Model Router

A comprehensive AI model routing system that automatically selects the optimal model for any task. Set up multiple AI providers (Anthropic, OpenAI, Gemini, Moonshot, Z.ai, GLM) with secure API key storage, then route tasks to the best model based on task type, complexity, and cost optimization. Includes interactive setup wizard, task classification, and cost-effective delegation patterns. Use when you need "use X model for this", "switch model", "optimal model", "which model should I use", or to balance quality vs cost across multiple AI providers.

Review before installing if you handle private, regulated, or business-sensitive data. Only configure provider keys you are comfortable storing locally, restrict access to ~/.model-router, verify each provider is approved for the data you route, and do not rely on the documented model aliases until the alias-to-model mapping is corrected.

Type: OpenClaw Skill Name: model-router Version: 1.1.0 The skill is classified as suspicious due to its inherent high-risk capability of collecting and locally storing sensitive API keys for multiple AI providers (e.g., Anthropic, OpenAI, Gemini). While the `scripts/setup-wizard.py` script implements security best practices like using `getpass` for input and setting restrictive file permissions (0o600) on the `~/.model-router/.api-keys` file, the handling of such credentials always presents a significant risk. There is no clear evidence of intentional malicious behavior like exfiltration or unauthorized execution within the provided code or documentation, but the presence of this sensitive capability without explicit API call logic to external endpoints in the provided files, makes it a 'risky capability without clear malicious intent'.