The Agent Skills Directory

[SAFE]: The skill operates entirely on local files within the AI_MEMORY directory structure to manage personal context and behavioral records.
[SAFE]: Implements a mandatory human-in-the-loop verification process, ensuring that the user must manually confirm or modify any identified behavioral patterns before they are promoted to long-term memory (L2).
[SAFE]: Uses standard, non-malicious system commands (e.g., grep) for pattern matching within the agent's own data logs.
[SAFE]: No network exfiltration, remote code execution, or credential harvesting patterns were detected.

mem-weekly