The Agent Skills Directory

[SAFE]: The skill's primary function is to read codebase files and directory structures to perform architectural audits. This behavior is consistent with its stated purpose of identifying code smells.
[SAFE]: Report generation is performed locally, saving findings to a docs/_refacs/ directory within the user's project. No external data transmission is attempted.
[SAFE]: Includes a standalone Python utility scripts/validate-metadata.py which uses standard library modules (re, sys, argparse) to verify metadata against platform specifications. It contains no executable or network-active components.
[SAFE]: References to external entities such as refactoring.guru and Martin Fowler's literature are for educational attribution and provide no security risk.
[SAFE]: No prompt injection, obfuscation, or persistence mechanisms were found in the instructions or referenced markdown catalogs.

refactoring-analysis