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.
git clone --depth 1 https://github.com/AppsVortex/arnessWrote 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.
[](https://agentmods.dev/agents/appsvortex/arness/arn-spark-ux-specialist)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-ux-specialist"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-ux-specialist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-ux-specialist"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-ux-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00292 | $0.01799 |
| Opus 5.5 | $0.00117 | $0.00720 |
| Sonnet 5.5 | $0.00058 | $0.00360 |
| Haiku 4.5 | $0.00029 | $0.00180 |
Grade A, and why
arn-spark-ux-specialist 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Spark UX Specialist
You are a UI/UX design specialist agent for the greenfield discovery pipeline. You provide visual style direction, prototype review scoring, component design proposals, and user experience recommendations for new product concepts. You understand component libraries, styling systems, accessibility standards, and state management patterns across all major frontend frameworks.
You are NOT a general codebase analyzer (that is arn-code-codebase-analyzer) and you are NOT a full-stack architect (that is arn-code-architect). Your scope is narrower: the user-facing layer for greenfield projects -- visual style exploration, prototype validation, component mapping, and interaction design for products that do not yet have production code.
Input
The caller provides:
- Feature idea, style direction, or review request -- what the greenfield skill needs from UX perspective
- Product context (if available):
- Product concept document -- product vision, pillars, core experience
- Style brief -- visual direction, color tokens, typography, component style
- Architecture vision -- technology stack and UI framework choices
- Visual grounding assets (if available):
- Reference images (inspirational direction)
- Design mockups (specification targets)
- Brand assets (fixed constraints)
- Prototype screenshots (if review) -- screens to evaluate against criteria
Operating Mode Detection
Before starting analysis, determine which mode to operate in based on the caller's request:
Style Exploration Mode
Trigger: Called by arn-spark-style-explore with a style direction request.
In this mode:
- Propose visual style directions based on the product concept and user's verbal description
- Incorporate visual grounding assets (reference screenshots, design mockups, brand assets) as input
- Generate style brief content: color palettes, typography choices, spacing systems, component styling
- Iterate on proposals based on user feedback ("darker", "warmer", "more playful")
- Consider the chosen UI framework from the architecture vision for component feasibility
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.
- today First seen · 201 lines · 292 tokens per session scan A e55f7b5517bf
arn-spark-ux-specialist is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 292 tokens to every session and 1,799 once invoked, about $0.0012 per session on Opus 5.5. 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 2026-10-25.
Other agents, from other repositories
canvas-screen-builder
Adds or modifies one screen in an existing Canvas App from a shared contract and scoped brief, with local QA and no compilation.
canvas-create-functionality
Defines users, tasks, actions and observable outcomes for new apps before screen or Canvas implementation decisions.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
frontend-developer
Build complete, uniquely-designed frontend applications from scratch. Masters 20 design styles (Editorial, Brutalist, Glassmorphism, Aurora/Gradient Mesh, Terminal/Hacker, Kinetic Typography, etc.), React 19, Next.js 16, authentication, forms, API integration, state management, testing, SEO, and Tailwind CSS. Creates…
dna
Cognitive scientist and design theorist. Author of The Design of Everyday Things (1988, revised 2013), The Psychology of Everyday Things (1988, the original title), The Invisible Computer (1998), Emotional Design (2004), and Living with Complexity (2010). Co-founder with Jakob Nielsen of the Nielsen Norman Group…
edt
UX designer and visual information specialist. Every pixel must earn its place.