The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several shell commands via allowed-tools (ls, wc, find, cat, grep, git log, diff) to audit documentation. These are restricted to specific patterns (e.g., ls*, wc*) and are used for their intended purpose of counting files and comparing content.
[REMOTE_CODE_EXECUTION]: The skill includes an example of running a local script using uv run python scripts/check_inventory.py. The instructions explicitly state to discover the actual command from project configuration files like pyproject.toml rather than assuming the filename exists. This is a standard development workflow for project-specific auditing.
[DATA_EXPOSURE]: The skill performs a 'leaked details' check (Check 4) which actively looks for sensitive data (vault paths, personal names) in public documentation to prevent accidental exposure. This is a security-positive feature.

docs-consistency