runs before a task can advance. Recorded plan status updates are required before completion.

Can I run scoped batches of tasks instead of a full sprint implementation?

Yes, you can run scoped batches instead of a full sprint. The workflow supports scoped batch execution while preserving dependency order and checkpoints for plan-driven implementation.