The Agent Skills Directory

[COMMAND_EXECUTION]: The strategy utilizes subprocess.run to execute the mcporter command-line utility. This is the primary interface for fetching market data and executing trades via the Senpi infrastructure. The implementation correctly uses argument lists rather than shell strings, which mitigates risks of shell-based injection.
[SAFE]: The skill manages its state and trade counters using local files within its designated workspace. It follows atomic write patterns to ensure data integrity and does not exhibit any patterns of unauthorized data exposure or exfiltration.
[SAFE]: The instructions require the agent to configure cron jobs for the scanner and risk management modules. This persistence mechanism is appropriate for the skill's function as an automated trading bot and is explicitly disclosed in the documentation.

wolverine-strategy