The Agent Skills Directory

[SAFE] (SAFE): No malicious code or patterns were detected. The skill serves as a reference for running reputable CLI tools for line counting and diffing.
[Indirect Prompt Injection] (LOW): The skill has an ingestion surface as it reads and processes local codebase files.
Ingestion points: Local filesystem files processed by tokei and difft.
Boundary markers: None; output is presented to the agent as standard tool output (tables or diffs).
Capability inventory: Local bash execution to run tokei, difft, and git.
Sanitization: None; the tools themselves handle the file parsing, and the agent receives the resulting statistics or structural diffs.

code-stats