Skip to main content
The CLI is SelfTune’s operational API. Start with the intent-level commands below. Use the installed command’s --help output as the source of truth for exact flags because the agent skill and CLI ship together.

​
Run a command

Without an executable on PATH, use:

​
Customer command map

Find a local skill without activating it with selftune skills search "task or collection" --json. See skill search for options and scope. For task-scoped use, the agent follows skills activate, skills load, and skills deactivate. Activation and cleanup preview unless --yes is supplied. Low-level grading, evolution, search, and orchestration commands remain available for debugging and expert control. The paired eval runner is part of the normal evidence workflow.

​
Machine-readable output

Use --json when the selected command supports it. Consumers must still check the returned state and target revision; a zero exit code alone does not prove that a skill improved or a service is healthy.

​
Safety boundaries

Local inspection, skill mutation, background operation, authentication, remote upload, publication, and deletion are distinct actions. Preview mutations and request user approval at the boundary that matters. See CLI and headless use for automation guidance and Privacy and permissions for data boundaries.