Docker Agent: Running and Operating Agents Overview This skill owns the operational side of Docker Agent: invoking against a local config, an alias, or a registry reference; choosing how much autonomy the agent gets over tool calls; isolating it in a sandbox VM; and diagnosing why a run fails. It assumes the already exists — see Related skills for authoring it. When to use this skill Activate this skill when: - The user wants to run an agent interactively or headlessly ( ). - The user is choosing or debugging , , or approval behavior for tool calls. - The user wants to isolate an agent's shel…