perf-profiling-specialist

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

In plain words
What is it for?
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.
Why use it?
It provides focused profiling and workload measurement when performance problems need evidence from GPU tools.

Agent for Claude Code

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-profiling-specialist
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/TensorRT-LLM

Made for: Claude Code.

Per session 152 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,172 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 $0.00152 $0.04172
Opus 5 $0.00076 $0.02086
Sonnet 5 $0.00030 $0.00834
Haiku 4.5 $0.00015 $0.00417

Measured 3d ago against content hash 2a941770b852, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

.claude/agents/perf-profiling-specialist.md · 384 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

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 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 (14,505 stars, last pushed 3d ago), with no licence file. It adds 152 tokens to every session and 4,172 once invoked, about $0.0008 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

owner-judge

Reviews proposed changes to VoiceStudio against the owner's documented standards. Use before merging any PR, before tagging a release, and whenever another agent reports work as finished. Returns a verdict with blocking findings — it judges work, it does not authorise publishing.

debpalash/VoiceStudio · 54 tokens

triage-labels

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

debpalash/VoiceStudio · 0 tokens

google-colab-expert

Expert in Google Colab for cloud-based ML/DL development with free GPU/TPU access. Specializes in Colab 2025 features (Gemini AI integration, google.colab.ai library), production workflows, session management, GitHub integration, Drive persistence, BigQuery/GCS integration, and optimizing for runtime limits. Use for…

andisab/swe-marketplace · 282 tokens

AGENTS

../AGENTS.md.

NVIDIA/cuopt · 0 tokens

metal-reviewer

Reviews Metal / Apple-Silicon code under core/src/metal/ (runtime, picture, IOSurface import) and core/src/feature/metal/ (.mm / .metal pairs) for correctness, parity vs the CUDA / Vulkan twins, and Apple-Family-7 gating. Use when reviewing .mm host wrappers, .metal MSL kernels, or IOSurface zero-copy patterns.

VMAFx/vmafx · 82 tokens

pr-body-checker

Validates a PR body against the ADR-0108 deep-dive deliverables checklist locally before push. Catches the dominant CI-waste failure mode (prose-bullet deliverables instead of - [x] Item checkboxes) in under 5 seconds. Use when reviewing a draft PR description before opening or after editing.

VMAFx/vmafx · 75 tokens