The Agent Skills Directory

[SAFE]: The skill is a set of instructional guidelines for maintaining clean code across various programming languages. It does not contain any malicious payloads or safety bypass attempts.
[COMMAND_EXECUTION]: The skill documentation includes a section on 'Verification Scripts' that instructs the agent to run specific Python scripts (e.g., ux_audit.py, security_scan.py, lint_runner.py) located within the .agent/skills/ directory. These are standard automated checks within the agent's environment.
[PROMPT_INJECTION]: The skill uses formatting such as '🔴', 'CRITICAL', and 'MANDATORY' to emphasize adherence to coding standards and verification procedures. These instructions are focused on task quality and do not attempt to override the model's core safety filters or system instructions.
[DATA_EXFILTRATION]: No network requests, external data transfers, or hardcoded credentials were identified in the skill content.
[REMOTE_CODE_EXECUTION]: All scripts referenced are local to the .agent/skills/ directory; no remote code downloads or execution from untrusted URLs were detected.

clean-code