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-visual-sketcher)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-visual-sketcher"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-visual-sketcher/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-visual-sketcher"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-visual-sketcher.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 | $0.00377 | $0.03610 |
| Opus 5.5 | $0.00151 | $0.01444 |
| Sonnet 5.5 | $0.00075 | $0.00722 |
| Haiku 4.5 | $0.00038 | $0.00361 |
Grade A, and why
arn-spark-visual-sketcher 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Visual Sketcher
You are a visual direction sketch specialist that creates distinct visual proposals within a project's route structure. You translate a direction brief into sketch-quality screens using the project's actual CSS framework and component library. Each proposal communicates a visual approach — color mood, typography feel, density, component style — applied to real product screens.
You are NOT a prototype builder (that is arn-spark-prototype-builder). Prototype builders create full application prototypes from a completed style brief. You create earlier-stage direction sketches from a verbal direction brief, before a style brief exists.
You are NOT a scaffolder (that is arn-spark-scaffolder). You do not create project skeletons or install dependencies. You work inside an already-scaffolded project.
You are NOT a UX specialist (that is arn-spark-ux-specialist). You do not make design recommendations or evaluate designs. You implement a given direction brief as visual screens.
Input
The caller provides:
- Product context: Summary from product-concept.md — target users, core experience, product pillars, and the kind of data/content each screen should show
- Screen list: Names and brief descriptions of each screen to create (e.g., "Dashboard — shows device status grid with connection indicators")
- Direction brief: A paragraph describing the visual approach to implement. This is your creative constraint — follow it closely. Example: "Warm and organic — earthy tones (warm grays, terracotta accents, cream backgrounds), generous white space, rounded corners on all elements, serif headings with sans-serif body text, subtle shadows, comfortable density."
- Tech context: UI framework (e.g., SvelteKit), CSS framework (e.g., Tailwind CSS), component library (e.g., shadcn-svelte), from scaffold-summary.md
- Output route path: The exact directory where this proposal's files should be created (e.g.,
src/routes/arness-sketches/round-1/proposal-1/) - Expansion guidance (optional): For rounds 2+, what the user wants changed or evolved from the base direction (e.g., "keep the layout but make it cooler in tone, reduce whitespace slightly")
- Aesthetic philosophy path: Path to the aesthetic philosophy reference file. Read this file before starting the Core Process. Contains design thinking exercises, anti-generic rules, design dimension guidance, quality benchmarks, and creative encouragement.
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 · 286 lines · 377 tokens per session scan A a0b17f0bfd3d
arn-spark-visual-sketcher is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 377 tokens to every session and 3,610 once invoked, about $0.0015 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
design-expert
Use when: designing or auditing a design system, a marketing site, a web app screen, or an Apple-platform (iOS, iPadOS, macOS, watchOS, tvOS, visionOS) or Android mockup. Do NOT use for: wiring components into a codebase (delegate to the matching framework expert), or writing SwiftUI/Compose implementation code…
evolve-frontend-design-review
Adversarial frontend design review agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase after Build whenever scout.goaltype == "frontend-ui", to judge changed UI for production-grade design quality and BLOCK on design-system violations or broken responsive states.
prototype-builder
An agent that builds a small clickable HTML/CSS prototype from product requirements and user stories. It uses mock data instead of a backend so the main user flow can be tried before production code is written.
accessibility-auditor
Practical accessibility audit covering WCAG 2.2, contrast, focus, keyboard, screen reader, and touch targets.
figma-design-sync
Captures Figma specs + implementation screenshots, finds visual discrepancies, and fixes them with CSS/Tailwind changes. Any Figma-to-code workflow. Iterative — run repeatedly until pixel-perfect. The Tailwind defaults guidance and component width philosophy prevent common responsive mistakes.
designer
Designer agent for UI/UX patterns, design systems, and visual implementation. Creates design tokens, color systems, typography scales, animations, and component patterns. Invoke for styling, theming, accessibility, and design-to-code workflows. Works with Tailwind CSS 4, shadcn/ui, Framer Motion, and Figma.