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/danielrosehill/Claude-AI-Video-Producer-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/danielrosehill/claude-ai-video-producer-plugin/claude-ai-video-producer-plugin)<a href="https://agentmods.dev/plugins/danielrosehill/claude-ai-video-producer-plugin/claude-ai-video-producer-plugin"><img src="https://agentmods.dev/badge/plugins/danielrosehill/claude-ai-video-producer-plugin/claude-ai-video-producer-plugin/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/danielrosehill/claude-ai-video-producer-plugin/claude-ai-video-producer-plugin"><img src="https://agentmods.dev/badge/plugins/danielrosehill/claude-ai-video-producer-plugin/claude-ai-video-producer-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ai-video-producer 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 12d 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": "ai-video-producer",
"version": "1.3.0",
"description": "Drive a single AI-generated video project end-to-end: creative brief, model selection, character sheets, script (script-writer agent), storyboard, generation pipelines (text-to-image, image-to-video, voice, lip-sync), GPU-aware concatenation/normalisation/aspect conversion, ComfyUI import-export, budget estimation, and final export. State-aware lifecycle plugin designed to operate inside a per-project workspace. Ships with fal.ai, Replicate, and MiniMax MCP servers plus fal-js and WaveSpeed Python SDK runners, all wired to a persistent ~/.config/ai-video-producer/.env.",
"author": {
"name": "Daniel Rosehill",
"url": "https://github.com/danielrosehill"
},
"repository": "https://github.com/danielrosehill/AI-Video-Producer",
"license": "MIT",
"keywords": ["video", "generative-ai", "fal", "replicate", "wavespeed", "minimax", "hailuo", "elevenlabs", "lifecycle", "pipeline", "lip-sync", "text-to-video", "image-to-video", "comfyui", "ffmpeg", "nvenc"]
}
What it installs
The manifest is a name and a version. 11 skills, 11 commands, 7 agents, 3 MCP servers travel with it, and installing the plugin installs all of them — 2,515 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill recommend-model A 128 tokens
- Skill budget-estimator A 93 tokens
- Skill model-researcher A 115 tokens
- Skill video-workspace-conventions A 49 tokens
- Skill comfyui-export A 112 tokens
- Skill comfyui-import A 118 tokens
- Skill script-to-tts A 123 tokens
- Skill text-to-image-to-video A 61 tokens
- Skill upscale-and-interpolate A 34 tokens
- Skill voice-to-lip-sync A 43 tokens
- Skill text-to-video-direct A 41 tokens
- Command install-video-workspace A 22 tokens
- Command onboard A 20 tokens
- Command define-character A 16 tokens
- Command run-pipeline A 26 tokens
- Command storyboard A 22 tokens
- Command assemble A 22 tokens
- Command draft-script A 14 tokens
- Command export-final A 19 tokens
- Command log-take A 27 tokens
- Command promote-take A 24 tokens
- Command setup-credentials D 58 tokens
- Agent aspect-converter A 248 tokens
- Agent concatenator A 222 tokens
- Agent script-writer A 238 tokens
- Agent pipeline-builder A 139 tokens
- Agent pipeline-repo-setup A 154 tokens
- Agent pipeline-scaffolder A 161 tokens
- Agent normalizer C 166 tokens
- MCP server minimax A not measured
- MCP server fal-ai A not measured
- MCP server replicate 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.
- 12d ago First seen · 13 lines scan A 131f02443097
ai-video-producer is a plugin published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo 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
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
knowledge-work-plugins marketplace
Plugin marketplace listing 104 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
container
Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS.