# Claude Lazy Starter > Claude Lazy Starter is a free GitHub Actions workflow by The Atom that sends a single Hi through Claude Code once an hour. Because Claude Pro and Max usage windows only start when you send a message, this starts a new five hour window soon after the last one ends, even overnight, so unused hours move from your sleep into your working day. Built by The Atom (https://theatom.lk). An independent project, not affiliated with Anthropic. ## How it works - A Claude Pro or Max usage window lasts five hours and only starts when you send your first message. - Claude Lazy Starter is a GitHub Actions workflow that runs once an hour. - Each run installs Claude Code and sends one short message ("Hi") on Haiku, the smallest model, using the CLAUDE_CODE_OAUTH_TOKEN secret created with claude setup-token. - Claude Pro and Max share one usage window across claude.ai and Claude Code, so that message starts the window everywhere. - If the window has ended, a new one starts within the hour, even overnight. If a window is running, the message uses a sliver of it and nothing resets. - Result: you wake up to time already waiting, and a fresh five hour window opens right after it. ## Set it up 1. Paste the setup prompt from https://claudelazystarter.theatom.lk/#set-it-up into Claude Code. 2. Claude installs the GitHub CLI if it is missing, has you sign in to GitHub in your browser, creates a private repository, and adds the Lazy start workflow. 3. In your own terminal, run claude setup-token and save the token with gh secret set CLAUDE_CODE_OAUTH_TOKEN. 4. Claude runs the workflow once to check it. It then runs every hour by itself. Requirements: a Claude Pro or Max plan, a free GitHub account, and Claude Code. Cost: free. ## Questions ### What does Claude Lazy Starter actually do? Once an hour it sends a short Hi to Claude on your behalf. If your usage window has ended, that starts the next one. Because a window only begins once you send something, starting it early means the five hour clock runs during hours you were not going to use anyway. ### Why would I want my window to start while I sleep? A usage window lasts a fixed length once it opens. If it refreshes at eight in the morning but you do not start until noon, those four hours are lost. Starting the window at refresh time shifts that time back toward your working day. ### Does this use the Claude API? No. It sends one short message through Claude Code, the official Claude command line tool, signed in with your own subscription. Claude Code and the Claude app share the same usage window, so that one line starts your window everywhere. Nothing else is sent and your work never leaves your account. ### Where is my token kept? Only in your own GitHub repository, as an encrypted Actions secret. This site never sees it, and there is no shared server holding anyone's account. Each person runs the workflow in their own private repository. ### Does the hourly message use up my limit? Barely. Each run sends a single Hi on Haiku, the smallest model, which is a tiny slice of a window. If a window is already running the message simply uses a sliver of it; nothing resets. ### Why every hour instead of the exact moment? The workflow cannot see when your window ends, so it checks in every hour. That means a fresh window starts at most about an hour after the last one ends, while keeping the number of messages low. ### Can I change the message or turn it off? Yes. Set the LAZY_MESSAGE and LAZY_MODEL repository variables to change what is sent, or disable the Lazy start workflow from the Actions tab to pause it at any time. ### Who makes Claude Lazy Starter? Claude Lazy Starter is built by The Atom (theatom.lk). It is an independent project, not made by or affiliated with Anthropic. It only uses Claude Code, the official command line tool, with your own subscription. ## Links - Website: https://claudelazystarter.theatom.lk - Setup: https://claudelazystarter.theatom.lk/#set-it-up - Built by: https://theatom.lk