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 imaginpro/imaginepro-claude-pluginnpx agentmods add plugins/imaginpro/imaginepro-claude-plugin/imaginepro-claude-plugingit clone --depth 1 https://github.com/imaginpro/imaginepro-claude-pluginWrote 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/imaginpro/imaginepro-claude-plugin/imaginepro-claude-plugin)<a href="https://agentmods.dev/plugins/imaginpro/imaginepro-claude-plugin/imaginepro-claude-plugin"><img src="https://agentmods.dev/badge/plugins/imaginpro/imaginepro-claude-plugin/imaginepro-claude-plugin.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
imaginepro 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "imaginepro",
"displayName": "ImaginePro - AI Image & Video Generator",
"description": "Professional AI image and video generation for developers. Generate web assets, UI components, marketing materials, and videos without leaving Claude Code. Features specialized agents for web development, UI/UX design, marketing, and video production workflows.",
"version": "1.0.0",
"author": {
"name": "ImaginePro",
"email": "[email protected]",
"url": "https://imaginepro.ai"
},
"repository": {
"type": "git",
"url": "https://github.com/imaginpro/imaginepro-claude-plugin"
},
"bugs": {
"url": "https://github.com/imaginpro/imaginepro-claude-plugin/issues"
},
"homepage": "https://github.com/imaginpro/imaginepro-claude-plugin#readme",
"license": "MIT",
"keywords": [
"image-generation",
"video-generation",
"ai",
"creative",
"imaginepro",
"web-assets",
"ui-design",
"marketing",
"productivity"
],
"categories": [
"productivity",
"creative",
"ai-tools",
"development"
],
"engines": {
"claudeCode": ">=2.0.0",
"node": ">=18.0.0"
},
"requirements": {
"environment": {
"IMAGINEPRO_API_KEY": {
"description": "Your ImaginePro API key from https://imaginepro.ai - Sign up for free and get your API key from account settings",
"required": true,
"type": "string"
}
},
"dependencies": {
"npm": {
"imaginepro-mcp-server": "^1.1.0"
}
}
},
"features": {
"agents": [
{
"name": "web-asset-producer",
"description": "Generate production-ready assets for web development (hero images, backgrounds, etc.)"
},
{
"name": "ui-asset-generator",
"description": "Create design system assets, icons, and UI illustrations"
},
{
"name": "marketing-creative",
"description": "Generate marketing materials, ads, and social media content"
What it installs
The manifest is a name and a version. 5 commands, 4 agents, 1 MCP server travel with it, and installing the plugin installs all of them — 0 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command imagine-guide A 0 tokens
- Command video-flow A 0 tokens
- Command vary-it A 0 tokens
- Command upscale-it A 0 tokens
- Command imagine-pro A 0 tokens
- Agent marketing-creative A 0 tokens
- Agent video-director A 0 tokens
- Agent ui-asset-generator A 0 tokens
- Agent web-asset-producer A 0 tokens
- MCP server imaginepro A not measured
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.
- 5d ago First seen · 117 lines scan A 6107e8fc2c64
imaginepro is a plugin published in the GitHub repository imaginpro/imaginepro-claude-plugin (5 stars, last pushed 10mo 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 2026-08-31.
Other plugins, from other repositories
claude-image-generation
Generate and edit images using Google Gemini, OpenAI GPT Image, xAI Grok Image, and OpenRouter APIs.
codex-image
Generate and edit images from Claude Code by dispatching to Codex CLI's built-in imagegen skill.
poppify
Photo-led short-form vertical reels for Instagram / TikTok / YouTube Shorts / Facebook — the creative slot in an agentic marketing stack for SMBs (5–19 employees) and solo service providers. Upload 1–10 photos, get a captioned vertical reel (typically 10–45s, text-length-driven pacing) with motion, library-matched…
imagegen
Generate, edit, and batch-create images from inside Claude Code by delegating to OpenAI's Codex CLI (built-in gpt-image, billed against the user's ChatGPT subscription — no API key, no per-image $ charges).
rasterize
Generate raster images (PNG, JPEG, WebP) from natural language prompts using Python rendering engines (Pillow, Cairo, Matplotlib, Plotly, Playwright).
han-communication
Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…