Dashboard Overview
The screen an app opens on: shell, header, KPI row, chart and activity feed — numbers first, shape second, changes last.
One run opened up in the order you would debug it — intent, actions, the retries that are invisible in both, then cost.
app/agent-run-page.tsxnpx hoverlab add agent-run-page
Or over MCP, from your editor's agent — no account needed.
Free to read, copy and install, for personal and non-commercial projects. Shipping it in client work or a paid product needs Pro ($79 once). The source lands in your repo and stops being ours — no attribution, nothing to upgrade.
Everything the run did, in the order you would debug it — intent, actions, failures, then cost.
A retried step that is invisible reads as a slow agent. A retried step that is shown reads as a careful one, and it is the same run either way.
Per step, not per month. A bill that only arrives in aggregate cannot be acted on — the useful version says which step was expensive and whether it needed to be.
The real page, rendered in your current theme — every section below is a live block, not a screenshot.
Only want one section? Open it and copy that block instead — browse Agent Reasoning.
Want the whole project rather than this one screen? A template ships every route, the theme tokens and the layout.
/**
* One agent run, opened up — what it thought, what it called, what it
* retried, and what it cost.
*
* The four panels here are usually four products' worth of surface, and
* most agent UIs ship the first one alone: a reasoning trace, which shows
* the thinking and hides everything that makes the thinking trustworthy.
*
* The order is the order somebody debugs in. The trace says what it was
* trying to do; the tool calls say what it actually did; the retry log
* says what went wrong on the way, which is invisible in the first two;
* and the cost breakdown says what that sequence was worth. Reading them
* in that order turns a run from a wall of text into an account.
*
* The obvious wrong answer is putting cost first because it is the
* smallest number on the page. Cost is the last question, not the first —
* nobody asks what a run cost until they know whether it worked.
*
* A note for anyone copying this: the retry log is the panel to keep if
* you only keep one besides the trace. A retried step that is invisible
* reads as a slow agent, and slowness with no explanation is the most
* common reason these products get abandoned.
*/
import * as React from 'react'
import { AgentThinkingTrace } from '@/components/agent-thinking-trace'
import { AgentToolCalls } from '@/components/agent-tool-calls'
import { AgentRetryLog } from '@/components/agent-retry-log'
import { AgentCostBreakdown } from '@/components/agent-cost-breakdown'
export default function AgentRunPage() {
return (
<main className="min-h-screen bg-background text-foreground">
<section className="mx-auto w-full max-w-3xl px-6 pb-2 pt-12">
<h1 className="text-2xl font-bold tracking-tight">Run detail</h1>
<p className="mt-1 text-sm text-muted-foreground">
Everything the run did, in the order you would debug it — intent,
actions, failures, then cost.
</p>
</section>
<AgentThinkingTrace />
<AgentToolCalls />
<AgentRetryLog />
<AgentCostBreakdown />
</main>
)
}
components/ — each block page has its own copy button.app/agent-run-page.tsx. The imports already point at @/components/…, so they resolve with no edits.The component, its props, the design tokens it expects and the command that installs it — as one prompt. Paste it into Claude, Cursor, v0 or ChatGPT and what they build around it will match the rest of the catalog instead of inventing its own system.
The screen an app opens on: shell, header, KPI row, chart and activity feed — numbers first, shape second, changes last.
An agent working inside a real app: a transcript down the middle — reasoning, answer, then the one card that can act — with what it may read and what it noticed demoted to a rail.
A kanban board inside the app shell, with tabs that admit the board is one view among several and a header whose primary action is creating work.
The canonical CRUD list — header, toolbar, sortable table and pagination framed as one panel instead of three stacked cards.
A wizard for the session someone finishes and a checklist for the one they do not, with the only genuinely blocking step in front of both.
Built around the state a search page is in most of the time — empty — so recent queries lead and the facets sit in a sidebar that survives growing to twelve.
The queue, the same queue sorted by how long things have waited, and the policy that decided both — with the policy last so it is not scrolled past forever.
The blank thread answered with real starter prompts, the model picker with the three numbers the choice turns on, and the four surfaces a session grows into — attachments, branches, canvas, threads.
The three states an agent screen usually omits: the wait before the first token, the trace after something broke with retries costed in the open, and the diff it wants a person to accept.
Why the answer said what it said: what is connected, how stale it is, what the query was allowed to see, what fitted in the window and what fell out — plus the failed-search state a debugging tool is most needed in.
Five ways to reach a model without the cursor leaving the sentence — slash menu, inline completion, selection toolbar, action menu, property inspector — and the two surfaces that say where the answer came from.
A table after real people have used it — columns reordered from the keyboard, a selection bar that asks page-or-all, subtotals that survive collapsing, cells edited in place, and the empty state its own filters produced.
The saved view and the comparison window first, because every figure below depends on both — then six charts, none of which load a charting library.
Thresholds with how often each has actually fired, what that produced, where it went — and the digest settings that exist because of the answer.
The flow between an empty product and a useful one, in the order it goes wrong: sample data offered with equal weight, a file, a URL, the column mapping everything stalls on, and an upload that survives the connection dropping.
A profile form where the role options state what they actually change, the avatar crop works from the keyboard, and a navigation guard names the fields it is about to throw away.
The furniture that is on every screen and belongs to none — navbar, mobile drawer, command palette, shortcut sheet, header search, scope switcher, and the two shapes a detail view takes without losing the list.
Backwards from now and forwards from it on one screen — a day-grouped timeline, a month grid where a busy Tuesday never changes the row height, and the state both are in on day one.
What the product looks like while onboarding happens: a tour step anchored to the control it explains, the skeletons of the slowest load it will ever do, and the checklist that outlives both.