The Claude Code workbench
The workbench is a folder you download once and keep. Opened with Claude Code, it turns the agent into your Looky guide: it installs the tools, connects the folder to your instance, and then works with you day to day — pulling workspaces, authoring content, validating and publishing — explaining each step in plain language. No terminal, Python or git knowledge required.
Prefer git? git clone https://github.com/paranoid-software/looky-claude-code works too, and updates arrive via git pull.
Before you start
- Claude Code installed, on a paid Claude plan (or API credit) — Claude Code is not part of the free tier. If a free option matters to you, the Cursor workbench covers the same ground on Cursor's free plan.
- Access to your Looky instance: an invitation to an account, as a developer if you'll publish content.
- Windows, macOS or Linux — the workbench handles each one's quirks.
Get going in three steps
- Download and extract the ZIP wherever you keep your documents.
- Rename the folder after your instance — for example
my-lookyformy.looky.studio. One folder per instance; several instances, several folders. - Open the folder with Claude Code and type: "Help me set up this looky workbench from scratch."
The agent asks how you prefer to work and takes it from there. The verification code for signing in arrives in your email — that, choosing names, and approving what gets published are the only things it will ever need from you.
Two ways of working — you choose, and can switch anytime
Guide mode
You type, it teaches
The agent dictates each command, explains what it does in one line, and you run it in your terminal. By the end you can drive Looky yourself — ideal for training.
Do-it mode
It runs, you approve
The agent executes everything itself and narrates. You review, decide and approve — especially anything that goes live.
Daily life in the workbench
Creating content is just conversation. "Make me a bar chart of sales by month", "a dashboard for the fulfillment team with these three KPIs" — the agent authors it, validates it, and shows you. For the mechanical operations there are shortcuts:
/setup— first-time setup, or repairing anything missing/connect— sign in / reconnect to your instance/billingand/workspaces— see and switch where you're working/pull— bring a workspace's content to your folder/create-workspace— start a brand-new workspace/validate— check everything before publishing/publish— review and publish, always with your explicit approval/update— update the workbench itself to the latest version/mode— switch between guide mode and do-it mode
What keeps you safe
- Nothing goes live without your yes. Publishing always ends in an explicit question, and the instance validates content before writing anything.
- Credentials stay out of reach. The workbench never touches data-source credentials or deploys source settings — that remains with your account's developer or owner.
- Everything is contained. The tools install inside the folder; your computer's setup is left alone. Deleting the folder deletes everything (your published content lives safely in your instance — pull it again anytime).
See the change with your own eyes: after each publish, open your Looky in the browser and refresh. That loop — ask, publish, look — is the whole workflow.