Who it is forA developer who has hit a rough edge in Errand, such as a confusing activity state or a connection problem, and wants to fix it.
The problemWithout a reproducible report and passing checks, a fix is hard for maintainers to review and may break the build.
The outcomeA tested change is ready as a pull request, with steps to reproduce and the expected behavior written up as the project asks.
What you need first
- A Mac running macOS 13 or later on Apple Silicon
- Node.js 22 to 26 and npm 10 or later
- A Runta account with model access configured for your agents
- Git to clone the repository
Steps
- Run
git clone https://github.com/runta-dev/errand.gitandcd errand - Run
npm ciandnpm run devto reproduce the issue - Make your change, then run
npm run typecheck,npm run lint,npm test, andnpm run build - Open a pull request at https://github.com/runta-dev/errand/pulls that includes the steps to reproduce, what you expected, and what happened
Prompt for your agent
In the runta-dev/errand repository, reproduce the bug <bug description> using npm ci and npm run dev, then apply a fix. Expected output: a diff where npm run typecheck, npm run lint, npm test, and npm run build all pass. Verify each script exits with success before you write the pull request description.
Caveat. The README asks for reproducible reports, so an unverified guess about a bug is less likely to be accepted than a fix with clear reproduction steps.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for runta-dev/errand and "Fix a bug in Errand and run its checks before a pull request"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer