Nucleus Configuration
NUCLEUS.md is a per-tenant configuration file that customizes how Nucleus behaves. It lets you define workflows, skip confirmation prompts, and set up post-launch automation — all in plain Markdown.
Where to Edit
Section titled “Where to Edit”NUCLEUS.md is managed in the orchestrator dashboard:
- Open the orchestrator at your deployment URL
- Go to Settings
- Find the NUCLEUS.md section
- Click Edit NUCLEUS.md
Your configuration is stored in the browser and sent to Nucleus as part of its system instructions on every request. Maximum length is 10,000 characters.
How It Works
Section titled “How It Works”When Nucleus receives a message, it loads your NUCLEUS.md content as mandatory instructions that override its default behavior. Nucleus will execute every step you define in order — it won’t skip steps or stop early. Safety requirements (confirming destructive operations like stop/remove) still take priority.
Directives
Section titled “Directives”Auto-Launch
Section titled “Auto-Launch”By default, Nucleus shows a launch summary and waits for your confirmation before creating a DevBox. Add the auto-launch directive to skip the confirmation:
## Launch Settings
auto-launchWith auto-launch enabled, Nucleus still resolves all values (worker, image, name) and shows a brief summary, but proceeds immediately without waiting for “yes.”
Post-Launch Workflow
Section titled “Post-Launch Workflow”Define what Nucleus should do automatically after launching a DevBox. Without a workflow, Nucleus asks if you’d like to open a terminal. With a workflow, it executes your steps instead:
## Post-Launch Workflow
1. Start Claude Code in the DevBox with `--dangerously-skip-permissions`2. Open the terminal so I can watchNucleus will follow these steps sequentially after a successful launch, loading the appropriate skills (background-exec, interactive-exec) as needed.
Example
Section titled “Example”Here’s a complete NUCLEUS.md that auto-launches DevBoxes and starts the AI agent automatically:
## Launch Settings
auto-launch
## Post-Launch Workflow
1. Start Claude Code with --dangerously-skip-permissions2. Open the live terminal
## Preferences
- Always use terminal images, not display images- Default to 8 GB memory for DevBoxes- When I say "go", treat it as a launch request- Keep instructions clear and actionable — Nucleus follows them literally
- Use numbered lists for sequential workflows
- The Preferences section is free-form — Nucleus interprets it as behavioral guidance
- You can reset to defaults at any time from the Settings page
- Changes take effect on the next Nucleus message — no restart needed