Model Router

Route model requests based on configured models, costs and task complexity. Use for routing general/low-complexity requests to the cheapest available model and for higher-complexity requests to stronger models.

This skill appears to do only local model selection based on a JSON config and heuristics. Before installing: review your models.json (or OpenClaw config) to ensure entries point only to providers you trust (the example includes an 'internal' provider), because the router will pick whatever model records you give it; consider cost implications if you wire the router into an automated pipeline (it may route many requests to expensive models); test the heuristics on representative tasks to ensure routing matches your expectations; and avoid passing sensitive user data to untrusted provider entries in the models file. Overall the package is coherent and low-risk, but validate the models configuration and how the chosen model is subsequently invoked in your system.

Type: OpenClaw Skill Name: model-router-premium Version: 0.1.1 The OpenClaw skill 'model-router-premium' is designed to route model requests based on configuration. The `SKILL.md` instructs the agent to execute a local Python script (`scripts/router.py`), which reads a local JSON file (`examples/models.json`) for model definitions. The Python script performs string processing and file I/O for its stated purpose but does not engage in network communication, arbitrary command execution, or access to sensitive system files. No prompt injection attempts against the agent or the script itself were identified that would lead to malicious behavior.