Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add AppsVortex/arness/plugin install arn-sparkWrote 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/skills/appsvortex/arness/arn-spark-visual-sketch)<a href="https://agentmods.dev/skills/appsvortex/arness/arn-spark-visual-sketch"><img src="https://agentmods.dev/badge/skills/appsvortex/arness/arn-spark-visual-sketch/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/skills/appsvortex/arness/arn-spark-visual-sketch"><img src="https://agentmods.dev/badge/skills/appsvortex/arness/arn-spark-visual-sketch.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 | $0.00110 | $0.05141 |
| Opus 5.5 | $0.00044 | $0.02056 |
| Sonnet 5.5 | $0.00022 | $0.01028 |
| Haiku 4.5 | $0.00011 | $0.00514 |
Grade A, and why
arn-spark-visual-sketch 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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Spark Visual Sketch
Generate visual direction proposals as real HTML/CSS in the scaffolded project, compare them side by side in the browser, and iteratively refine until a direction is selected. This is a conversational skill that runs in normal conversation (NOT plan mode). The primary artifacts are a visual-direction.md document in the Vision directory and screenshot captures of the selected direction in the visual grounding directory.
This skill sits between /arn-spark-scaffold and /arn-spark-style-explore in the greenfield pipeline. It produces a visual-direction.md that style-explore uses as primary input for detailed design token specification. The user sees what the product could look like before committing to a full design system.
The iterative process works in rounds:
- Round 1: N proposals with distinct visual directions (default 3)
- Round 2+: N expansions of the selected proposal with user-guided refinements
- Final: The selected direction is captured and documented
Each proposal runs on the scaffold's actual dev server using the project's real CSS framework and component library.
Prerequisites
The following artifacts inform the sketch generation. Check in order:
Determine the output directories:
- Read the project's
CLAUDE.mdand check for a## Arnesssection - If found, extract the configured Vision directory path and Visual grounding directory path
- If no
## Arnesssection exists or Arness Spark fields are missing, inform the user: "Arness Spark is not configured for this project yet. Run/arn-brainstormingto get started — it will set everything up automatically." Do not proceed without it. - Create directories if they do not exist
All references to "Vision directory" and "visual grounding directory" in this skill refer to the configured directories determined above.
Scaffold (required):
- Check the Vision directory for
scaffold-summary.md - If no
## Arnesssection found, check.arness/vision/scaffold-summary.mdat the project root - Also check for
package.jsonat the project root
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 377 lines · 110 tokens per session scan A ca2039bd8329
arn-spark-visual-sketch is a skill published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 5,141 once invoked, about $0.0004 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 skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
antigravity-design-expert
Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS.
scroll-craft
Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
web-typography
Select, pair, and implement typefaces for web projects. Use when the user mentions "font pairing", "which typeface", "line height", "responsive typography", "web font loading", "type hierarchy", "variable fonts", "FOUT/FOIT", "typographic scale", or "the text is hard to read". Also trigger when choosing between system…