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 bdd-container-updategit 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/bdd-container-update)<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/bdd-container-update"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/bdd-container-update/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/bdd-container-update"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/bdd-container-update.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 | $0.00117 | $0.01254 |
| Opus 5.5 | $0.00047 | $0.00502 |
| Sonnet 5.5 | $0.00023 | $0.00251 |
| Haiku 4.5 | $0.00012 | $0.00125 |
Grade A, and why
bdd-container-update 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 1mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BDD Test Container Update
The BDD test container runs bdd_test from
<INTERNAL_REGISTRY>/bdd_tests:<TAG>. Since the CI
runner bind-mounts the host repo's test source into /app/, the image only
needs to be rebuilt when the things it bakes in change.
When to rebuild
Rebuild required -- files baked into the image:
test/bdd_tests/Dockerfiletest/bdd_tests/docker-entrypoint.shtest/bdd_tests/pyproject.toml(any change -- deps or pytest config)test/bdd_tests/poetry.locktest/bdd_tests/test_videos/*(sample clips baked to/app/test_videos)
Note on
test_videos/: the clip binaries are gitignored -- they are NOT in the repo, only baked into the published image. The pushed image is the source of truth. Before rebuilding you must repopulatetest/bdd_tests/test_videos/from the current published image (or a backup); seetest/bdd_tests/test_videos/README.md. A rebuild from a clean checkout without these files would bake an empty/app/test_videos.
Rebuild NOT required -- bind-mounted at runtime by
cicd_files/docker-compose-test/start_test.sh:
test/bdd_tests/tests/**test/bdd_tests/features/**test/bdd_tests/scripts/**test/bdd_tests/data/**test/bdd_tests/conftest.pytest/bdd_tests/config.json
If a change touches only files in the second list, stop here -- no container
work is needed and start_test.sh is unchanged.
1. Identify the current image tag
The image tag lives in cicd_files/docker-compose-test/start_test.sh inside
the update_docker_compose() function, on the line that sets the test
service image:
image: <INTERNAL_REGISTRY>/bdd_tests:v<MAJOR>.<MINOR>.<PATCH>_x86
Extract the current MAJOR, MINOR, and PATCH numbers.
2. Determine version bump
Classify the changes made under test/bdd_tests/:
| Change type | Bump | Examples |
|---|---|---|
| Major | Increment MAJOR, reset MINOR and PATCH to 0 | Dockerfile base image change, entrypoint rewrite, Python major version bump, dependency major version upgrade (e.g. poetry major), new system-level package added to Dockerfile |
| Minor | Increment MINOR, reset PATCH to 0 | New runtime dependency in pyproject.toml, dependency minor version updates in pyproject.toml/poetry.lock, new pytest plugin in deps, additions to the Dockerfile that do not break existing tests |
| Patch | Increment PATCH | Dependency patch upgrades, minor Dockerfile cleanup, comment-only edits to Dockerfile/entrypoint, pinning a transitive dependency in poetry.lock |
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.
- 1mo ago Changed · +8 lines 2ca3897f0efe
- 1mo ago First seen · 122 lines · 117 tokens per session scan A d08d9063d346
bdd-container-update is a skill published in the GitHub repository NVIDIA-AI-Blueprints/video-search-and-summarization (1,951 stars, last pushed today), licensed Apache-2.0. It adds 117 tokens to every session and 1,254 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
wiremock-standalone-docker
Provides patterns and configurations for running WireMock as a standalone Docker container. Generates mock HTTP endpoints, creates stub mappings for testing, validates integration scenarios, and simulates error conditions. Use when you need to mock APIs, create a mock server, stub external services, simulate…
vibe-service-health-dashboard
Queries all configured services for health status — uptime, restarts, errors, resources. Use when checking the health of running services.
quiz-generator
Generate educational quizzes from topics, learning goals, or provided documents. Supports multiple question types, difficulty levels, answer keys, explanations, and study-focused assessment. Use when the user wants practice questions, review quizzes, mock tests, self-checks, or exam prep.
exam2knowledge
An exam-analysis skill that works backward from exam or practice questions to identify frequently tested topics and reusable solution patterns.
ad-campaign-analyzer
Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.
agent-evaluation
Evaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt changes, reproducing failures, or running agent regression tests.