The Agent Skills Directory

[SAFE]: The skill operates entirely on local project documentation files located in docs/ and .guardrails/ directories. It does not access sensitive system paths or credentials.
[SAFE]: No network operations (exfiltration) or external downloads were detected. The skill uses local templates for seeding guideline files.
[SAFE]: Command execution is limited to standard version control operations such as git diff and git commit within a defined worktree context.
[SAFE]: The skill includes internal logic (Step 5) to enforce compliance with project standards, acting as a safeguard against reducing documentation quality.
[SAFE]: No obfuscation, prompt injection attempts, or dynamic execution patterns were identified.

tailor-guidelines