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-manage-alertsgit 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-manage-alerts)<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-manage-alerts"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-manage-alerts/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-manage-alerts"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-manage-alerts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.12993 |
| Opus 5.5 | $0.00022 | $0.05197 |
| Sonnet 5.5 | $0.00011 | $0.02599 |
| Haiku 4.5 | $0.00005 | $0.01299 |
Grade B, and why
vss-manage-alerts scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -sf -X POST "$AB/api/v1/verification/ondemand" -H 'Content-Type: application/json' -d '{ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` and `jq` on the agent host. Docker Compose mode detection may use How it starts
The opening of the file, as written. The whole thing — 501 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Operate the VSS alert pipeline (mode detection, Alert-Bridge subscriptions, verification verdicts, on-demand verification, always-on operation, Slack notifications, queries, camera onboarding, verifier-prompt customization).
Prerequisites
- The
vssCLI onPATH. The OpenClaw and Hermes harness images ship it; anywhere else, install it from the same checkout as this skill so the CLI and the skill match:uv tool install <checkout>/libs/vss/cli. - Active VSS alerts profile reachable either on Docker (
$HOST_IP:9080Alert Bridge) or through the public Ingress (VSS_PUBLIC_URLwith/alert-bridge). - Follow
../vss-build-vision-ai/references/deployment_resolution.mdfor the sharedVSS_PUBLIC_URLcontract. curlandjqon the agent host. Docker Compose mode detection may usedocker/generated.env; Kubernetes must not.
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
Runnable end-to-end scenarios live under evals/ (each *.json manifest); inline curl blocks appear in each workflow below. Replay with nv-base validate <this-skill-dir> --agent-eval.
Limitations
Requires the matching VSS profile/microservice deployed and reachable. NGC-hosted models/NIMs are subject to rate-limits, GPU-memory needs, and license terms; concurrency and storage limits depend on host hardware and the profile's compose file.
Troubleshooting
- Connection refused → microservice not running: probe
/docsor/health, redeploy viavss-build-vision-ai. - HTTP 401/403 on NGC pulls → missing/expired
NGC_CLI_API_KEY:docker login nvcr.ioand re-export the key. - OOM / model load failure → insufficient GPU memory: use a smaller variant or
docker compose downto free GPUs.
What ships with it
31 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.
- evals/alert_enhancement_handoff.json 9.3 KB
- evals/alerts_vlm_real_time.json 30 KB
- evals/always_on_operate.json 8.9 KB
- evals/cv_mode_gate.json 9.4 KB
- evals/evals.json 19 KB
- evals/ondemand_verification.json 10 KB
- evals/routing_e_gate_negative.json 11 KB
- evals/routing_vlm_c_vs_d.json 6.0 KB
- evals/slack_notify_ops.json 8.5 KB
- evals/subscriptions_create_phrasings.json 13 KB
- evals/subscriptions_edge_cases.json 6.7 KB
- evals/subscriptions_lifecycle.json 9.3 KB
- evals/verification_flow.json 16 KB
- references/alert-notify.md 21 KB
- references/alert-subscriptions.md 26 KB
- references/always-on.md 8.3 KB
- references/cv-verifier-prompts.md 285 B
- references/deploy-alerts.md 12 KB
- references/integrate-alerts.md 28 KB
- references/on-demand-verification.md 4.7 KB
- references/query-incidents.md 26 KB
- references/response-parser.md 23 KB
- references/verification.md 17 KB
- scripts/alert-notify/.gitignore 25 B
- scripts/alert-notify/incident_utils.py 2.3 KB runs code
- scripts/alert-notify/notifier_base.py 2.4 KB runs code
- scripts/alert-notify/open_claw_dashboard_notifier.py 11 KB runs code
- scripts/alert-notify/requirements.txt 82 B
- scripts/alert-notify/server.py 16 KB runs code
- scripts/alert-notify/slack_notifier.py 8.2 KB runs code
- skill-card.md 4.3 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.
- 17d ago Changed 12a4ac6572ee
- 24d ago Changed · +4 lines 94583555047c
- 1mo ago Changed 812f78e5c19f
- 1mo ago Changed · -261 lines 1deac93d4fea
- 1mo ago Changed · -4 lines 28eddee8bf3b
- 1mo ago Changed · +120 lines 6049979af2f8
- 1mo ago Changed · +5 lines d2bb7a4d2510
- 1mo ago Changed 6f0d77276080
- 2mo ago Changed · +19 lines c2dd50ae29cb
- 2mo ago First seen · 618 lines · 54 tokens per session scan B 4a81c2cb33ef
vss-manage-alerts is a skill published in the GitHub repository NVIDIA-AI-Blueprints/video-search-and-summarization (1,968 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 12,993 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
vss-manage-alerts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vss-manage-alertsNVIDIA-AI-Blueprints/video-search-and-summarization | Skill | 2.0k | yesterday | Apache-2.0 | B | 54 | Claude Code, Codex |
| bubbaloop-physical-aikornia/bubbaloop | Skill | 30 | 4mo ago | Apache-2.0 | A | 40 | Claude Code, Codex |
| using-bubbaloopkornia/bubbaloop | Skill | 30 | 4mo ago | Apache-2.0 | B | 53 | Claude Code |
| cardputer-buddyanthropics/claude-plugins-official | Skill | 46k | yesterday | Apache-2.0 | A | 109 | Claude Code |
| apigee-agent-gateway-governancegoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 222 | Claude Code, Codex |
| developer-device-platform-basicsgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 57 | Claude Code, Codex |
| google-cloud-filestore-autoscalegoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 102 | Claude Code, Codex |