agent-substrate-deploylisted

# Agent Substrate Deploy Stand up [Agent Substrate](https://github.com/agent-substrate/substrate) and an Orka-compatible `WorkerPool` + `ActorTemplate` on a local kind cluster, wire Orka with `--substrate-*` flags, then validate the direct Substrate actor/router and MCP tool paths. Today, `type: agent` Tasks whose `spec.execution.workspace` uses `provider: substrate` are expected-failure/future API checks because the service-backed harness rejects execution workspaces. This skill is for **local/kind evaluation and validation**, not production. Orka does not install or manage Substrate (CRDs, control plane, router, snapshot store, WorkerPool capacity) in production. See `website/docs/concepts/substrate.md` for the full design, controller flags, and ActorTemplate compatibility contract. ## What this skill orchestrates (do not retype) The repeatable standup already lives in `hack/demos/cluster/install-substrate.sh`, a thin `KEEP_CLUSTER=1` wrapper over the CI-proven `scripts/agent-substrate-e2e.sh`. **Drive the installer in place; do not copy either script into the skill.** They pin the Substrate revision (`SUBSTRATE_REF`, default `b80031d260959b1fc5c6f61e3099fe2a6d368af1`) and own the heavy lifting: clone Substrate at the pinned ref, create the kind cluster + local registry, deploy the `ate-system` control plane, build/push the controller, workspace-agent, MCP server, and tool-client images; publish the Substrate `ateom-gvisor` image; create a `WorkerPool` + gVisor `ActorTe