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 agentmods add skills/nvidia/tensorrt-model-connect/setup-trtmc-environmentnpx skills add NVIDIA/TensorRT-Model-Connect --skill setup-trtmc-environmentgit clone --depth 1 https://github.com/NVIDIA/TensorRT-Model-ConnectWhat 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 | $0.00048 | $0.00370 |
| Opus 5 | $0.00024 | $0.00185 |
| Sonnet 5 | $0.00010 | $0.00074 |
| Haiku 4.5 | $0.00005 | $0.00037 |
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 3d 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, not from existing container names or machine-specific workspace conventions.
- Find the repository root with
git rev-parse --show-toplevel. - Read the current environment guide,
Dockerfile, and matchingscripts/docker_build_*.sh/scripts/docker_run_*.sh. Treat them as the source of truth; do not copy assumptions from another host. - Inspect the host as needed (
uname,docker info,nvidia-smi, free disk) and select a repo-supported path. If none matches, explain the gap and stop. Do not install drivers or reconfigure the container runtime without separate authorization. - Build the selected repo image when it is missing or stale, using the repo's build path. Do not prebuild unrelated model-family reference profiles.
- Start a fresh container from that image with this checkout mounted read-write for development or read-only for deployment validation. Choose paths and names for this checkout; do not reuse, migrate, or remove unrelated containers.
- Verify the checkout mount, required GPU visibility, and TensorRT import, then run the requested build, test, packaging, or runtime command.
Keep model-specific dependencies on demand and follow each family's own lock and verification files. Report setup evidence separately from compilation, tests, model parity, performance, and production-deployment evidence.
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.
- 3d 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 (188 stars, last pushed 3d ago), licensed Apache-2.0. It adds 48 tokens to every session and 370 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.
Other skills, from other repositories
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.
weights-and-biases
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform.
huggingface-accelerate
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.
huggingface-hub
Hugging Face Hub — model discovery, download, inference, and upload.
ml-training
Machine learning model training authority — classifier and regressor training with scikit-learn and PyTorch, feature engineering, cross-validation, hyperparameter tuning, fine-tuning transformer models with HuggingFace, dataset splits, loss functions, learning rate schedules, and reproducible training runs.