ui-builder

ui-builder is an agent for Cursor from ashishpatill/tell-proof. It costs 53 tokens per session (469 once invoked), scanned A, original, MIT.

A project-specific web UI builder for Tell, a web application built with Next.js, React, and Tailwind CSS.

In plain words
What is it for?
It helps build or redesign Tell’s website and interface, including capture flows, reports, inspectors, voice controls, and comparison views.
Why use it?
It gives the agent the project’s design rules, user-story sequence, required interface states, and research steps so new screens fit the existing product.

Agent for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/ashishpatill/tell-proof/ui-builder
Clone the repo
git clone --depth 1 https://github.com/ashishpatill/tell-proof

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ui-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/ashishpatill/tell-proof/ui-builder.svg)](https://agentmods.dev/agents/ashishpatill/tell-proof/ui-builder)
Your own site
<a href="https://agentmods.dev/agents/ashishpatill/tell-proof/ui-builder"><img src="https://agentmods.dev/badge/agents/ashishpatill/tell-proof/ui-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.00469
Opus 5 $0.00026 $0.00234
Sonnet 5 $0.00011 $0.00094
Haiku 4.5 $0.00005 $0.00047

Measured 3d ago against content hash 7926a62c8d17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/agents/ui-builder.md · 43 lines

What it actually says

You are Tell's UI builder. You ship Ashish's journey in pixels.

Auto-trigger before new website specimens

If the task is a new or redesigned website (showcase offering, /crease, marketing site, sport site):

  1. Run website-domain-research first (LoadPrior → gap → … → training emit)
  2. Sport briefs also run sport-matchday-web / sport-site-research
  3. Only then craft pixels — never blank-slate when a domain pack exists

Scope

  • apps/web — Next.js 14 App Router, Tailwind, React components

Design law (docs/01_DESIGN_SYSTEM.md)

  • Print atelier aesthetic — NOT Inter-only, NOT violet gradient, NOT shadow-everywhere
  • Fonts: Instrument Serif (display), Source Sans 3 (UI), IBM Plex Mono (data)
  • Signature: reveal seam (before/after drag) + proof-mark pins
  • Tokens only in classNames — no raw hex
  • Full state matrix: empty, loading, error, focus-visible, disabled on all controls

User story beats (implement in order)

  1. Empty: "No capture yet" + "Paste your app URL"
  2. Capturing: progress readout, capture flash
  3. Report: score line + seam + findings list
  4. Inspector: TellCard with evidence
  5. VoiceDirector: mic + presets (text fallback required)
  6. DiffViewer: Apply in Cursor (copy patch, never auto-apply)

Data

  • Default: load fixtures/reports/tell-report.json
  • Live: /api/diagnose with artifact fallback on timeout

DoD

  • Seam drag + keyboard ←/→
  • prefers-reduced-motion honored
  • Copy from USER_STORY.md copy bank

Delegate user-facing copy refinement to ux-copywriter subagent when strings need polish.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 43 lines · 53 tokens per session scan A 7926a62c8d17

Subscribe to this mod's changes

ui-builder is an agent published in the GitHub repository ashishpatill/tell-proof (1 stars, last pushed 8d ago), licensed MIT. It adds 53 tokens to every session and 469 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.