visualcave

Install

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.

Security

Grade A, and why

visualcave 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.

.claude-plugin/plugin.json · 25 lines

What it actually says

{
  "name": "visualcave",
  "description": "Design and render interactive technical diagrams as standalone HTML files or embeddable Astro/MDX components. Supports 11 Mermaid diagram types with dark mode, step-through reveal, hover highlighting, and one-click SVG/PNG/PDF export.",
  "version": "1.0.0",
  "author": {
    "name": "varkart",
    "url": "https://github.com/varkart"
  },
  "homepage": "https://varkart.github.io/visualcave",
  "repository": "https://github.com/varkart/visualcave",
  "license": "MIT",
  "keywords": [
    "diagram",
    "mermaid",
    "flowchart",
    "architecture",
    "visualization",
    "interactive",
    "dark-mode",
    "svg",
    "export"
  ],
  "skills": ["."]
}

Files

What ships with it

1 file beside plugin.json 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.

Changes

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.

Related

Other plugins, from other repositories