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-deploy-detection-tracking-2dgit 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-deploy-detection-tracking-2d)<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-detection-tracking-2d"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-detection-tracking-2d/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-detection-tracking-2d"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-detection-tracking-2d.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 | $0.00108 | $0.04848 |
| Opus 5.5 | $0.00043 | $0.01939 |
| Sonnet 5.5 | $0.00022 | $0.00970 |
| Haiku 4.5 | $0.00011 | $0.00485 |
Grade A, and why
vss-deploy-detection-tracking-2d 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl`, `jq`, and Docker available on the caller. How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Deploy, debug, and operate the RTVI-CV detection / tracking 2D microservice and drive its REST API.
When to Use
- Deploy, tear down, or debug the RTVI-CV 2D microservice ("deploy rtvi-cv", "start warehouse 2d", "stop the perception container", "rtvi-cv won't start")
- Manage streams or call the RTVI-CV REST API on an already-running instance (add/remove/list streams, health checks, metrics, embeddings)
Not for VLM, embedding, or analytics — use the matching vss-* skill.
Prerequisites
- Active VSS deployment reachable on
$HOST_IP(seevss-build-vision-aiandreferences/). - NGC credentials in
$NGC_CLI_API_KEYand$NVIDIA_API_KEYfor any image pulls. curl,jq, and Docker available on the caller.
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/ and helper scripts live in scripts/ — call them via run_script when the skill points to a script by name.
Examples
Worked end-to-end examples are kept under evals/ (each *.json manifest contains a runnable scenario) and inline in the per-workflow curl blocks below. Run a Tier-3 evaluation with nv-base validate <this-skill-dir> --agent-eval to replay them.
Limitations
- Requires the matching VSS profile / microservice to be deployed and reachable from the caller.
- NGC-hosted models and NIMs may be subject to rate-limits, GPU memory requirements, and license restrictions.
- Concurrency, GPU memory, and storage limits depend on the host hardware and the profile's compose file.
Troubleshooting
- Error: REST call returns connection refused. Cause: target microservice not running. Solution: probe
/docsor/health; redeploy viavss-build-vision-aior the matchingvss-deploy-*skill. - Error: HTTP 401/403 from NGC pulls. Cause: missing/expired
NGC_CLI_API_KEY. Solution:docker login nvcr.ioand re-export the key before retrying. - Error: container OOM or model fails to load. Cause: insufficient GPU memory for the selected profile. Solution: switch to a smaller variant or free GPUs via
docker compose down.
What ships with it
50 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.
- assets/deploy-defaults.yml 12 KB
- BENCHMARK.md 3.5 KB
- evals/deploy-evals.json 3.5 KB
- evals/evals.json 2.0 KB
- evals/usage-evals.json 13 KB
- references/api-reference.md 8.4 KB
- references/apply-config.md 60 KB
- references/container-reuse.md 11 KB
- references/deploy-vss-detection-tracking-2d.md 62 KB
- references/environment.md 6.4 KB
- references/integrate-vss-detection-tracking-2d.md 10 KB
- references/next-steps.md 31 KB
- references/ngc-setup.md 6.9 KB
- references/pipeline-config.md 13 KB
- references/platforms.md 7.1 KB
- references/resource-plan.md 19 KB
- references/start-app.md 27 KB
- references/task-list.md 13 KB
- references/teardown-flow.md 5.9 KB
- references/troubleshooting.md 8.0 KB
- references/upgrade-rollback.md 2.3 KB
- references/usage-vss-detection-tracking-2d.md 15 KB
- references/usecases.md 14 KB
- references/ux-conventions.md 15 KB
- references/workflow-reference.md 10 KB
- scripts/add_streams.sh 9.1 KB runs code
- scripts/apply_config.sh 23 KB runs code
- scripts/apply_in_container.sh 2.9 KB runs code
- scripts/cache_nvinfer_engine.sh 4.3 KB runs code
- scripts/calibration_manager.py 9.8 KB runs code
- scripts/check_container_gpu.sh 3.1 KB runs code
- scripts/clean_engine_cache.sh 2.9 KB runs code
- scripts/collect_metrics.sh 14 KB runs code
- scripts/common.sh 15 KB runs code
- scripts/discover_streams.sh 8.2 KB runs code
- scripts/fetch_resources.sh 11 KB runs code
- scripts/load_defaults.sh 5.1 KB runs code
- scripts/prelaunch_nvinfer_engine.sh 8.7 KB runs code
- scripts/render_box.sh 2.4 KB runs code
- scripts/run_app_and_wait.sh 15 KB runs code
- scripts/setup_gdino.sh 6.6 KB runs code
- scripts/setup_sparse4d.sh 9.2 KB runs code
- scripts/setup_tracker_reid.sh 11 KB runs code
- scripts/start_app_in_container.sh 6.0 KB runs code
- scripts/synthesize_docker_run.sh 7.2 KB runs code
- scripts/update_batch_size.sh 6.5 KB runs code
- scripts/update_output_sink.sh 17 KB runs code
- scripts/update_stream_sources.sh 6.8 KB runs code
- scripts/write_deployment_log.sh 11 KB runs code
- skill-card.md 4.2 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.
- 28d ago Changed 3d5d6d0d0f9b
- 29d ago Changed · +7 lines 6577362d7a0f
- 1mo ago Changed dce7b639d8a8
- 1mo ago First seen · 278 lines · 108 tokens per session scan A f5514e079c7b
vss-deploy-detection-tracking-2d 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 108 tokens to every session and 4,848 once invoked, about $0.0004 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 2026-08-30.
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…
google-cloud-solution-n-tier-serverless-web-app
Assists in designing and implementing secure n-tier serverless web applications and microservices on Google Cloud. Use when users need architecture designs, security checklists, Terraform code, or deployment guidance for multi-tier serverless apps, regional data residency / European sovereignty compliance, zero-trust…
api-gateway-mcp-server
Configures Google Cloud API Gateway to act as a remote Model Context Protocol (MCP) server (Public Preview) that exposes REST APIs as agent tools over HTTP (POST /mcp). Use when migrating OpenAPI 2.0 specs to OpenAPI 3.x for MCP, annotating specs with x-google-api-management.mcp and x-google-mcp-tool, securing…
google-cloud-global-frontend-configuration
Guides agents through a 6-step discovery process to design and deploy Google Cloud global external Application Load Balancers with Cloud CDN, Cloud Armor, and Service Extensions, mapping workload requirements to best-practice configurations. Use when: Designing, configuring, or deploying a Google Cloud global external…
sandbox-stable
Build or maintain Cloudflare Sandbox apps on the stable @cloudflare/sandbox package. Use sandbox-next for preview apps and sandbox-migrate-to-next for stable-to-preview migrations.
sandbox-next
Build or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.