perf-torch-cuda-graph-specialist

perf-torch-cuda-graph-specialist is an agent for Claude Code from NVIDIA/TensorRT-LLM. It costs 120 tokens per session (738 once invoked), scanned A, original, no licence file.

An expert coding agent for CUDA Graphs in PyTorch. CUDA Graphs capture a sequence of GPU operations so it can be replayed with less CPU work.

In plain words
What is it for?
Reviewing CUDA Graph compatibility, removing host-device synchronization, and choosing an appropriate PyTorch or related CUDA Graph API.
Why use it?
It helps find issues that prevent graph capture or cause unnecessary CPU-to-GPU synchronization during replay.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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 agents/nvidia/tensorrt-llm/perf-torch-cuda-graph-specialist
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 perf-torch-cuda-graph-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/nvidia/tensorrt-llm/perf-torch-cuda-graph-specialist.svg)](https://agentmods.dev/agents/nvidia/tensorrt-llm/perf-torch-cuda-graph-specialist)
Your own site
<a href="https://agentmods.dev/agents/nvidia/tensorrt-llm/perf-torch-cuda-graph-specialist"><img src="https://agentmods.dev/badge/agents/nvidia/tensorrt-llm/perf-torch-cuda-graph-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 120 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 738 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00120 $0.00738
Opus 5 $0.00060 $0.00369
Sonnet 5 $0.00024 $0.00148
Haiku 4.5 $0.00012 $0.00074

Measured 6d ago against content hash 8eba70179e1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

perf-torch-cuda-graph-specialist 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 6d 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.

.claude/agents/perf-torch-cuda-graph-specialist.md · 61 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. 6d ago First seen · 61 lines · 120 tokens per session scan A 8eba70179e1e

Subscribe to this mod's changes

perf-torch-cuda-graph-specialist is an agent published in the GitHub repository NVIDIA/TensorRT-LLM (14,550 stars, last pushed today), with no licence file. It adds 120 tokens to every session and 738 once invoked, about $0.0006 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 agents, from other repositories

analysis_expert

Analysis expert in Single-Cell and Spatial Omics data analysis, with expertise in analyze data with python tools in scverse ecosystem and jupyter notebook. It's has the visual understanding ability can observe and understand the images.

aristoteleo/PantheonOS · 47 tokens

pollen-forecaster

Combines station counts with weather to produce a two day outlook per region. Accuracy collapses during a wet spring because the counting stations themselves under sample, which is a data problem rather than a model one.

wrg32786/aigent-os · 0 tokens

staff-data-sci

Personas are Opus-only. The Data Science Reviewer — data science, ML, and statistical-modeling expertise complementing the Staff Engineer's review.

dbc-oduffy/coordinator-claude · 35 tokens

STAgent

STAgent is a multiagent system built by [[org:liulab-bioelectronics-harvard]] designed to facilitate the analysis of [[domain:spatial]] transcriptomics data. The system provides an end-to-end workflow for processing .h5ad datasets, integrating autonomous reasoning and visual analysis to interpret tissue organization…

seandavi/biomedical-agent-kg · 2 tokens

Apex Metabolic AI Lab

Apex Metabolic AI Lab is a specialized biomedical system designed to address complex challenges in metabolic research. It focuses on synthesizing high-dimensional biological data to support advanced analytical workflows.

seandavi/biomedical-agent-kg · 6 tokens

ml-engineer

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

viksant/vibe-coding-tools-content · 51 tokens