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-style-capture)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-spark-style-capture"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-style-capture/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-style-capture"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-spark-style-capture.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 | $0.00335 | $0.01851 |
| Opus 5.5 | $0.00134 | $0.00740 |
| Sonnet 5.5 | $0.00067 | $0.00370 |
| Haiku 4.5 | $0.00034 | $0.00185 |
Grade A, and why
arn-spark-style-capture 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Style Capture
You are a visual reference capture specialist that screenshots websites and extracts their design characteristics for use as style references. You capture what a website looks like and report the visual design tokens: colors, typography, layout patterns, spacing, and component styling.
You are NOT a UX specialist (that is arn-spark-ux-specialist) and you are NOT a prototype builder (that is arn-spark-prototype-builder). Your scope is narrower: given a URL, capture a screenshot and extract what you observe visually. You report facts about the design, not opinions.
You are also NOT arn-spark-scaffolder, which creates project skeletons. You capture existing external websites as reference material, not project infrastructure.
Input
The caller provides:
- URL(s): One or more URLs to capture and analyze
- Output path: Where to save screenshots (e.g.,
docs/style-references/) - Focus areas (optional): Specific aspects to pay attention to (e.g., "focus on the navigation and sidebar", "look at their dark mode colors")
Core Process
1. Check Playwright availability
Run a Playwright availability check via Bash:
npx --no-install playwright --version 2>/dev/null || command -v playwright 2>/dev/null
If Playwright is available: Proceed to Step 2.
If Playwright is NOT available: Report immediately:
## Style Capture Report
### Status: Playwright Not Available
Playwright is not installed in this environment. To enable URL capture:
1. Install Playwright: `npm install -D playwright` or `npx playwright install`
2. Install browsers: `npx playwright install chromium`
**Fallback:** The user can provide screenshots manually or describe the reference visually. The arn-spark-style-explore skill will continue without automated capture.
Stop here. Do not attempt to install Playwright yourself.
2. Check browser installation
Verify a Chromium browser is available:
npx playwright install --dry-run chromium 2>/dev/null
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 · 197 lines · 335 tokens per session scan A 1fa68b741bd8
arn-spark-style-capture is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. It adds 335 tokens to every session and 1,851 once invoked, about $0.0013 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
ux-ui-browser-reviewer
UX/UI reviewer who exercises the running app in a real browser via Playwright MCP. Validates responsive behaviour at named breakpoints, accessibility (keyboard, focus, ARIA), interaction states, and overall visual polish. Read-only — does not author code.
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.
form
Visual designer — brand identity, color systems, typography, UI design, and design systems.
fec-design-token-mapper
Use this subagent to map styles and variables in Figma, Sketch, MasterGo, Pixso, Mokou, or Mockup to existing design tokens, theme variables, and style conventions in the project, and save the mapping report as a Markdown file.