Precise timing.
Your phone has a stopwatch, and it is fine until you need to actually do something with the lap times. The built-in apps record laps and then bury them in a list you cannot sort or compare. If you are timing sprints, cooking steps, or measuring how long a task really takes, you want to see which lap was fastest and which one dragged, at a glance. This blueprint builds a stopwatch that treats laps as data, not a scrolling receipt.
A precise stopwatch with real lap tracking. Start it, hit lap as many times as you need, and each split lands in a list below the timer. The fastest and slowest laps are highlighted automatically, so the standout and the drag jump out without you scanning every row. The timing runs off a proper clock rather than a naive interval, so the elapsed count stays accurate even when the tab is busy.
You watch it happen in the task workspace: the agent scaffolds the project, writes the timing and lap logic, starts the dev server, and confirms the laps record and highlight correctly before handing you a live preview. The code lands on a branch in your repository with a pull request ready.
The first version is a starting point you steer with plain follow-up messages:
Each follow-up wakes the same repository and the agent continues on its own code.
How precise is the timing? It tracks elapsed time against the system clock rather than counting interval ticks, so it stays accurate over long runs instead of drifting.
What does the highlighting show? The fastest and slowest laps are marked as you go, so your best and worst splits are obvious without any manual comparison.
Does it keep my laps if I refresh? Not by default; ask the agent to save laps to local storage and your session survives a reload.