deepstream-dev

Development guidance for NVIDIA DeepStream, a toolkit for building video-processing and computer-vision pipelines. It covers Python pipelines, TensorRT model execution, and streaming video analytics.

In plain words
What is it for?
Building DeepStream pipelines that read video, run inference, optionally track objects, and display results with labels or bounding boxes.
Why use it?
It gives coding agents the required software versions, pipeline structure, and API details needed to avoid incorrect configurations.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/practicalswan/agent-skills/deepstream-dev
Any agent
npx skills add PracticalSwan/agent-skills --skill deepstream-dev
Clone the repo
git clone --depth 1 https://github.com/PracticalSwan/agent-skills

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,718 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00031 $0.03718
Opus 5 $0.00015 $0.01859
Sonnet 5 $0.00006 $0.00744
Haiku 4.5 $0.00003 $0.00372

Measured 2d ago against content hash 7753ebb16775, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deepstream-dev 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 2d 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.

deepstream-dev/SKILL.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepStream Development Skill

When this skill is active, ALWAYS read the relevant reference documents before generating code. Do NOT rely on memory - the reference documents contain critical details about exact property names, correct API usage, and common pitfalls.

SDK and Architecture Quick Reference

DeepStream SDK Version Requirements

  • GStreamer: 1.24.2
  • NVIDIA Driver: 590+
  • CUDA: 13.1
  • TensorRT: 10.14.1.48
  • Platforms: Ubuntu 24.04 (x86_64 and ARM64/Jetson)

Typical Pipeline Flow

Source → Stream Muxer → Inference → [Tracker] → OSD → Renderer

Components in [brackets] are optional -- only add them when the user explicitly requests them.

Stage Role Key Element(s) Required?
Source Input from files, RTSP, cameras nvurisrcbin (preferred), nvmultiurisrcbin, filesrc Yes
Stream Muxer Batches streams for inference nvstreammux Yes
Inference TensorRT model execution nvinfer, nvinferserver Yes
Tracker Multi-object tracking across frames nvtracker Only if requested
OSD Draws bounding boxes, labels, overlays nvosdbin Yes (for visualization)
Renderer Display or save output nveglglessink, nv3dsink, filesink Yes

Memory Model

DeepStream uses NVIDIA Video Memory Manager (NVMM) for zero-copy GPU buffer transfers. Caps strings use memory:NVMM to indicate GPU memory (e.g., video/x-raw(memory:NVMM), format=NV12).

Critical Rules

  1. Only Add Requested Components: Do NOT add pipeline elements the user did not ask for.
    • Tracker (nvtracker): Only add when the user explicitly requests tracking or object IDs across frames
    • Secondary GIEs: Only add when the user requests classification or attribute extraction
    • Analytics (nvdsanalytics): Only add when the user requests line crossing, ROI counting, etc.
    • Message broker (nvmsgbroker/nvmsgconv): Only add when the user requests Kafka/cloud messaging
    • When in doubt, build the minimal working pipeline and let the user ask for additions

Read the full file on GitHub · 229 lines

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. 2d ago First seen · 229 lines · 31 tokens per session scan A 7753ebb16775

Subscribe to this mod's changes

deepstream-dev is a skill published in the GitHub repository PracticalSwan/agent-skills (11 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 3,718 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

bilibili-video-notes

从 B 站教育/讲课视频生成带截图的 DOCX 学习笔记。下载视频+字幕→全覆盖抽帧→OCR去重→AI视觉打分→提取图中内容→融合生成DOCX。.

asdhabdua/bilibili-video-notes-skill · 58 tokens

nemoclaw-maintainer-validate-launchable

Validate the user-facing staging Brev Launchable deployment, NemoClaw image and runtime identity, onboarding, CLI behavior, and inference. Use when a maintainer asks to test the staging Launchable in the Brev web interface, provides a deployed Brev environment URL, hands a Launchable instance to Codex, or needs…

NVIDIA/NemoClaw · 87 tokens

nemoclaw-maintainer-find-review-pr

Find open PRs with the security label and Urgent or High Project Priority. Link each PR to its issue. Identify competing or superseded PRs and report review candidates. Use when looking for the next PR to review. Trigger keywords - find pr, find review, next pr, pr to review, duplicate pr, security pr.

NVIDIA/NemoClaw · 76 tokens

nemoclaw-maintainer-verify-stale

Verifies whether stale NVIDIA/NemoClaw bug reports still reproduce on the newest release tag. Use when maintainers ask to verify stale issues, reproduce old bugs on the newest release tag, or drain the bug backlog. Treats issue reproducers as untrusted, validates them on the reported release before a fixed verdict…

NVIDIA/NemoClaw · 91 tokens

nemoclaw-contributor-implement-issue

Implement an accepted NemoClaw GitHub issue in the current checkout. Use when a user asks to pick up an issue for implementation, implement or fix a named issue, or add the issue's tests. Confirm accepted scope, deliver the smallest independently valuable capability slice, and record validation and remaining gates…

NVIDIA/NemoClaw · 134 tokens

nemoclaw-maintainer-triage

Triage NemoClaw issues and PRs with Issue Type, Project fields, and allowed labels. Support one item or a batch. Show proposed changes and apply only changes the maintainer accepts. Trigger keywords - triage, label issues, suggest labels, batch triage, triage issue, triage PR, label this, what labels.

NVIDIA/NemoClaw · 78 tokens