benchmark-video-summarization

benchmark-video-summarization is a skill for Claude Code, Codex from NVIDIA-AI-Blueprints/video-search-and-summarization. It costs 41 tokens per session (4,591 once invoked), scanned C, original, no licence file.

A benchmarking workflow for a deployed LVS video-summarization service, using test media to measure speed, capacity, and GPU usage.

In plain words
What is it for?
It is for testing single-video response time and handling many videos at once, then reviewing GPU and latency metrics.
Why use it?
It shows where latency or burst-load limits occur and provides configuration recommendations based on the measurements.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/dev-profile.sh up \.

Good fit It is for testing single-video response time and handling many videos at once, then reviewing GPU and latency metrics.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization
agentmods
npx agentmods add skills/nvidia-ai-blueprints/video-search-and-summarization/benchmark-video-summarization

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for benchmark-video-summarization

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/benchmark-video-summarization/github.svg)](https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/benchmark-video-summarization)
Your own site
<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/benchmark-video-summarization"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/benchmark-video-summarization/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.

agentmods 80×15 button for benchmark-video-summarization

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/benchmark-video-summarization"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/benchmark-video-summarization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,591 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.04591
Opus 5 $0.00020 $0.02295
Sonnet 5 $0.00008 $0.00918
Haiku 4.5 $0.00004 $0.00459

Measured 8d ago against content hash 1d84cc70b962, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

benchmark-video-summarization scanned grade C 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 8d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/base.py, scripts/cpu_monitor.py, scripts/fetch-videos.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s "http://localhost:8888/videos/" | python3 -m json.tool 2>/dev/null || \

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| LVS deployed by you via `vss-deploy-profile` (lvs profile) with a unique `COMPOSE_PROJECT_NAME` | `curl -sf ${LVS_BACKEND}/v1/ready` returns 200 |
skills/benchmarking/benchmark-video-summarization/SKILL.md · 355 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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.

  1. 8d ago First seen · 355 lines · 41 tokens per session scan C 1d84cc70b962

Subscribe to this mod's changes

benchmark-video-summarization is a skill published in the GitHub repository NVIDIA-AI-Blueprints/video-search-and-summarization (1,859 stars, last pushed today), with no licence file. It adds 41 tokens to every session and 4,591 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

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…

Graphify-Labs/graphify · 76 tokens

google-cloud-solution-rag-enterprise-search-gke-sqldb

Discovers requirements, and generates architectural, design, and deployment guidance for a retrieval-augmented generation (RAG)-capable enterprise search system in Google Cloud. Use when users need a vector-enabled SQL database as the store and index for the embedding vectors, an open model and open-source inferencing…

google/skills · 114 tokens

evalscope

LLM evaluation & inference performance testing via the evalscope CLI. Translates natural language requests into evalscope commands for: (1) Model accuracy evaluation — runs registered benchmarks against local checkpoints or API endpoints (OpenAI-compatible, Anthropic, LiteLLM); (2) Performance stress testing — TTFT…

modelscope/evalscope · 195 tokens

gpt-image-2

A skill for generating or editing images with GPT Image 2 across local, host-provided, or advisory setups.

ConardLi/garden-skills · 177 tokens

kb-retriever

A retrieval and question-answering assistant for a local folder of documents, including Markdown, text, PDFs, and spreadsheets.

ConardLi/garden-skills · 105 tokens