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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarizationnpx agentmods add skills/nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-warehouse-helmWrote 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-deploy-warehouse-helm)<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-warehouse-helm"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-warehouse-helm/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-deploy-warehouse-helm"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-warehouse-helm.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 | $0.00083 | $0.04224 |
| Opus 5.5 | $0.00033 | $0.01690 |
| Sonnet 5.5 | $0.00017 | $0.00845 |
| Haiku 4.5 | $0.00008 | $0.00422 |
Grade A, and why
vss-deploy-warehouse-helm 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 28d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VSS Warehouse — Helm Deploy
When to Use
- Deploy, upgrade, or size the VSS warehouse blueprint (2D / 3D / MV3DT) on Kubernetes via Helm
- Compute a GPU-aware
NUM_STREAMScap for a warehouse Helm install so it matches what the perception pipeline can sustain
Do not use this skill for:
- Docker Compose warehouse deployment — use
vss-build-vision-ai'sreferences/warehouse.md; it owns theHARDWARE_PROFILE→ GPU mapping table and theblueprint_config.ymlstream-cap semantics this skill reuses. - Non-warehouse Helm profiles (
base,search,lvs,alerts) — those don't have abp-configuratorGPU-aware stream cap; deploy them per their own chart READMEs. - Runtime operations (adding cameras, querying behavior analytics) — use
vss-manage-alerts/vss-query-analyticsagainst the running deployment.
Why this exists
Docker Compose's warehouse deploy caps NUM_STREAMS per GPU automatically: the configurator reads
deploy/docker/industry-profiles/warehouse-operations/blueprint-configurator/blueprint_config.yml's
max_streams_supported table for the detected HARDWARE_PROFILE and mode, and clamps
final_stream_count = min(NUM_STREAMS, max_streams_supported).
The Helm charts (deploy/helm/industry-profiles/warehouse-operations/warehouse-{2d,3d,mv3dt}-app)
do not do this — their bp-configurator.env ships a fixed NUM_STREAMS and never sets
HARDWARE_PROFILE at all (ENABLE_PROFILE_CONFIGURATOR=false). A user who asks for more streams
than the GPU can sustain gets no protection. This skill closes that gap by computing the same cap
Compose would apply and writing it into a Helm values-override file before install.
Available Scripts
| Script | Purpose | Arguments |
|---|---|---|
../../../deploy/helm/industry-profiles/warehouse-operations/scripts/compute_stream_cap.py |
Detect GPU (or take an explicit HARDWARE_PROFILE), read max_streams_supported from blueprint_config.yml, cap the requested stream count, and write a bp-configurator.env-patched values-override YAML. Pass any values file(s) your install already uses via -f so custom bp-configurator.env entries in them aren't dropped. |
--mode {2d,3d,mv3dt} --num-streams N [--hardware-profile P] [--gpu-index I] [-f VALUES]... [-o FILE] |
What ships with it
2 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.
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.
- 28d ago Changed 6af968e953b6
- 29d ago Changed · +5 lines 2e4cbf67e03d
- 1mo ago Changed · +1 tokens per session 8622ba9cf2cf
- 1mo ago First seen · 229 lines · 82 tokens per session scan A 5047c798cad5
vss-deploy-warehouse-helm is a skill published in the GitHub repository NVIDIA-AI-Blueprints/video-search-and-summarization (1,953 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 4,224 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
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…
application-integration-authoring
Builds, versions, publishes, tests, and executes Google Cloud Application Integration workflows through the REST API and Python discovery client, and promotes versions across environments. Use when listing integrations, downloading or uploading integration versions as JSON, configuring API triggers or config…
gke-alert-configuration
Configures alerting policies in Terraform for Google Kubernetes Engine (GKE) clusters, workloads, and services using PromQL and Google Cloud Managed Service for Prometheus. Use when writing, analyzing, validating, or deploying Terraform alerting policies to monitor GKE service latency, traffic, error rates using…
gke-ai-troubleshooting-tpu-partition-overlap
Diagnose and resolve GKE TPU slice creation failures (SliceCreationFailed) caused by partition overlap conflicts where requested TPU partitions or their nodes are already used by another slice or JobSet. Use when diagnosing GKE TPU slice creation failures with SliceCreationFailed partition or node conflicts. Don't use…
application-integration-basics
Explains Google Cloud Application Integration concepts, region provisioning, IAM roles, run-as service accounts, interface choices (REST, Python discovery client, Terraform, ADK), and platform limits. Use when setting up Application Integration in a Google Cloud project, enabling required APIs, provisioning a region…
cloud-run-basics
Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run event-triggered or scheduled tasks (jobs), or handle always-on pull-based background processing (worker pools).