subagent-driven-development

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

Updated May 2, 2026
One-click install
npx skills add https://github.com/artgaurav16420-oss/Mega-Skills --skill subagent-driven-development-artgaurav16420-oss
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-driven-development
Source: https://github.com/artgaurav16420-oss/Mega-Skills/tree/main/distribution/harnesses/tabnine/agent/skills/subagent-driven-development
Command: npx skills add https://github.com/artgaurav16420-oss/Mega-Skills --skill subagent-driven-development-artgaurav16420-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Execute plan execution by dispatching fresh subagents per task, with a two-stage review after each: spec compliance review first, then code quality review. This approach isolates context per task and preserves your own session context for coordination work.

Core Features & Use Cases

  • Fresh subagent per task to keep contexts isolated and prevent cross-task leakage.
  • Two-stage review after each task: spec compliance, then code quality.
  • Clear role separation: implementer and reviewer subagents to enforce discipline.
  • Works for plan-driven workflows where tasks can be executed in parallel or sequentially.

Quick Start

Dispatch a fresh subagent for each task in a plan and perform a two-stage review after each task.

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 plan execution with isolated context per task?

Automating plan execution with isolated context requires dispatching a fresh subagent for each task, which prevents cross-task leakage and preserves your main session context for coordination work.

What is a two-stage review process for code quality and spec compliance?

A two-stage review process evaluates completed tasks sequentially: a reviewer subagent first checks spec compliance, then a second review enforces code quality to maintain high standards in plan-driven workflows.

How do I set up subagent task dispatch for parallel and sequential workflows?

Setting up subagent task dispatch involves assigning dedicated implementer subagents to execute individual plan tasks sequentially or in parallel, followed by automated reviews to ensure spec compliance.

Why does my context window overflow during multi-task plan execution?

Context window overflow during multi-task plan execution happens when a single session handles all tasks; dispatching a fresh subagent per task isolates context and prevents cross-task leakage.

Does subagent-driven development work for sequential task execution?

Yes, subagent-driven development works for plan-driven workflows where tasks can be executed in parallel or sequentially, applying a two-stage review after each task completes.