Verified against Cursor · 2026-07-25
Hand Cursor Background Agents a task that survives you not being there
A self-contained brief for Cursor's Background Agents — the async, remote-run agent mode — with success criteria and a rule to resolve ambiguity conservatively, since no one will answer follow-up questions while it works.
The prompt
Ready to copy — highlighted parts are example details you can swap.
BACKGROUND AGENT TASK This runs unattended in a remote environment. No one is present to answer follow-up questions while you work — resolve ambiguity by choosing the most conservative option and documenting the choice, rather than pausing to ask. TASK Migrate all remaining class components in src/components/legacy/ to function components with hooks, preserving existing prop interfaces exactly. SUCCESS CRITERIA — the task is only done when every one of these is true 1. Zero class components remain under src/components/legacy/. 2. Existing prop types are unchanged. 3. Full test suite passes. 4. No new console warnings in dev mode. CHECK-IN POINTS — pause and report progress at these milestones, but keep working past them unless told otherwise After every 5 components migrated, and immediately if any existing test starts failing. RULES FOR UNATTENDED WORK - Commit in small, reviewable increments with descriptive messages, not one giant commit at the end. - If you hit a blocker the success criteria can't resolve, stop, write down exactly what you tried and why it failed, and leave the branch in a working, buildable state rather than half-finished. - Open a draft PR when finished, with a summary of every decision you made without asking, so it can be reviewed in one pass.
Customize the highlighted detailsoptional — the prompt above already works
Why this works
Background Agents run in an isolated, cloud-provisioned checkout disconnected from your live editor session, and they run asynchronously — the entire back-and-forth clarification loop that a live Composer session gets for free (you notice it's about to do something wrong and say so mid-turn) isn't available here. The brief has to front-load every decision point that would normally get resolved in chat, which is why 'resolve ambiguity conservatively and document the choice' is doing real work: it substitutes a standing policy for the live human judgment call that isn't there. SUCCESS CRITERIA plays the same substitute role for the human 'yes, that's right, keep going' signal. Requiring small commits and a draft PR at the end matches how the output actually gets consumed — you review it as a diff/PR afterward, not as a live edit stream, so the deliverable has to be reviewable in that shape from the start, not reconstructed after the fact.
Verified against
Cursor 2.1 · 2026-07-25
Changelog
- 2026-07-25 — Initial publish, verified against Cursor 2.1 Background Agents.
Need this built into your business?
If a prompt isn't enough — custom software, built and maintained for you — that's Scult's day job.
EXPLORE CUSTOM SOFTWARE

