The Agent Skills Directory

[SAFE]: The skill documents legitimate development workflows including task execution, testing with npx tsc, and version control via git. It explicitly restricts potentially destructive commands such as booth stop, booth restart, and booth shutdown. The use of an internal CLI for reporting is a standard operational procedure for this type of agent framework. No malicious patterns such as obfuscation, credential exfiltration, or unauthorized remote code execution were detected.

booth-deck