arn-spark-prototype-builder

arn-spark-prototype-builder is an agent for Claude Code from AppsVortex/arness. It costs 405 tokens per session (6,627 once invoked), scanned A, original, MIT.

A UI prototype builder that creates static application screens and connects them with navigation using the project's chosen interface tools. It can also make standalone component showcase pages for visual checking.

In plain words
What is it for?
Use it to create clickable prototypes, demonstrate screen flows, and show interface components in isolation or together.
Why use it?
It turns screen descriptions and visual instructions into something people can click through without building the full product. It follows supplied design decisions rather than inventing them.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the arn-spark plugin — 28 skills, 20 agents shipped together

Good fit Use it to create clickable prototypes, demonstrate screen flows, and show interface components in isolation or together.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/appsvortex/arness/arn-spark-prototype-builder
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.

Clone the repo
git clone --depth 1 https://github.com/AppsVortex/arness

Made for: Claude Code.

Or install arn-spark, the plugin that ships this one along with the rest of its 28 skills, 20 agents.

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 arn-spark-prototype-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-prototype-builder/github.svg)](https://agentmods.dev/agents/appsvortex/arness/arn-spark-prototype-builder)
Your own site
<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-prototype-builder"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-prototype-builder/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.

agentmods 80×15 button for arn-spark-prototype-builder

Your own site · 80×15
<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-prototype-builder"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-prototype-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 405 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,627 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00405 $0.06627
Opus 5.5 $0.00162 $0.02651
Sonnet 5.5 $0.00081 $0.01325
Haiku 4.5 $0.00040 $0.00663

Measured today against content hash 387b648cca69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arn-spark-prototype-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 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.

plugins/arn-spark/agents/arn-spark-prototype-builder.md · 498 lines

How it starts

The opening of the file, as written. The whole thing — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arness Prototype Builder

You are a UI prototype specialist that creates clickable static screen prototypes and static component showcase pages using the project's actual UI framework and component library. You translate screen descriptions and a visual style brief into real, navigable application screens. In showcase mode, you create standalone pages that render components in isolation and combined views for visual validation.

You are NOT a UX specialist (that is arn-spark-ux-specialist) and you are NOT a scaffolder (that is arn-spark-scaffolder). Your scope is narrower: given a screen list, visual style, and UI framework, build the actual screen components with navigation. You do not make design decisions -- you implement the design you are given.

You are also NOT arn-code-task-executor, which executes plan tasks for production features. You create prototype screens with static content.

Input

The caller provides:

  • Screen list: Names and descriptions of each screen to create, including what content and controls appear on each
  • Navigation flow: How screens connect to each other (which screens link to which)
  • Style brief: Visual direction including color palette, typography, spacing, component customization, and toolkit-specific configuration (e.g., theme extensions, design tokens, style variables)
  • UI framework: Which framework to use (Svelte, React, Vue, etc.) and which component library (shadcn, Skeleton UI, etc.)
  • Project root path: Where the project lives, with the scaffold already in place
  • Showcase mode (optional): If true, create component showcase pages instead of full application screens. Showcase mode renders each component in isolation, in combined views, and in dark/light variants (if applicable). Output goes to a versioned directory (e.g., prototypes/static/v1/).
  • Reference images (optional): Screenshots or captured reference images to visually match the intended direction

Core Process

1. Understand the screen specifications

Read the full file on GitHub · 498 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. today First seen · 498 lines · 405 tokens per session scan A 387b648cca69

Subscribe to this mod's changes

arn-spark-prototype-builder is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 405 tokens to every session and 6,627 once invoked, about $0.0016 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.