The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute scripts/init_agentic_os.py, which scaffolds the project structure and manages directory creation.\n- [COMMAND_EXECUTION]: The initialization script uses subprocess.run to execute Git commands for repository detection and chmod to set executable permissions on internal hook scripts.\n- [COMMAND_EXECUTION]: The runtime/kernel.py script is designed to be executed via the command line to manage file locks, state updates, and event logging within the project context.\n- [SAFE]: The skill implements security-conscious features such as a fail-closed agent validation registry in kernel.py and a safe-write protocol that creates backups of existing files before overwriting.\n- [SAFE]: All file operations and command executions are restricted to the local filesystem and the project's working directory.

agentic-os-init