The Agent Skills Directory

[SAFE]: The skill performs legitimate cost tracking by querying a local API endpoint. All operations are confined to the local environment and do not pose a risk of data exfiltration or unauthorized code execution.- [COMMAND_EXECUTION]: The skill utilizes curl to retrieve usage data from a local service (localhost:3005). This is a localized operation for agent-specific monitoring and does not involve interaction with external or untrusted servers.- [DATA_EXFILTRATION]: No evidence of data being sent to external domains. The network operations are limited to the loopback address, which is safe for internal service communication.

cost-tracker