The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using rg combined with Unix processing tools like cut, sort, and uniq. These commands are used to identify and quantify code patterns such as any types, null checks, and TODO comments.
[DATA_EXPOSURE]: File access is restricted to the local repository and specifically targets source code by using glob patterns that exclude sensitive or irrelevant directories like node_modules, dist, and build artifacts. There is no evidence of attempts to access credentials or system configuration files.

codebase-slop-audit