The Agent Skills Directory

[SAFE]: The skill strictly enforces a read-only policy as defined in its rules and governance sections. It explicitly forbids creating plans, writing code, or making any changes during the investigation process.
[SAFE]: The execution flow utilizes standard file system operations (std:fs.list, std:fs.read, std:fs.search) to discover codebase structure, dependencies, and patterns. These operations are scoped to the project context.
[SAFE]: No external network operations, remote script executions, or sensitive credential access patterns were found in the provided files.

investigate