Cloud features
Run planning and code review in the cloud from Cluster Build — /ultraplan plans against your repos on a remote VM, and /ultrareview runs a fleet of review agents on a pull request.
Most of Cluster Build runs locally on your machine. Two commands reach into the cloud for work that's bigger than a single session — they run on Cluster's Managed Agents service, on remote VMs, while you watch the results stream into your terminal.
Cloud features need the managed-agents host set in your config:
cluster config set managed_agents_url https://agents.clusterbase.devBoth commands are available in interactive sessions only.
/ultraplan
/ultraplan [--repo name=spec] <request>/ultraplan offloads read-only planning to a cloud VM. Cluster provisions an
ephemeral environment with your repositories cloned, a planning agent explores the
code there, and the resulting plan streams back to your terminal — ready for you to
review and implement locally. Nothing is changed on the remote VM; the output is a
plan, not a commit.
Use it when planning a change needs more context than your local session can hold, or spans repositories you don't have checked out.
/ultraplan is model-managed: the assistant starts the run, tells you it's
continuing in the background, and delivers the finished plan back into the
conversation on its own — you don't poll for it. Use /ultraplan --status to
check on an in-flight run, or /ultraplan --stop to cancel it.
/ultrareview
/ultrareview/ultrareview launches a cloud multi-agent code review. The assistant infers
what to review — a diff against a base branch, your uncommitted changes, a
specific commit, or custom instructions — from the conversation and your repo
state, asking only if the scope is genuinely ambiguous. A fleet of specialist
review agents (correctness, security, performance, and more) then runs in
parallel on a remote VM, and their findings are cross-validated into a single
consolidated review. When the reviewed changes match an open pull request, the
review is also posted there as a comment.
Like /ultraplan, /ultrareview is model-managed: it runs in the background and
its findings are delivered back automatically. Use /ultrareview --status to
check progress, or /ultrareview --stop to cancel it.
You can also trigger a review from GitHub by mentioning @cluster-build review
(or @cluster-build ultrareview) on a pull request — see
Triggers.
How it runs
Both commands run server-side, on the same infrastructure described in the Managed Agents docs:
- On-demand runs — how a one-off cloud run is kicked off, with your repos cloned in.
- Environments — the Firecracker VMs the agents execute inside, provisioned on your behalf and torn down automatically.
The VM is provisioned under your own identity using the credentials from
cluster login, so it sees only what you can access.
Next steps
- Models & configuration — where
managed_agents_urllives. - Managed Agents — define, schedule, and trigger your own cloud agents beyond these built-ins.