The Agent Skills Directory

[SAFE]: The skill is entirely composed of documentation and instructional patterns for repository management. It promotes security-positive behaviors such as mechanical enforcement of architectural boundaries and using structured, version-controlled documentation as the single source of truth.\n- [COMMAND_EXECUTION]: The documentation includes code examples for structural tests and custom linters (e.g., using Node.js fs and glob). These are provided as patterns for the developer to implement within their project's test suite to ensure architectural integrity and are consistent with standard software development practices.\n- [EXTERNAL_DOWNLOADS]: The skill references an official blog post from OpenAI regarding 'harness engineering' as a foundational concept. This is a reference to a well-known and trusted technology organization and is used for educational context.

agent-first-repo