parallel-dispatch

Dispatch parallel development tracks with file manifests and automated verification.

2|Updated Apr 8, 2026

Search Tags:#verification #concurrency #dispatch #orchestration #parallel #file-manifest

Ready to run

npx skills add https://github.com/DojoGenesis/gateway --skill parallel-dispatch-dojogenesis

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: parallel-dispatch
Source: https://github.com/DojoGenesis/gateway/tree/main/plugins/agent-orchestration/skills/parallel-dispatch
Command: npx skills add https://github.com/DojoGenesis/gateway --skill parallel-dispatch-dojogenesis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Managing multiple concurrent code changes safely is hard; agents can conflict or produce unverified output. This skill provides a structured workflow that plans, dispatches, verifies, and integrates parallel AI agents, preventing merge conflicts and ensuring quality.

Core Features & Use Cases

Explicit file manifests to guarantee exclusive file ownership.
Automated verification using git status, test commands, and build checks.
Controlled concurrency with a maximum of five agents per wave.
Dynamic routing to appropriate LLM models (sonnet for simple, opus for complex).
Error handling that re‑dispatches failing tracks after diagnosis. Ideal for developers needing to refactor large codebases, implement multiple features simultaneously, or run batch fixes across a monorepo.

Quick Start

Ask the parallel‑dispatch skill to run three independent tracks for fixing middleware, adding unit tests, and updating status files.

Frequently Asked Questions about parallel-dispatch

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

FAQPage Schema

How do I run multiple AI agents in parallel without causing merge conflicts in a monorepo?▼

To run parallel AI agents safely, enforce explicit file manifests that guarantee exclusive file ownership for each track. This structured workflow prevents merge conflicts by ensuring agents only modify their assigned files during concurrent refactoring or feature additions.

What is the best way to verify automated code changes from concurrent AI agents?▼

The best way to verify automated code changes is to run automated build and test checks before integration. This workflow uses git status and test commands to validate each parallel track, re-dispatching any failing tracks after diagnosis to ensure quality.

How many concurrent AI agents can I dispatch at once for codebase refactoring?▼

You can dispatch a maximum of five concurrent AI agents per wave for codebase refactoring. This controlled concurrency limit prevents system overload while allowing multiple independent development tracks to process simultaneously across distinct file sets.

Can I route complex refactoring tasks to a more capable LLM model while running simpler tracks in parallel?▼

Yes, you can use dynamic routing to assign complex refactoring tasks to advanced models like opus, while routing simpler parallel tracks to models like sonnet. This ensures efficient resource allocation across concurrent development tracks.

What should I do when a parallel development track fails automated verification during integration?▼

When a parallel development track fails automated verification, the error handling process diagnoses the failure and re-dispatches the failing track. This ensures unverified output is automatically corrected before final integration into the codebase.