The Agent Skills Directory

[SAFE]: The skill's behavior is consistent with its stated purpose of defining information architecture. It operates locally by reading and writing files within the project's directory structure.
[COMMAND_EXECUTION]: The skill instructs the agent to explore the existing codebase (e.g., Next.js routes, navigation components, layouts). This is a read-only operation performed via standard file system exploration tools to understand the current project context.
[DATA_EXPOSURE]: The skill reads .design/*/DESIGN_BRIEF.md files. This is an expected behavior for a developer-centric AI agent and does not involve exfiltration of data to external servers.
[NO_CODE]: The skill does not bundle or execute external scripts, binary files, or installation commands.

information-architecture