OpenClaw plugins extend the OpenClaw runtime with hooks, services, tools, or provider integrations. They are different from NemoClaw-managed agent skills:
SKILL.md directories that teach an agent how to perform a task.Today, the supported NemoClaw path for OpenClaw plugins is to bake the plugin into a custom sandbox image and onboard from that Dockerfile.
Put the Dockerfile and everything it needs to COPY in one directory.
nemoclaw onboard --from <Dockerfile> uses the Dockerfile’s parent directory as
the Docker build context.
Use the custom image to copy the plugin into the OpenClaw extensions directory and let OpenClaw refresh its config before NemoClaw starts the sandbox.
If the plugin needs configuration in openclaw.json, apply it after
openclaw doctor --fix so the base config exists first.
Point nemoclaw onboard --from at the Dockerfile in the build directory.
If you need a second sandbox alongside an existing one, use a dedicated build directory and rerun onboarding with the sandbox name and ports you intend to use.
Plugins still run inside the sandbox policy boundary. If a plugin needs network egress, add or update a policy preset for the required hostnames and binaries before rebuilding the sandbox.
For example, see Network Policies for policy concepts and Customize Network Policy for custom preset workflows.
These are the most common places where plugin installation gets mixed up with other NemoClaw extension paths.
nemoclaw <sandbox> skill install for OpenClaw plugins. That
command only installs SKILL.md agent skills./tmp unless you intend
to send that whole directory as the Docker build context.