NVIDIA AI Blueprint for Video Search and Summarization (VSS) is a reference architecture for applications that use AI to search, analyze, question, and summarize live or recorded video. It is intended for building video analytics agents with vision-language models, language models, retrieval-augmented generation, and NVIDIA NIM microservices. The catalogue entries provide coding-agent rules, skills, commands, agents, instructions, and settings associated with the project.
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 skills add NVIDIA-AI-Blueprints/video-search-and-summarization --skill vss-setup-behavior-analyticsgit clone --depth 1 https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarizationWrote 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/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-setup-behavior-analytics)<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-setup-behavior-analytics"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-setup-behavior-analytics/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/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-setup-behavior-analytics"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-setup-behavior-analytics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00042 | $0.02538 |
| Opus 5.5 | $0.00017 | $0.01015 |
| Sonnet 5.5 | $0.00008 | $0.00508 |
| Haiku 4.5 | $0.00004 | $0.00254 |
Grade A, and why
vss-setup-behavior-analytics scanned grade A with 1 finding 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 26d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
no REST endpoint, so there is nothing to `curl` and no `/health` to probe. Verify it through container logs and How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Deploy the behavior-analytics service standalone with the user's chosen entrypoint, config, and calibration.
Instructions
Follow the routing tables and step-by-step workflows below. Each section that ends in workflow, quick start, or flow is intended to be executed top-to-bottom. Detailed reference material lives in references/.
Examples
Worked end-to-end examples are kept under evals/ (each *.json manifest
contains a runnable scenario). Run a Tier-3 evaluation to replay them:
nv-base validate skills/deployment/vss-setup-behavior-analytics --agent-eval
A minimal standalone bring-up looks like:
cd $REPO/deploy/docker
export VSS_APPS_DIR=$(pwd)
docker compose -f services/analytics/behavior-analytics/compose.yml up -d vss-behavior-analytics-base
Follow references/deploy-behavior-analytics-service.md for the full
workflow (entrypoint pick, config source, dynamic updates).
Limitations
- No HTTP API. This is a broker stream processor — it reads and writes Kafka / Redis Streams / MQTT and serves
no REST endpoint, so there is nothing to
curland no/healthto probe. Verify it through container logs and the output topics. - CPU-only. It loads no models and reserves no GPU (
gpu_count: 0in this skill's own evals), so GPU memory and NIM rate-limits are not constraints here. - At least one processor must be enabled, and forgetting is quiet. With every
numWorkersFor*at0the runner logsFATAL - Error in app: No processors registered, closes its listeners and returns — the process exits 0, so to anything watching exit codes it looks like a clean shutdown. Only the log distinguishes it. - A destination the config omits is a disabled output, not an error. The sink logs
No destination configured for '<key>'; output for it is disabledonce per key and drops the rest, so a missing topic looks like an empty stream rather than a failure. - One behavior producer per deployment. Two instances producing behaviors for the same sensors write every behavior twice, from processes with independent state. Nothing detects this.
What ships with it
14 files beside SKILL.md 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.
- BENCHMARK.md 3.8 KB
- evals/deploy_search_and_alerts.json 1.8 KB
- evals/evals.json 1002 B
- evals/fov_count_alert.json 2.6 KB
- evals/proximity_alert.json 2.3 KB
- evals/roi_bbox_overlap.json 2.6 KB
- evals/standalone_deploy.json 1.8 KB
- references/configuration.md 5.8 KB
- references/deploy-behavior-analytics-service.md 22 KB
- references/dynamic-calibration.md 11 KB
- references/dynamic-config.md 13 KB
- references/integrate-behavior-analytics-service.md 19 KB
- references/ngc-api-key-registry-login.md 2.0 KB
- skill-card.md 4.1 KB
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.
- 26d ago Changed 3e3091b35a00
- 1mo ago Changed 6676ea6aecda
- 1mo ago First seen · 145 lines · 42 tokens per session scan A 392ea512734b
vss-setup-behavior-analytics is a skill published in the GitHub repository NVIDIA-AI-Blueprints/video-search-and-summarization (1,947 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 2,538 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
build-mcpb
This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem…
apigee-agent-gateway-governance
Stands up an Apigee API proxy that a Google Cloud Agent Gateway calls as an ext-proc (Service Extension) callout on an agent's LLM traffic, to meter token usage per model, extract caller identity, and apply Model Armor prompt screening or a semantic cache. Use when wiring Apigee in as an AI gateway behind an Agent…
gke-app-onboarding
Manages GKE application onboarding, covering containerization, deployment manifests, and migration. Use when onboarding or deploying an application to GKE for the first time, or containerizing an app for GKE. Don't use for general GKE cluster administration or upgrades (use gke-basics or gke-upgrades instead).
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
beautiful-article
A tool for turning source material—such as a web page, PDF, DOCX, Markdown file, text, screenshot, or pasted content—into a single offline HTML article.
motion-showreel
A code-based workflow for making short videos built from animated graphics, text, logos, or interface elements. It produces MP4 video and editable source code rather than filming or editing existing footage.