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/plugins/appsvortex/arness/arn-spark)<a href="https://agentmods.dev/plugins/appsvortex/arness/arn-spark"><img src="https://agentmods.dev/badge/plugins/appsvortex/arness/arn-spark/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/plugins/appsvortex/arness/arn-spark"><img src="https://agentmods.dev/badge/plugins/appsvortex/arness/arn-spark.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
arn-spark 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.
What it actually says
{
"name": "arn-spark",
"repository": "https://github.com/AppsVortex/arness",
"author": {
"name": "Fryderyk Benigni",
"url": "https://github.com/fredcallagan"
},
"description": "Greenfield exploration for Claude Code — discovery, personas, use cases, architecture vision, naming, scaffolding, visual sketches, prototype validation. 19 skills, 13 agents."
}
What it installs
The manifest is a name and a version. 28 skills, 20 agents travel with it, and installing the plugin installs all of them — 10,631 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill arn-spark-feature-extract A 131 tokens
- Skill arn-brainstorming A 206 tokens
- Skill arn-spark-clickable-prototype A 117 tokens
- Skill arn-spark-use-cases A 120 tokens
- Skill arn-spark-visual-strategy A 124 tokens
- Skill arn-spark-init A 177 tokens
- Skill arn-spark-static-prototype A 109 tokens
- Skill arn-spark-visual-sketch A 110 tokens
- Skill arn-spark-dev-setup A 152 tokens
- Skill arn-spark-naming A 122 tokens
- Skill arn-spark-arch-vision A 125 tokens
- Skill arn-spark-prototype-lock A 97 tokens
- Skill arn-spark-help A 123 tokens
- Skill arn-spark-report A 131 tokens
- Skill arn-spark-concept-review A 122 tokens
- Skill arn-spark-discover A 127 tokens
- Skill arn-spark-style-explore A 96 tokens
- Skill arn-spark-stress-interview A 109 tokens
- Skill arn-spark-visual-readiness A 80 tokens
- Skill arn-spark-scaffold A 82 tokens
- Skill arn-spark-spike A 92 tokens
- Skill arn-spark-stress-prfaq A 144 tokens
- Skill arn-spark-stress-competitive A 101 tokens
- Skill arn-spark-stress-premortem A 118 tokens
- Skill arn-spark-clickable-prototype-teams B 174 tokens
- Skill arn-spark-ensure-config A 127 tokens
- Skill arn-spark-static-prototype-teams B 151 tokens
- Skill arn-spark-use-cases-teams B 122 tokens
- Agent arn-spark-prototype-builder A 405 tokens
- Agent arn-spark-brand-strategist A 432 tokens
- Agent arn-spark-persona-architect A 476 tokens
- Agent arn-spark-tech-evaluator A 259 tokens
- Agent arn-spark-use-case-writer A 434 tokens
- Agent arn-spark-visual-sketcher A 377 tokens
- Agent arn-spark-forensic-investigator A 329 tokens
- Agent arn-spark-market-researcher A 421 tokens
- Agent arn-spark-marketing-pm A 335 tokens
- Agent arn-spark-persona-impersonator A 444 tokens
- Agent arn-spark-product-strategist A 274 tokens
- Agent arn-spark-scaffolder A 271 tokens
- Agent arn-spark-ui-interactor A 325 tokens
- Agent arn-spark-ux-judge A 395 tokens
- Agent arn-spark-dev-env-builder A 297 tokens
- Agent arn-spark-spike-runner A 282 tokens
- Agent arn-spark-style-capture A 335 tokens
- Agent arn-spark-ux-specialist A 292 tokens
- Agent arn-spark-doctor A 212 tokens
- Agent arn-spark-visual-test-engineer A 547 tokens
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 · 10 lines scan A ab7069a0728f
arn-spark is a plugin published in the GitHub repository AppsVortex/arness (33 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
frontend-design
Production-grade frontend design skill that avoids AI slop — specific rules for typography, color (OKLCH), layout, motion, interaction, and UX writing.
visual-gen
Generate blog cover images, architecture diagrams, and process infographics as PNG files using HTML+CSS rendered via Chrome headless.
cyxj-image-studio
An image-making add-on for creating posters, book covers, album covers, and video cover images in several visual styles and sizes.
design
Five-phase design thinking process for component design, writing to Figma canvas via MCP.
branding
Five-phase brand creation process with compliance auditing — discover, strategy, verbal, visual, guidelines.
site-forge
Build a distinctive, production-grade website (and optional Remotion promo video) for any business, product, or person, then deploy it free. Two modes: auto (fast, autonomous) and full (best quality).