NVIDIA/TensorRT-Model-Connect is a collection of C++ reference implementations for deploying supported Hugging Face models with NVIDIA TensorRT, a system that runs trained models to produce inference results. It is for developers who want to build and run supported models or evaluate model integrations through TensorRT. The catalogue entries provide skills and instructions for using this model deployment workflow.
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/TensorRT-Model-Connect --skill setup-trtmc-environmentgit clone --depth 1 https://github.com/NVIDIA/TensorRT-Model-ConnectWrote 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/tensorrt-model-connect/setup-trtmc-environment)<a href="https://agentmods.dev/skills/nvidia/tensorrt-model-connect/setup-trtmc-environment"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-model-connect/setup-trtmc-environment/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/tensorrt-model-connect/setup-trtmc-environment"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-model-connect/setup-trtmc-environment.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 | $0.00032 | $0.00314 |
| Opus 5.5 | $0.00013 | $0.00126 |
| Sonnet 5.5 | $0.00006 | $0.00063 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
setup-trtmc-environment 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.
What it actually says
Set Up the Environment
Start from the checkout and current repository documentation, not a remembered machine or container name.
- Resolve the repository root and read
website/docs/getting-started/source-build.md,Dockerfile, andapps/devtoolkit/README.md. - Inspect host architecture, available disk, Docker access, GPU visibility, driver, and compute capability only as needed for the requested work.
- Prefer the existing
apps/devtoolkitAPI for a checkout-owned environment. Use its Docker path for the supported development image or its local path with an explicit existing Python interpreter. - Select one family when model work is requested. Install only that family's
optional
families/<family>/requirements.txt; a missing file means no family package step. - Verify the checkout mount, Python import, TensorRT import, GPU visibility, runtime root, and requested native target before starting the real task.
Do not reuse, replace, or remove an unrelated container. Do not install GPU drivers, reconfigure the container runtime, or change runner settings without separate authorization. Stop and explain the unsupported host boundary when the documented paths do not apply.
Report environment preparation separately from compilation, tests, model correctness, performance, and deployment qualification.
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 · -2 lines · -16 tokens per session 8c8ed0e13741
- 1mo ago First seen · 36 lines · 48 tokens per session scan A 83273b27917d
setup-trtmc-environment is a skill published in the GitHub repository NVIDIA/TensorRT-Model-Connect (280 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 314 once invoked, about $0.0001 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
huggingface-transformers
Use when running or fine-tuning Hugging Face Transformers models in Python — pipeline() inference for text classification and generation, loading weights with AutoModel/AutoTokenizer, devicemap and dtype memory management, tokenizer usage, Trainer fine-tuning, and BGE embeddings for Chinese RAG. Covers transformers…
graphsignal-profiler
Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about graphsignal-run or graphsignal.watch(), or asks about CUPTI / Prometheus / OTLP setup.
feature-flag-creation
Guide for adding new base::Feature flags and feature parameters (BASEFEATURE, BASEFEATUREPARAM, BASEFEATUREENUMPARAM) in Chromium, including choosing the right feature file, macro syntax, comment placement, testing with ScopedFeatureList, and optional chrome://flags or Android Java exposure.
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…
qa
QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or app — including a local dev server (e.g. "qa test localhost:5173", "does the checkout work?", "rate this landing page").…