Launch from Ticket
The hands-on ClusterCode workflow: paste a ticket, get a DevBox prepared for it — repo cloned, branch created, ticket context written, agent CLI installed — and take the terminal yourself. To have ClusterCode do the work instead, see Run an agent on demand.
1. Open the launch modal
Section titled “1. Open the launch modal”From the orchestrator dashboard, click Launch or ask Nucleus:
“Launch a DevBox for https://github.com/org/repo/issues/42”
2. Paste the ticket URL
Section titled “2. Paste the ticket URL”Supported formats:
https://github.com/owner/repo/issues/123https://dev.azure.com/org/project/_workitems/edit/456- Trello and Monday.com — coming soon
3. Select a worker
Section titled “3. Select a worker”The system pre-selects a worker for you, and you can override it. Leaving it on auto-select hands the choice to the placement rules — which pack onto the fullest host that still fits, not the least-loaded one. See how a target is chosen.
4. Choose a runtime
Section titled “4. Choose a runtime”Pick an AI agent:
- Claude Code (default)
- GitHub Copilot
- Codex
5. Launch
Section titled “5. Launch”Click Launch. Within 30 seconds the DevBox is ready:
- Ticket details are fetched from the provider
- A
CLAUDE.mdis generated with full context - The repository is cloned into the DevBox
- The agent CLI is installed and the ticket context is in place
The agent is ready — it is not running yet. A launch gives you a prepared environment, not an autonomous worker. To start work, pick one:
| You want | Do this |
|---|---|
| To drive the agent yourself | Open the live terminal and run claude (or codex, copilot) |
| The agent started for you on every launch | Add a Post-Launch Workflow to your NUCLEUS.md |
| ClusterCode to plan and execute the whole ticket | Start a Run with the ticket URL instead of launching a DevBox |
6. Monitor
Section titled “6. Monitor”From the dashboard:
- Watch the live terminal output
- See resource usage (CPU, memory, disk)
- Intervene at any time via the web terminal
7. Review the results
Section titled “7. Review the results”A DevBox does not open a PR on its own — the agent working inside it does, when you ask it to. Once the work is done, from the live terminal:
gh pr create --draftopens the draft PR- Update the ticket from the terminal, or let a Run handle it
If you want ticket → PR with no manual steps, that’s a Run, not a launch.
- Use specific, well-written tickets — the AI agent’s output quality depends on the input context
- Enable host networking if the DevBox needs to expose ports for local testing
- You can launch multiple DevBoxes in parallel across different workers