The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructional content with no executable scripts or code components.
[SAFE]: No network activity, external data transfers, or data exfiltration patterns were detected.
[SAFE]: No prompt injection or obfuscation techniques (such as Base64 encoding or hidden characters) are present.
[SAFE]: File operations are limited to logging decisions within the local memory/ directory and updating MEMORY.md, which are standard agent memory management practices.
[SAFE]: No use of dynamic context injection or dangerous shell commands was found.

decision-playbook