agentmods.dev

TensorRT-LLM: Skill for Claude Code

.claude/skills/kernel-triton-writing/SKILL.md

kernel-triton-writing is a skill for Claude Code from NVIDIA/TensorRT-LLM. It costs 105 tokens per session (4,234 once invoked), scanned C, original, no licence file.

A guide for writing GPU kernels with OpenAI Triton, a Python-based language for GPU programming. It covers common fused operations, reductions, matrix multiplication, and attention-related kernels.

In plain words
What is it for?
Writing Triton kernels for operations such as fused elementwise code, softmax, LayerNorm, RMSNorm, tiled matrix multiplication, and flash-attention work.
Why use it?
It helps avoid applying CUDA C++ or other GPU-kernel techniques to code that specifically uses Triton.

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 →

not rated 15krepo +41 changed 17d ago C scan 105 tokens custom licence
View source ↗ NVIDIA/TensorRT-LLM nvidia.github.io
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/kernel-triton-writing/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 kernel-triton-writing

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia/tensorrt-llm/kernel-triton-writing"><img src="https://agentmods.dev/badge/skills/nvidia/tensorrt-llm/kernel-triton-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,234 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00105 $0.04234
Opus 5.5 $0.00042 $0.01694
Sonnet 5.5 $0.00021 $0.00847
Haiku 4.5 $0.00011 $0.00423

Measured 17d ago against content hash 953178aecb25, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

kernel-triton-writing scanned grade C 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 17d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/__init__.py, scripts/benchmark_kernel.py, scripts/verify_kernel.py), 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| Kernel not updating after edit | Stale compilation cache | `rm -rf ~/.triton/cache/` |
.claude/skills/kernel-triton-writing/SKILL.md · 343 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

Files

What ships with it

12 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. 17d ago Changed · +5 tokens per session 953178aecb25
  2. 2mo ago First seen · 343 lines · 100 tokens per session scan C 5a379c6acccc

Subscribe to this mod's changes

kernel-triton-writing is a skill published in the GitHub repository NVIDIA/TensorRT-LLM (15,021 stars, last pushed today), with no licence file. It adds 105 tokens to every session and 4,234 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LanguagesPyTorchPythonblackwellcudallm-servingmoetriton
Related

kernel-triton-writing compared with skills from other repositories

kernel-triton-writing next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kernel-triton-writingNVIDIA/TensorRT-LLMSkill15ktodaynoneC105Claude Code
cuopt-developerNVIDIA/cuoptSkill1.1kyesterdayApache-2.0B47Cursor
cutedsl_megamoeflashinfer-ai/flashinferSkill6.9ktodayApache-2.0C0Claude Code, Codex
swapab_cutedsl_megakernelflashinfer-ai/flashinferSkill6.9ktodayApache-2.0C0Claude Code, Codex
rapids-firstTioSisai/rapids-firstSkill425d agoMITA76Claude Code, Codex
cuopt-installNVIDIA/cuoptSkill1.1kyesterdayApache-2.0A40Cursor
cuopt-routing-api-pythonNVIDIA/cuoptSkill1.1kyesterdayApache-2.0A37Cursor