The Agent Skills Directory

[SAFE]: The skill's primary function is to manage architectural documentation and ensure development stays within defined boundaries. All operations are transparent and aligned with this purpose.
[SAFE]: No suspicious network activity or data exfiltration patterns were identified. The skill does not use tools like curl or wget to interact with external domains.
[SAFE]: The skill implements a 'cold review' process using a sub-agent to provide adversarial feedback on architectural proposals, which is a defensive measure to improve documentation quality.
[SAFE]: Modifications to agent configuration files (e.g., .cursorrules, CLAUDE.md) are explicitly documented as part of the setup process to enforce the methodology within the development environment.

design-driven