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.
npx agentmods add plugins/nvidia/skills/marketplace/plugin marketplace add NVIDIA/skillsgit clone --depth 1 https://github.com/NVIDIA/skillsGrade A, and why
nvidia-official 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": "nvidia-official",
"owner": {
"name": "NVIDIA",
"url": "https://github.com/NVIDIA/skills"
},
"metadata": {
"description": "NVIDIA plugin marketplace — install the curated NVIDIA plugins and skills from this catalog repo.",
"version": "1.0.0"
},
"plugins": [
{
"name": "nvidia-skills",
"source": "./plugins/nvidia-skills",
"description": "Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered workflows."
}
]
}
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 · 19 lines scan A 3b00c749319b
nvidia-official is a plugin published in the GitHub repository NVIDIA/skills (3,144 stars, last pushed 2d ago), licensed Apache-2.0. 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
memi
Claude Code plugins for memi design-system memory, MCP tooling, shadcn/ui workflows, and UI quality gates.
rudder
Plugin marketplace listing 1 plugin: rudder.
memi
Memi is the design layer for agentic AI.
rudder
Maintain a device-local spec from coding-session intent, then generate focused unit tests with your existing coding agent.
docuseal
Add DocuSeal document signing to your app with embed components, REST API, SDKs, and webhooks.
docuseal-agent-skills
Plugin marketplace listing 1 plugin: docuseal.