The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to identify and run test commands from project configuration files such as package.json, Makefile, and pyproject.toml. This behavior is restricted to standard development workflows and project-defined scripts.
[PROMPT_INJECTION]: The instructions utilize strict directives and constraints (e.g., 'The Iron Law', 'Delete means delete') to ensure the agent follows TDD principles. These are functional instructions for methodology enforcement and do not attempt to override model safety guidelines.
[SAFE]: Analysis of the skill and its reference files found no evidence of obfuscation, malicious code, credential exposure, or unauthorized network operations. The skill's operation is consistent with its intended purpose as a developer tool.

tdd