agentmods.dev

deepstream-import-vision-model

deepstream-import-vision-model is a skill for Codex from PracticalSwan/agent-skills. It costs 41 tokens per session (4,390 once invoked), scanned A, a copy of deepstream-import-vision-model, MIT.

A guided workflow for importing object-detection vision models into NVIDIA DeepStream, a system for building video and image-processing pipelines. It covers model acquisition, TensorRT engine building, pipeline setup, benchmarking, and reports.

In plain words
What is it for?
Use it to bring supported models from Hugging Face or NVIDIA NGC into DeepStream, build engines, run single- and multi-stream tests, and produce benchmark reports.
Why use it?
It brings the model-import steps together and checks important environment details, reducing the chance of incompatible builds or incomplete performance testing.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

not rated 13repo changed yesterday A scan 41 tokens copy · 88% MIT

Good fit Use it to bring supported models from Hugging Face or NVIDIA NGC into DeepStream, build engines, run single- and multi-stream tests, and produce benchmark reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/practicalswan/agent-skills/deepstream-import-vision-model
View source ↗ PracticalSwan/agent-skills
Install

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.

Any agent
npx skills add PracticalSwan/agent-skills --skill deepstream-import-vision-model
Clone the repo
git clone --depth 1 https://github.com/PracticalSwan/agent-skills

Made for: 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 deepstream-import-vision-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/practicalswan/agent-skills/deepstream-import-vision-model.svg)](https://agentmods.dev/skills/practicalswan/agent-skills/deepstream-import-vision-model)
Your own site
<a href="https://agentmods.dev/skills/practicalswan/agent-skills/deepstream-import-vision-model"><img src="https://agentmods.dev/badge/skills/practicalswan/agent-skills/deepstream-import-vision-model.svg" alt="Measured on agentmods" 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 4,390 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod 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 $0.04390
Opus 5 $0.00020 $0.02195
Sonnet 5 $0.00008 $0.00878
Haiku 4.5 $0.00004 $0.00439

Measured yesterday against content hash 44920804adc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

deepstream-import-vision-model 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 yesterday.

The scan reads SKILL.md. This mod also ships 33 executable files (install.ps1, install.sh, scripts/deepstream/benchmark-ds.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.

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.

Origin

This is a copy

88% identical to deepstream-import-vision-model — 77 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

deepstream-import-vision-model/SKILL.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepStream Import Vision Model

When this skill is active, read the relevant reference document before starting each phase. Do not rely on memory — reference documents contain exact script paths, bash variable conventions, log filename contracts, and critical parsing rules.

Current scope: Object detection models only. Fail fast on classification, segmentation, or other architectures detected in config.json.

Model choice — always offer two options

Before preflight, browsing, downloads, or file creation, present exactly these two choices. Do not start with only an open-ended model-source prompt. If the user's request already clearly selects a model, confirm the matching choice instead of asking redundantly.

1. Default model (recommended)

Use the validated Hugging Face RT-DETR model:

model_id: PekingU/rtdetr_r50vd
source: huggingface
task: object-detection
precision_preference: fp16

2. Custom object-detection model

Ask for one supported source:

  • Hugging Face model ID (organization/model) or full model URL.
  • NVIDIA NGC catalog model URL including its version.

Explain that the skill currently rejects classification, segmentation, and other non-detection architectures after inspecting config.json. Do not invent or silently substitute a model when the custom source is missing or unsupported.

For a dry run, present the same two choices and simulate discovery, build, benchmark, and report stages without browsing, downloading, launching Docker, writing files, or starting processes.

Pipeline Overview

Step Phase Reference What it does
1–3 Model Acquire references/model-acquire.md Browse HF/NGC, detect format, download ONNX or export SafeTensors
4–5 Engine Build references/engine-build.md Build dynamic TRT engine, run trtexec BS=1 and BS=MAX_BS
6–7 DS Pipeline references/pipeline-run.md Custom bbox parser, nvinfer config, single-stream + multi-stream benchmarks
8 Report references/report-generation.md 5 charts, HTML, PDF benchmark report

Read the full file on GitHub · 289 lines

Files

What ships with it

55 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.

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. yesterday Changed · +66 lines 44920804adc9
  2. 4d ago Changed cdfafa0e91e5
  3. 7d ago First seen · 223 lines · 41 tokens per session scan A 69c36087d1f6

Subscribe to this mod's changes

deepstream-import-vision-model is a skill published in the GitHub repository PracticalSwan/agent-skills (13 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 4,390 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to deepstream-import-vision-model, differing in 77 lines, and is treated as a copy.

Data and AINVIDIAdeepstreammodel-importonnxtensorrtvision
Related

Other skills, from other repositories

nemo-curator

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or…

davila7/claude-code-templates · 83 tokens

training-llms-megatron

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA…

davila7/claude-code-templates · 82 tokens

nemo-guardrails

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

davila7/claude-code-templates · 61 tokens

nemotron-retrieval-recipes

Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes.

NVIDIA-NeMo/Nemotron · 36 tokens

nemotron-nano3

Reference desk for Nemotron 3 Nano / Llama-Nemotron Nano 3 — architecture, training data, recipes, evaluation, quantization, deployment. Use when the user asks facts about the model rather than building a pipeline.

NVIDIA-NeMo/Nemotron · 53 tokens

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

Orchestra-Research/AI-Research-SKILLs · 88 tokens