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.
/plugin marketplace add Cavalry-Collective/visual-stacknpx agentmods add plugins/cavalry-collective/visual-stack/vstackgit clone --depth 1 https://github.com/Cavalry-Collective/visual-stackGrade 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 yesterday.
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": "6.4.0",
"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 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.
- yesterday First seen · 31 lines scan A d29347c3fa5b
vstack is a plugin published in the GitHub repository Cavalry-Collective/visual-stack (11 stars, last pushed 12d 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
markifact
Run Google Ads, Meta Ads, GA4, Shopify, and 20+ more platforms from Claude. 1000+ operations with human-in-the-loop on every write.
alibabacloud-agent-toolkit
Plugin marketplace listing 3 plugins: alibabacloud-core, alibabacloud-spec-ops, alibabacloud-ecs-ops.
alibabacloud-spec-ops
Alibaba Cloud AI Ops Plugin - Infrastructure operations workflow with intelligent planning, validation, and execution powered by MCP tooling.
serpapi-plugins
Official SerpApi plugins for Claude Code.
neatcontext
Save Claude Code work as reusable, domain-aware context.
talk-to-anyone
Turn any public figure into your personal coach, living or historical. /coach researches the person across the web, pulls real transcripts when they have video anywhere on YouTube, builds a persona, and talks to you as them until you switch or end.