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/Cavalry-Collective/visual-stackWrote 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/cavalry-collective/visual-stack/vstack)<a href="https://agentmods.dev/plugins/cavalry-collective/visual-stack/vstack"><img src="https://agentmods.dev/badge/plugins/cavalry-collective/visual-stack/vstack/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/cavalry-collective/visual-stack/vstack"><img src="https://agentmods.dev/badge/plugins/cavalry-collective/visual-stack/vstack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
vstack 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 7d ago.
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": "vstack",
"displayName": "Visual Stack",
"version": "6.8.0",
"description": "Stop prompting. Start pointing. Visual Stack adds a Figma-like feedback layer to Claude Code. Create a new screen from a prompt, screenshot, reference site, or design system, or open an app you already have running. Click any element and leave feedback exactly where the problem is hiding, and Claude publishes the next revision into the same workspace. Compare revisions on a timeline, preview desktop, tablet, and mobile layouts, and keep every comment attached to the element, route, and version it refers to. Wireframes are self-contained HTML and review state stays in your project.",
"author": {
"name": "Cavalry Collective",
"email": "[email protected]",
"url": "https://cavalry.sg"
},
"homepage": "https://www.cavalry.sg/visual-stack",
"repository": "https://github.com/Cavalry-Collective/visual-stack",
"license": "MIT",
"keywords": [
"wireframe",
"wireframing",
"mockup",
"prototype",
"ui",
"ui-review",
"ux",
"design",
"design-review",
"design-feedback",
"frontend",
"annotate",
"visual-feedback",
"screenshot"
]
}
What it installs
The manifest is a name and a version. 7 skills, 1 hook travel with it, and installing the plugin installs all of them — 604 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 7d ago Changed ff7b94e67927
- 1mo ago First seen · 31 lines scan A d29347c3fa5b
vstack is a plugin published in the GitHub repository Cavalry-Collective/visual-stack (11 stars, last pushed 3d ago), 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 2026-08-30.
Other plugins, from other repositories
product
Product strategy, UX and usability audit, design systems, interface craft, brand expression, and visual direction.
security
Threat modeling, security architecture review, incident response, vulnerability management, and access and identity. Reviewer-class: blocking findings are not overrulable by the department under review.
data-analytics
Data governance, warehouse and semantic modeling, business intelligence, and AI/ML governance.
executive
Direction, capital and attention allocation, cross-functional arbitration, strategy validation, and the method for structuring the organization itself.
revenue
Outbound, sales enablement, revenue operations, pricing and packaging, activation, retention, and referrals.
markifact
Performance marketing automation across Google Ads, Meta Ads, GA4, Shopify and more via Markifact's remote MCP server.