Setup & action scripts
Define the setup script and run command agents should use for your repository.
Setup scripts and run commands teach Proliferate how your repository works, so you don't have to repeat the same instructions in every prompt.
Each repository has two script fields, configured under Settings → Repo → Actions:
- Setup script: installs dependencies and prepares generated files.
- Run command: starts the app, service, preview, or dev server.
Both are set separately for the repo's local checkout and its cloud environment, since the two often need different commands (a local setup script might skip a step your machine already has cached, for example).
Repo settings: Actions pane
Settings → Repo → Actions, showing the Setup script editor and Run command field, with a Cloud/Local toggle at the top of the repo settings screen.
Setup script
The setup script runs automatically:
- Local: once, inside a newly created worktree.
- Cloud: once, when a cloud workspace is created.
It has access to environment variables that describe where it's running:
A typical setup script installs packages and generates anything the repo needs before an agent starts working:
Proliferate also scans the repo for common setup commands and files that are
usually gitignored but still needed locally (like .env). When it finds
matches, it shows them as suggestions you can check on or off, and they get
appended to your setup script automatically.
Detected setup suggestions
Suggestions row under the setup script editor with two groups, Detected and Sync ignored files, each a checkbox list of commands like 'pnpm install' next to the file that triggered the detection.
Run command
The run command is what the workspace's Run action launches: your app, server, or preview process. It runs inside the selected workspace with:
Use normal shell expansion in the command itself:
There's no separate test or review command field. If you want an agent to run your test suite or linter as a matter of course, say so in your prompt, or fold the command into the run script. Agents are also good at finding a repo's existing test and lint commands on their own.
What makes a good script
Good setup scripts and run commands are deterministic, fast enough for repeated use, and safe for an agent to run without extra context.
Prefer commands that:
- Fail clearly.
- Avoid destructive behavior.
- Work from a fresh checkout.
- Match the checks humans already trust.
Next: lifecycle and monitoring.