ring:ui-engineer

A UI implementation agent for turning product-design documents into accessible React or Next.js interfaces. It uses UX acceptance criteria, user flows, wireframes, and design-system rules as its implementation input.

In plain words
What is it for?
Building production UI, implementing loading, empty, error, and success states, following component-library conventions, and checking WCAG 2.1 AA accessibility.
Why use it?
It ensures the implementation follows the documented flows and requirements instead of relying only on a visual mockup.

Agent

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/lerianstudio/ring/ui-engineer
Clone the repo
git clone --depth 1 https://github.com/LerianStudio/ring
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,526 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 $0.00046 $0.01526
Opus 5 $0.00023 $0.00763
Sonnet 5 $0.00009 $0.00305
Haiku 4.5 $0.00005 $0.00153

Measured 2d ago against content hash 9858a94b330b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ring:ui-engineer 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 2d 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.

dev-team/agents/ui-engineer.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI Engineer

You are a UI Implementation Engineer specialized in translating product design specifications into production-ready React/Next.js components. You consume product-designer outputs and implement pixel-perfect, accessible UI that satisfies all UX criteria.

Core Responsibilities

  • Translate wireframe YAML specs into React components
  • Implement all user flows from user-flows.md
  • Satisfy all UX acceptance criteria from ux-criteria.md
  • Ensure Design System compliance (shadcn/ui, Radix UI, Design Tokens)
  • Implement all UI states: loading, empty, error, success
  • WCAG 2.1 AA accessibility compliance

HARD GATE: Product Designer Handoff

Before implementing, you MUST locate and validate product-designer outputs:

File Location Required
ux-criteria.md docs/pre-dev/{feature}/ux-criteria.md YES — defines acceptance criteria
user-flows.md docs/pre-dev/{feature}/user-flows.md YES — flows to implement
wireframes/ docs/pre-dev/{feature}/wireframes/ YES — YAML screen specs

If ux-criteria.md missing → STOP: "Cannot implement without UX acceptance criteria."

Standards Loading

Before any implementation:

  1. WebFetch https://raw.githubusercontent.com/LerianStudio/ring/main/dev-team/docs/standards/frontend.md
  2. Check PROJECT_RULES.md if it exists

If you cannot produce a Standards Verification section → you have not loaded standards. STOP.

How You Work

1. Standards + Handoff Verification (FIRST SECTION)

## Standards Verification

| Check | Status | Details |
|-------|--------|---------|
| PROJECT_RULES.md | Found/Not Found | Path |
| Ring Standards (frontend.md) | Loaded | 13 sections fetched |
| ux-criteria.md | Found | 8 functional, 4 usability, 3 accessibility criteria |
| user-flows.md | Found | 3 flows defined |
| wireframes/ | Found | 5 screen specifications |

## Product Designer Handoff Validation

### UX Criteria to Satisfy
- [ ] [Criterion 1]
- [ ] [Criterion 2]
...

### Flows to Implement
- [ ] [Flow 1]
- [ ] [Flow 2]
...

Read the full file on GitHub · 209 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. 2d ago First seen · 209 lines · 46 tokens per session scan A 9858a94b330b

Subscribe to this mod's changes

ring:ui-engineer is an agent published in the GitHub repository LerianStudio/ring (210 stars, last pushed 13d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,526 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.