What is perf-profiling-specialist?

A specialist for measuring GPU performance in TensorRT-LLM workloads, which run large language models with NVIDIA's inference software.

Use it to run Python scripts, CUDA programs, or shell commands and profile them with nvidia-smi, Nsight Systems, Nsight Compute, or the PyTorch profiler.

It provides focused profiling and workload measurement when performance problems need evidence from GPU tools.

How NVIDIA/TensorRT-LLM configures Claude Code

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/agents/perf-profiling-specialist.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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/nvidia/tensorrt-llm/perf-profiling-specialist/github.svg)](https://agentmods.dev/agents/nvidia/tensorrt-llm/perf-profiling-specialist)

Your own site

<a href="https://agentmods.dev/agents/nvidia/tensorrt-llm/perf-profiling-specialist"><img src="https://agentmods.dev/badge/agents/nvidia/tensorrt-llm/perf-profiling-specialist/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/nvidia/tensorrt-llm/perf-profiling-specialist"><img src="https://agentmods.dev/badge/agents/nvidia/tensorrt-llm/perf-profiling-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 163 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 4,763 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00163	$0.04763
Opus 5.5	$0.00065	$0.01905
Sonnet 5.5	$0.00033	$0.00953
Haiku 4.5	$0.00016	$0.00476

Measured 17d ago against content hash 445979204f13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

perf-profiling-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 17d 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-profiling-specialist.md · 417 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.

17d ago Changed · +33 lines · +11 tokens per session 445979204f13
2mo ago First seen · 384 lines · 152 tokens per session scan A 2a941770b852

Subscribe to this mod's changes

perf-profiling-specialist is an agent published in the GitHub repository NVIDIA/TensorRT-LLM (15,021 stars, last pushed today), with no licence file. It adds 163 tokens to every session and 4,763 once invoked, about $0.0007 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.

Analytics and metrics Debugging PyTorch blackwell cuda llm-serving moe

perf-profiling-specialist next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
perf-profiling-specialistNVIDIA/TensorRT-LLM	Agent	15k	today	none	A	163	Claude Code
kernel-optimizerpjt222/agent-almanac	Agent	43	yesterday	MIT	A	30	Claude Code
debuggerTT-Wang/forge	Agent	35	3d ago	MIT	A	17	Claude Code
loom-advisorcosmix/loom	Agent	65	5d ago	MIT	A	53	Claude Code
scramjet:instruction-semantics-analyzerLeanAndMean/scramjet	Agent	8	4d ago	Apache-2.0	A	35	Claude Code
wizardskeggsguy/adventure-party	Agent	6	24d ago	MIT	A	60	Claude Code
debuggerNickCrew/Claude-Cortex	Agent	66	4mo ago	MIT	A	38	Claude Code

TensorRT-LLM: Agent for Claude Code