The Agent Skills Directory

[SAFE]: The skill is purely educational and architectural in nature. It contains guidelines, code snippets, and a local validation script intended for improving software design boundaries.- [COMMAND_EXECUTION]: The skill provides example grep commands in its documentation and includes a Python script (scripts/validate_architecture.py) for architectural linting. These tools are designed to operate locally on source code to identify dependency violations and do not pose a security risk in their intended context.- [DATA_EXFILTRATION]: No network activity, external URL references (other than standard documentation examples), or data exfiltration patterns were found.- [PROMPT_INJECTION]: The instructions are focused on software engineering principles and do not contain any attempt to override agent behavior, bypass safety filters, or extract system prompts.

hexagonal-architecture