The Agent Skills Directory

[SAFE]: The skill performs expected development tasks such as file creation, configuration updates, and documentation maintenance within the project's local directory.
[COMMAND_EXECUTION]: The core functionality involves generating and registering executable JavaScript hooks. The implementation uses structured templates and performs basic sanitization on user-provided inputs (e.g., character replacement for file names) to ensure safe and predictable file system operations.
[PROMPT_INJECTION]: The instructions utilize strong language (e.g., 'IRON LAWS', 'MANDATORY', 'CRITICAL') to enforce framework consistency and architectural compliance. These are operational constraints for the agent and do not constitute attempts to bypass safety filters or extract system prompts.
[DATA_EXFILTRATION]: No network operations or unauthorized access to sensitive user credentials were detected. The skill interacts exclusively with project-specific files like settings.json and learnings.md in the .claude directory.

hook-creator