Tasks
Each task is a small, realistic job with a hidden test suite. Tasks get added one at a time, and only after the harness proves it can tell broken work from correct work.
Task #1: Fix a broken authentication flowDebuggingA small Node.js auth module ships with six user-reported bugs: broken password checks, case-sensitive emails, sessions that die instantly, logout that doesn't log out, account takeover via re-registration, and an off-by-one lockout. The agent gets the bug reports and 3 visible tests; scoring uses a 19-test hidden suite.19 hidden tests · JavaScript (Node.js 20+, zero dependencies) · published Oct 11, 2026Next tasks (planned, not yet published)
- Build a landing page from a written brief (visual + accessibility checks)
- Add Stripe-style payment webhooks to an existing API
- Refactor a legacy module without changing behaviour
- Find and fix a bug from a production stack trace
Want a specific task? Propose one.