The Agent Skills Directory

[SAFE]: The skill operates as an instructional and configuration layer for model selection. No evidence of malicious intent, prompt injection, or unauthorized data access was found.
[SAFE]: The implementation examples using the Task tool are standard agentic patterns and do not involve insecure code execution or dynamic loading of untrusted resources.
[SAFE]: Metadata and routing rules in routing-rules.json align with the stated purpose of cost optimization and performance management. References to agent names like frankx-content-creation are consistent with the author's known identity.

model-routing