@scute/harness
Guardrails for the agents you build: permissions, verification, approvals, grounding and budgets from Scute, on the agent framework you already use.
Guardrails for the agents you build. Guards decide on every tool call: who may do what (Scute's engine), whether the person has to verify or confirm, whether an argument was made up, whether a budget is spent. It works with the agent framework you already use and any model provider, because it hooks the tool calls, not the model.
⚡ How to use @scute/harness
Indexed from npm. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/scute-scuteharnessCapabilities
Do you own @scute/harness?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.