What is deepstream-sop?

A reference project for checking whether camera video follows standard operating procedures, meaning defined work instructions. It combines video processing, AI-based reasoning, camera input, and streaming or event outputs.

Use it as a reference for GPU-accelerated video analysis, Basler GigE camera integration, procedure checks with Cosmos Reason models, and sending results through Kafka, server-sent events, or RTSP video streams.

It provides a documented starting point for building an automated system that detects events and checks them against workplace procedures.

deepstream-sop — Plugin by NVIDIA

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.

agentmods

npx agentmods add plugins/nvidia/skills/deepstream-sop

Claude Code

/plugin marketplace add NVIDIA/skills

Clone the repo

git clone --depth 1 https://github.com/NVIDIA/skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

deepstream-sop 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.

skills/deepstream-sop/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "deepstream-sop",
  "description": "DeepStream SOP compliance monitoring — 18-section reference covering GPU-accelerated event boundary detection (GEBD, e.g. DDM) + VLM-based SOP checking with Cosmos Reason 1 or 2, Triton CAPI, Basler GigE camera (Pylon SDK + emulation), Kafka/SSE output, and RTSP streaming output.",
  "author": {
    "name": "Wind Yuan",
    "email": "[email protected]"
  },
  "license": "CC-BY-4.0 AND Apache-2.0",
  "skills": "./"
}

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.

yesterday First seen · 11 lines scan A 83ca2cce4d6b

Subscribe to this mod's changes

deepstream-sop 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.

agent-skills agentic-ai ai-agents claude-code codex coding-agents

deepstream-sop

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

memi

rudder

memi

rudder

docuseal

docuseal-agent-skills