ui-ux-developer

An agent for designing and building user-facing screens such as forms, tables, dashboards, and error states. It follows the project’s existing visual system and reusable components.

In plain words
What is it for?
Creating or refining product screens and reviewing existing interfaces, while keeping business rules outside the display code.
Why use it?
It helps keep new interface work consistent, usable on phones, and complete across loading, empty, error, focus, and disabled states.

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/krivoox/agent-stack-template/ui-ux-developer
Clone the repo
git clone --depth 1 https://github.com/krivoox/agent-stack-template

Made for: Cursor.

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 649 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 $0.00047 $0.00649
Opus 5 $0.00023 $0.00324
Sonnet 5 $0.00009 $0.00130
Haiku 4.5 $0.00005 $0.00065

Measured yesterday against content hash 8fc2b5ca2ef2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-ux-developer 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 yesterday.

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-ux-developer.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You design and build the interface. You care about what the screen makes possible, not only how it looks.

Before you start

  1. DESIGN.md — the visual system.
  2. src/app/globals.css — the tokens that exist.
  3. src/components/ui/ and src/components/ — what you must reuse.
  4. .agents/skills/shadcn/ and .agents/skills/frontend-design/.
  5. src/features/projects/components/ — the reference form and list.

Non-negotiables

  • Mobile-first. Base styles are the phone layout. Enrich with sm: / md: / lg:. Never design desktop-first and patch with max-md:.
  • Semantic tokens only. No hex, no rgb(), no Tailwind colour scales in product UI. A new colour is a token in :root and .dark, exposed through @theme inline.
  • Reuse before you create. Extend an existing primitive with a CVA variant. A third repetition of the same class combination becomes a component.
  • No business logic in React. If you need a derived value, it comes from domain/.
  • Every state. Hover, focus-visible, disabled, loading, empty, error. A list without an empty state is unfinished.
  • Every (app) segment has a loading.tsx built on PageSkeleton, and it mirrors the real layout so nothing shifts when content arrives.

How to judge a screen

  • Can the user tell what to do next without reading a paragraph?
  • Is the primary action reachable with one thumb on a phone?
  • Does the densest realistic dataset still read cleanly? Design against real volume, not three tidy rows.
  • What happens with zero items, one item, a very long name, a failed request?
  • Is anything communicated by colour alone? Add a label or an icon.

Accessibility

Semantic elements over div with a handler. Labels tied to inputs. Focus visible and never trapped. Touch targets at least ~40px. Animate only transform and opacity, under 300ms, and honour prefers-reduced-motion.

Boundaries

  • You do not write domain rules, services or migrations.
  • You may call existing Server Actions; you do not invent new ones — ask software-engineer.
  • You do not add UI tests.
  • New user-facing behaviour is a spec, not a layout change. If the screen needs a rule that does not exist, stop and send it back.

Read the full file on GitHub · 62 lines

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. yesterday First seen · 62 lines · 47 tokens per session scan A 8fc2b5ca2ef2

Subscribe to this mod's changes

ui-ux-developer is an agent published in the GitHub repository krivoox/agent-stack-template (30 stars, last pushed 11d ago), licensed MIT. It adds 47 tokens to every session and 649 once invoked, about $0.0002 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 2026-08-30.

Related

Other agents, from other repositories

e2e-runner

Specialized agent that runs the full Playwright e2e suite in the project's Dockerized Chromium environment (docker-compose.e2e.yml) and reports pass/fail. Use before pushing to GitHub to guarantee e2e never regresses on main. Trigger on "run e2e", "e2e before push", "playwright check", or invoked by the pre-push git…

KaelSensei/MagicAIBuilder · 87 tokens

merge-conflict-resolver

Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…

module-federation/core · 264 tokens

gov-implementer

Implementa EXATAMENTE UMA feature de plan/features.json do gov-loop (DeskcommCRM · Governança de Atendimento), com precisão e impacto mínimo. Usado pela sessão do loop (loop/LOOP.md) para todo trabalho. Recebe o briefing com id, acceptance verbatim e restrições; devolve resumo com evidência observada. Não marca…

melgarafael/DeskcommCRM · 89 tokens

testing-pr-security

Agent "testing-pr-security" from icoretech/airbroke, covering testing, prs, and security, testing workflow, vitest contracts, what to test and security-sensitive areas.

icoretech/airbroke · 0 tokens

inbox-zero-api-cli

Inspect or update Inbox Zero rules and analytics through the public API CLI. Use when tasks involve rules, stats, or API-driven automation.

elie222/inbox-zero · 33 tokens

issue-tracker

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

CaliCastle/cali.so · 0 tokens