Who it is forA developer with a backlog of small features or fixes who wants them worked on overnight, and who needs every change checked by tests before it reaches main.
The problemRunning claude in a plain loop forgets what it did, cannot split work, and can burn through your usage limits without warning.
The outcomeA sub-agent builds the requested change on its own branch, and the farm puts it on main only after your test command passes.
What you need first
- Docker on a machine or server that stays on
- A Claude subscription to sign in with
- A Git repo you control, with a deploy key if you want the farm to clone and push to it
- Your test command, for example pytest -q
Steps
- Run
curl -fsSL https://raw.githubusercontent.com/matank001/clodfarm/main/scripts/install.sh | shon the machine that will host the farm. - Open the login URL the installer shows, approve it on any device, and paste the code back.
- Set FARM_REPO_URL to your repo and add a deploy key, then set FARM_VERIFY_CMD="pytest -q" in your settings.
- Run
docker exec clodfarm clodfarm spawn "Add CSV export" --prompt "Add CSV export to the report page, with tests.". - Run
docker exec clodfarm clodfarm statusin the morning and check the result on main.
Prompt for your agent
Use the clodfarm repo (github.com/matank001/clodfarm). Start the farm with the install script, set FARM_REPO_URL to <repo-url> and FARM_VERIFY_CMD to "pytest -q", then spawn a task with `docker exec clodfarm clodfarm spawn "<task title>" --prompt "<task description>"`. Report the output of `docker exec clodfarm clodfarm status`, and confirm the change reached main only after tests passed.
Caveat. Clodfarm paces usage on your subscription, but every Claude on the farm still runs on a Claude subscription, so its limits still apply.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page