perf-host-analysis

perf-host-analysis is a skill for Claude Code, Codex from wenyi-li/awesome-agent-kernel-skills. It costs 171 tokens per session (3,942 once invoked), scanned A, original, no licence file.

A profiling guide for finding CPU and host-side delays in TensorRT-LLM inference using NVIDIA Nsight Systems traces. It examines GPU idle time and the phases that leave the GPU waiting.

In plain words
What is it for?
Use it to inspect host operation timings, isolate forward-pass steps, and compare all-reduce or NVTX-marked phases across trace versions.
Why use it?
It helps determine whether slow model serving is caused by CPU work instead of the GPU, and provides evidence for comparing performance regressions between versions.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to inspect host operation timings, isolate forward-pass steps, and compare all-reduce or NVTX-marked phases across trace versions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wenyi-li/awesome-agent-kernel-skills/perf-host-analysis
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.

Any agent
npx skills add wenyi-li/awesome-agent-kernel-skills --skill perf-host-analysis
Clone the repo
git clone --depth 1 https://github.com/wenyi-li/awesome-agent-kernel-skills

Made for: Claude Code, Codex.

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-host-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/wenyi-li/awesome-agent-kernel-skills/perf-host-analysis/github.svg)](https://agentmods.dev/skills/wenyi-li/awesome-agent-kernel-skills/perf-host-analysis)
Your own site
<a href="https://agentmods.dev/skills/wenyi-li/awesome-agent-kernel-skills/perf-host-analysis"><img src="https://agentmods.dev/badge/skills/wenyi-li/awesome-agent-kernel-skills/perf-host-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.

agentmods 80×15 button for perf-host-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/wenyi-li/awesome-agent-kernel-skills/perf-host-analysis"><img src="https://agentmods.dev/badge/skills/wenyi-li/awesome-agent-kernel-skills/perf-host-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 171 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,942 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00171 $0.03942
Opus 5 $0.00086 $0.01971
Sonnet 5 $0.00034 $0.00788
Haiku 4.5 $0.00017 $0.00394

Measured 6d ago against content hash 3d67ec228375, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

perf-host-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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/analyze_host_overhead.py, scripts/detect_host_overhead.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.

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.

perf-host-analysis/SKILL.md · 353 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. 6d ago First seen · 353 lines · 171 tokens per session scan A 3d67ec228375

Subscribe to this mod's changes

perf-host-analysis is a skill published in the GitHub repository wenyi-li/awesome-agent-kernel-skills (9 stars, last pushed 3mo ago), with no licence file. It adds 171 tokens to every session and 3,942 once invoked, about $0.0009 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 2026-09-03.

Related

Other skills, from other repositories

perf-host-analysis

Analyze host/CPU overhead in LLM inference (vLLM / SGLang / TRT-LLM serve / lmdeploy / TensorRT-LLM) from nsys traces. Phase 1 (Detection): determine whether host overhead is the bottleneck via a binary YES/NO verdict with metric evidence (GPU idle ratio, host prep exposed ratio, per-phase breakdown). Phase 2 (Root…

Saddss/cursor-skills · 202 tokens

perf-host-optimization

Profiles and optimizes LLM inference host / CPU overhead (vLLM / SGLang / TRT-LLM serve / lmdeploy / TensorRT-LLM PyExecutor) using lineprofiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low, when perf-host-analysis has concluded "host-bound", or…

Saddss/cursor-skills · 130 tokens

pytorch-profile-analysis

Analyze single-file PyTorch/Kineto Chrome trace .json(.gz) files using the VeloQ CLI. Use for CPU/CUDA/kernel correlation, ProfilerStep/annotation slicing, memory/shape grouping, and single-trace NCCL evidence.

lucifer1004/VeloQ · 56 tokens

performance-analysis

Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.

ruvnet/agentic-flow · 20 tokens

ncu-profile-analysis

Analyze Nsight Compute .ncu-rep and .ncu-repz kernel reports using the VeloQ CLI. Use for occupancy, warp stalls, memory/instruction bottlenecks, rule findings, source/SASS/PTX correlation, and metric CSV/table export.

lucifer1004/VeloQ · 61 tokens

nsys-profile-analysis

Analyze Nsight Systems .nsys-rep or pqtdir/ timeline traces using the VeloQ CLI. Use for GPU idle gaps, launch causes, CPU/GPU correlation, NVTX, CUDA graphs, metrics, sampling, and overlap/concurrency.

lucifer1004/VeloQ · 60 tokens