What is perf-analysis?

A workflow for investigating how well a program uses its hardware resources. It coordinates profiling and classifies bottlenecks such as computation, memory, job startup, communication, or synchronization.

Profiling workloads, checking metrics such as model flops utilization and achieved hardware speed, diagnosing bottlenecks, and producing a structured report.

It turns performance investigation into a structured process and helps identify what is slowing a workload down.

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/skills/perf-analysis/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nvidia/tensorrt-llm/perf-analysis/github.svg)](https://agentmods.dev/skills/nvidia/tensorrt-llm/perf-analysis)

Your own site

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

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,511 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.01511
Opus 5.5	$0.00022	$0.00604
Sonnet 5.5	$0.00011	$0.00302
Haiku 4.5	$0.00006	$0.00151

Measured 17d ago against content hash 87e190561a6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

perf-analysis 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/skills/perf-analysis/SKILL.md · 161 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 87e190561a6c
2mo ago First seen · 161 lines · 56 tokens per session scan A 17992064d7e4

Subscribe to this mod's changes

perf-analysis is a skill published in the GitHub repository NVIDIA/TensorRT-LLM (15,021 stars, last pushed today), with no licence file. It adds 56 tokens to every session and 1,511 once invoked, about $0.0002 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 analysis blackwell bottleneck cuda llm-serving moe profiling

perf-analysis next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
perf-analysisNVIDIA/TensorRT-LLM	Skill	15k	today	none	A	56	Claude Code
performance-analysisruvnet/agentic-flow	Skill	838	today	none	A	20	Claude Code
performance-analysisproffesor-for-testing/agentic-qe	Skill	525	yesterday	MIT	A	20	Claude Code
performance-analysisblkst8/skills	Skill	6	14d ago	none	A	20	Claude Code, Codex
perf-analysisSaddss/cursor-skills	Skill	2	1mo ago	none	A	131	Claude Code, Codex
performance-analysisruvnet/ruflo	Skill	81k	today	MIT	A	20	Claude Code
sglang-diffusion-benchmark-profilesgl-project/sglang	Skill	39k	today	Apache-2.0	A	26	Claude Code, Codex

TensorRT-LLM: Skill for Claude Code