The Agent Skills Directory

[SAFE]: The skill consists of instructional content and metadata focused on efficiency. It does not provide any scripts, executable code, or configurations that would grant unauthorized access or perform dangerous operations.
[SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found. The instructions for 'scripts over eyeballing' refer to the agent using its existing standard tools (like grep or jq) to process data more reliably than manual reasoning.
[SAFE]: The skill does not access sensitive file paths or perform network operations. All recommendations, such as byte-capping command output and ranged reads, are standard best practices for managing large contexts in a safe manner.

frugal