The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a bundled TypeScript script (audit-hexagon.ts) and perform search operations using rg (ripgrep). These commands are used solely to analyze the project's package dependencies and source code structure to ensure compliance with architectural boundaries.
[SAFE]: The analysis confirms that the skill performs read-only operations on the project source code. There are no patterns suggesting data exfiltration, remote code execution, or unauthorized privilege escalation. The script uses standard Node.js built-in modules for file system interaction and does not communicate with external network services.

hexagon-audit