subagent-driven-development

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

371|38|Updated Feb 17, 2026
One-click install
npx skills add https://github.com/Ibrahim-3d/conductor-orchestrator-superpowers --skill subagent-driven-development-ibrahim-3d
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/Ibrahim-3d/conductor-orchestrator-superpowers/tree/main/skills/subagent-driven-development
Command: npx skills add https://github.com/Ibrahim-3d/conductor-orchestrator-superpowers --skill subagent-driven-development-ibrahim-3d

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables executing implementation plans by dispatching fresh subagents per task, with a two-stage review after each task: spec compliance review first, then code quality review.

Core Features & Use Cases

  • Dispatch a dedicated subagent per task to maintain isolated context and reduce cross-task contamination.
  • Enforce a two-stage review workflow (spec compliance followed by code quality) to improve outcome quality.
  • Orchestrate multi-task plans within a single session with structured task tracking and re-review loops.

Quick Start

Initiate a plan run by dispatching a fresh implementer subagent for each task and follow the built-in spec and code-quality reviews to complete tasks.

Frequently Asked Questions about subagent-driven-development

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

FAQPage Schema
How do I automate implementation plans with isolated context for each task?

Automating implementation plans is achieved by dispatching fresh subagents to handle individual tasks within a single session. This maintains isolated context per task, enabling parallel execution while reducing cross-task contamination.

How does the two-stage code review process work for subagent task execution?

The two-stage code review enforces quality by first evaluating spec compliance, then assessing code quality. After each fresh subagent completes a task, it undergoes this structured review workflow before reporting completion.

Can I orchestrate multi-task plans with parallel execution in a single session?

Yes, you can orchestrate multi-task plans within a single session using structured task tracking. The system dispatches dedicated subagents for independent tasks, supporting parallel execution and re-review loops to ensure quality.

What is the best way to ensure spec compliance when automating plan execution?

The best way to ensure spec compliance is using a structured review workflow where subagents self-review their work against the plan. A dedicated spec compliance review stage runs before code quality checks to validate requirements.

Why does dispatching fresh subagents reduce cross-task contamination?

Dispatching fresh subagents reduces cross-task contamination because each task receives a dedicated, isolated context. This prevents state bleed between independent tasks during parallel execution within the same session.

Does this approach support TDD and automated task completion flow?

Yes, the system supports TDD workflows through its spec compliance review stage and automated task completion flow. It enforces a self-review loop before reporting, ensuring code aligns with test and specification requirements.