The Agent Skills Directory

[SAFE]: No executable code or scripts are included in the skill. The instructions are purely conceptual and logical for managing game-like state cycles.
[SAFE]: The skill does not perform any network operations, external downloads, or remote code execution.
[SAFE]: No sensitive file access, credential exposure, or hardcoded secrets were detected.
[SAFE]: The persistence discussed in the contract and rules refers to the logical management of 'run' state and 'meta carry' policies within a game loop, not system-level persistence mechanisms or unauthorized data storage.

roguelike-run