TensorRT-LLM: Skill for Claude Code

.claude/skills/trtllm-model-onboard-multimodal/SKILL.md

trtllm-model-onboard-multimodal is a skill for Claude Code from NVIDIA/TensorRT-LLM. It costs 93 tokens per session (11,572 once invoked), scanned A, original, no licence file.

A guide for adding multimodal Hugging Face models to TensorRT-LLM's PyTorch backend. Multimodal models process more than text, such as images, audio, or video.

In plain words
What is it for?
Adding or extending vision, audio, or video-and-text models by writing model code, input processing, and weight-mapping code.
Why use it?
It lays out the code areas needed to connect a model's inputs and weights to the backend.

Skill for Claude Code ✓ vendor

Written for Claude Code: installed under .claude/.

This is NVIDIA/TensorRT-LLM's own configuration. It tells Claude Code how to work on TensorRT-LLM itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TensorRT-LLM configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NVIDIA/TensorRT-LLM. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/NVIDIA/TensorRT-LLM/main/.claude/skills/trtllm-model-onboard-multimodal/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/TensorRT-LLM

Made for: Claude Code.

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 trtllm-model-onboard-multimodal

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia/tensorrt-llm/trtllm-model-onboard-multimodal/github.svg)](https://agentmods.dev/skills/nvidia/tensorrt-llm/trtllm-model-onboard-multimodal)
Your own site
<a href="https://agentmods.dev/skills/nvidia/tensorrt-llm/trtllm-model-onboard-multimodal"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-llm/trtllm-model-onboard-multimodal/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.

agentmods 80×15 button for trtllm-model-onboard-multimodal

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia/tensorrt-llm/trtllm-model-onboard-multimodal"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-llm/trtllm-model-onboard-multimodal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,572 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 7
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 16
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 16
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin unknown 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 5.1 $0.00093 $0.11572
Opus 5 $0.00046 $0.05786
Sonnet 5 $0.00019 $0.02314
Haiku 4.5 $0.00009 $0.01157

Measured 3d ago against content hash 4d54609c5960, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

trtllm-model-onboard-multimodal scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Send a chat completion with a real image; confirm coherent output. (TODO: 2ez4bz to provide ready-to-use curl examples.)
.claude/skills/trtllm-model-onboard-multimodal/SKILL.md · 472 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. 3d ago Changed 4d54609c5960
  2. 9d ago First seen · 472 lines · 93 tokens per session scan A 973fb74c1c7d

Subscribe to this mod's changes

trtllm-model-onboard-multimodal is a skill published in the GitHub repository NVIDIA/TensorRT-LLM (14,574 stars, last pushed today), with no licence file. It adds 93 tokens to every session and 11,572 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.