Agent Router
Intelligently routes user requests to the most appropriate UDAgent based on content and task requirements.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add agent-router npx -- -y @trustedskills/agent-router
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"agent-router": {
"command": "npx",
"args": [
"-y",
"@trustedskills/agent-router"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The Agent Router skill directs incoming requests to different AI agents based on predefined rules. It acts as a dispatcher, ensuring tasks are handled by the most appropriate agent within your system. This allows for specialized agents to focus on specific areas and improves overall efficiency.
When to use it
- Complex workflows: Route user queries about order status to an "Order Tracking" agent and general inquiries to a "Customer Support" agent.
- Specialized agents: Automatically send requests requiring code execution to an agent with coding capabilities.
- Skill-based routing: Direct tasks needing specific knowledge (e.g., legal or medical) to the corresponding expert agent.
- Load balancing: Distribute incoming requests across multiple instances of a particular agent type.
Key capabilities
- Rule-based routing: Define rules based on request content, user attributes, or other criteria.
- Agent selection: Choose from a list of available agents to route tasks.
- Request forwarding: Pass the original request and any relevant context to the selected agent.
Example prompts
- "Route this message to the 'Sales' agent."
- "If the query contains 'refund', send it to the 'Returns' agent."
- "Direct all requests from user 'John Doe' to the 'VIP Support' agent."
Tips & gotchas
The Agent Router relies on a correctly configured list of available agents. Ensure that the agents you are routing to are active and accessible for optimal performance.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.