About
This skill automatically classifies tasks and routes them to the appropriate AI model (Claude, Codex, or Gemini) based on multi-dimensional scoring and provider availability. It's ideal for developers needing to optimize cost, latency, and quality by intelligently selecting the best model for each task type. Key features include tier-based routing, confidence calibration, session pinning, and performance tracking.
Quick Install
Claude Code
Recommendednpx skills add vamseeachanta/workspace-hub -a claude-code/plugin add https://github.com/vamseeachanta/workspace-hubgit clone https://github.com/vamseeachanta/workspace-hub.git ~/.claude/skills/agent-routerCopy and paste this command in Claude Code to install this skill
GitHub Repository
Frequently asked questions
What is the agent-router skill?
agent-router is a Claude Skill by vamseeachanta. Skills package instructions and resources that Claude loads on demand, so Claude can perform agent-router-related tasks without extra prompting.
How do I install agent-router?
Use the install commands on this page: add agent-router to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does agent-router belong to?
agent-router is in the coordination category.
Is agent-router free to use?
Yes. agent-router is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
Related Skills
This skill enables queen-led multi-agent coordination with consensus mechanisms and persistent memory for complex collective intelligence tasks. Use it when you need sophisticated swarm coordination where a central queen agent orchestrates specialized workers through Byzantine consensus. It provides hierarchical architecture patterns for managing high-level objectives across distributed agent systems.
This skill enables queen-led multi-agent coordination with consensus mechanisms and persistent memory for complex distributed tasks. It's ideal for developers building sophisticated swarm systems requiring hierarchical orchestration and collective decision-making. Key features include Byzantine consensus, strategic queen coordination, and shared memory across specialized worker agents.
This skill implements a queen-led multi-agent coordination system with consensus mechanisms and persistent memory. Use it when you need to orchestrate sophisticated workflows across specialized AI agents for complex tasks. It provides hierarchical control, collective decision-making, and shared memory for advanced swarm intelligence applications.
This Claude Skill provides standardized JSON schemas for the Ralph event-driven messaging system. It defines the core message structure, ID format, and specific message types like `task_assign` for coordinating development workflows. Use it to ensure consistent and structured communication between different roles (e.g., PM, Developer, QA) within the system.