perf-host-analysis

perf-host-analysis is a skill for Claude Code, Codex from Saddss/cursor-skills. It costs 202 tokens per session (5,807 once invoked), scanned A, original, no licence file.

A trace-analysis workflow for measuring computer processor overhead during large language model inference, the process of generating model responses. It examines nsys traces, which are performance recordings, for systems such as vLLM, SGLang, and TensorRT-LLM.

In plain words
What is it for?
Checking whether host-side work is the bottleneck and breaking down the overhead by processing phase.
Why use it?
It determines whether work done by the computer’s main processor is making the graphics processor wait, using measurements from the trace.

Skill for Claude CodeCodex

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

Good fit Checking whether host-side work is the bottleneck and breaking down the overhead by processing phase.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saddss/cursor-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 Saddss/cursor-skills --skill perf-host-analysis
Clone the repo
git clone --depth 1 https://github.com/Saddss/cursor-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/saddss/cursor-skills/perf-host-analysis.svg)](https://agentmods.dev/skills/saddss/cursor-skills/perf-host-analysis)
Your own site
<a href="https://agentmods.dev/skills/saddss/cursor-skills/perf-host-analysis"><img src="https://agentmods.dev/badge/skills/saddss/cursor-skills/perf-host-analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,807 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 $0.00202 $0.05807
Opus 5 $0.00101 $0.02903
Sonnet 5 $0.00040 $0.01161
Haiku 4.5 $0.00020 $0.00581

Measured 7d ago against content hash f12b5c3e6c17, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyze_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.

skills/perf-host-analysis/SKILL.md · 542 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

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 542 lines · 202 tokens per session scan A f12b5c3e6c17

Subscribe to this mod's changes

perf-host-analysis is a skill published in the GitHub repository Saddss/cursor-skills (2 stars, last pushed 9d ago), with no licence file. It adds 202 tokens to every session and 5,807 once invoked, about $0.0010 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 2026-08-31.

Related

Other skills, from other repositories

perf-host-analysis

Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify…

wenyi-li/awesome-agent-kernel-skills · 171 tokens

perf-host-optimization

Profiles and optimizes TensorRT-LLM host/CPU overhead using lineprofiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.

wenyi-li/awesome-agent-kernel-skills · 52 tokens

performance-analysis

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

ruvnet/ruflo · 20 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