The Agent Skills Directory

[SAFE]: The skill's primary function is to manage project-level documentation for AI agents. It operates by reading the local codebase to understand project structure and interviewing the user for specific configuration details (commands, standards, and boundaries).
[SAFE]: File operations are restricted to writing documentation files (AGENTS.md, CLAUDE.md) to the project root based on local templates provided in the references/ directory. No arbitrary command execution or unauthorized file system access was detected.
[SAFE]: The skill does not perform any network operations, external downloads, or data exfiltration. All data processing remains local to the project environment.
[SAFE]: No obfuscation, persistence mechanisms, or privilege escalation patterns were identified. The use of disable-model-invocation: true in the frontmatter serves as a safety constraint on the execution environment.

agent-md