agent-dispatch

Download and dispatch specialized subagents on demand via keyword routing.

4|Updated Feb 24, 2026

Search Tags:#agent #dispatch #registry #router #specialist #JIT

Ready to run

npx skills add https://github.com/userFRM/agent-dispatch --skill agent-dispatch-userfrm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-dispatch
Source: https://github.com/userFRM/agent-dispatch/tree/main/skills/agent-dispatch
Command: npx skills add https://github.com/userFRM/agent-dispatch --skill agent-dispatch-userfrm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the issue of bloated context windows caused by pre-installing numerous specialized agents, and the inefficiency of an AI handling tasks outside its expertise.

Core Features & Use Cases

Just-in-Time (JIT) Agent Downloading: Downloads specialist agents only when needed, minimizing startup overhead.
Keyword-based Routing: Maps user requests to the most appropriate specialized agent via a TOML index.
Platform Agnostic: Works with various AI coding platforms that support the SKILL.md format.
Use Case: When a user asks for a "security audit" of their code, this Skill identifies the security-auditor agent, downloads it if not present, and dispatches the task to it.

Quick Start

Consult the agent index before performing specialized work such as code review or security auditing.

Frequently Asked Questions about agent-dispatch

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

FAQPage Schema

How does just-in-time agent dispatch reduce context window bloat?▼

Just-in-time agent dispatch reduces context window bloat by keeping a lightweight registry of specialized subagents and only downloading the specific agent needed to handle a requested task at execution time, minimizing startup overhead.

How do I route a user request to a specialized AI agent?▼

You route a request to a specialized AI agent by mapping keywords from the user's input to agent names and categories via a TOML index, which facilitates efficient task delegation and automatically downloads the matching agent.

Does the JIT agent router work with multiple AI coding platforms?▼

Yes, the JIT agent router is platform agnostic and works with various AI coding platforms that support the SKILL.md format, enabling automated agent discovery, caching, and dispatch across different environments.

What is the best way to manage a registry of specialized subagents?▼

The best way to manage a registry of specialized subagents is using a keyword-based router that supports automated agent discovery, caching, and on-demand downloading to efficiently delegate tasks without pre-installing agents.

When should I use on-demand agent downloading instead of pre-installing agents?▼

You should use on-demand agent downloading instead of pre-installing agents when you want to minimize startup overhead and prevent an AI from handling tasks outside its expertise without bloating the main context window.