The Agent Skills Directory

[SAFE]: The skill performs read-only exploration of project manifest files (e.g., package.json, pyproject.toml) and configuration files to synthesize documentation. These operations are localized to the current repository.
[SAFE]: File system modifications are limited to creating the '.maestro/context/' directory and writing documentation files. The '--reset' functionality is a standard cleanup task scoped to the skill's own generated files.
[SAFE]: No network operations, obfuscated code, or remote code execution patterns were detected. The skill uses standard shell commands like 'mkdir' for its operations.
[SAFE]: The instruction to explore the codebase without asking for permission is a behavioral optimization for the agent's task and does not bypass security controls.

init