xpu-profile-unitrace

xpu-profile-unitrace is a skill for Claude Code from intel/gpu-ai-skills. It costs 127 tokens per session (1,612 once invoked), scanned A, original, Apache-2.0.

A low-level profiler for Intel XPU workloads using Intel's unitrace tool. It records kernel timing, memory transfers, communication events, and hardware-counter data below the level normally visible in PyTorch profiling.

In plain words
What is it for?
Investigating SYCL or oneAPI workloads, examining Level Zero events, measuring memory-copy activity, profiling oneCCL or MPI communication, and collecting hardware counters.
Why use it?
It helps explain which low-level GPU operation is responsible when a higher-level profiler has already identified a slow operation.

Skill for Claude Code ✓ vendor

Written for Claude Code: shipped in a Claude Code plugin.

Part of the intel-gpu-ai-skills plugin — 21 skills, 1 agent shipped together

Good fit Investigating SYCL or oneAPI workloads, examining Level Zero events, measuring memory-copy activity, profiling oneCCL or MPI communication, and collecting hardware counters.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/intel/gpu-ai-skills/xpu-profile-unitrace
About the project

Intel GPU AI Skills is a collection of agent skills for setting up, running, benchmarking, and profiling Hugging Face models on Intel GPUs. It supports workflows involving PyTorch, vLLM-XPU, SGLang-XPU, llama.cpp-SYCL, and migration from CUDA to XPU. The catalogue contains the project's skills, instructions, agent, and plugin.

intel/gpu-ai-skills · 21 stars · on GitHub

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 intel/gpu-ai-skills --skill xpu-profile-unitrace
Clone the repo
git clone --depth 1 https://github.com/intel/gpu-ai-skills

Made for: Claude Code.

Or install intel-gpu-ai-skills, the plugin that ships this one along with the rest of its 21 skills, 1 agent.

Its marketplace also offers this one on its own, as the plugin xpu-profile-unitrace/plugin install xpu-profile-unitrace after adding the marketplace above.

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 xpu-profile-unitrace

README.md
[![agentmods](https://agentmods.dev/badge/skills/intel/gpu-ai-skills/xpu-profile-unitrace/github.svg)](https://agentmods.dev/skills/intel/gpu-ai-skills/xpu-profile-unitrace)
Your own site
<a href="https://agentmods.dev/skills/intel/gpu-ai-skills/xpu-profile-unitrace"><img src="https://agentmods.dev/badge/skills/intel/gpu-ai-skills/xpu-profile-unitrace/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 xpu-profile-unitrace

Your own site · 80×15
<a href="https://agentmods.dev/skills/intel/gpu-ai-skills/xpu-profile-unitrace"><img src="https://agentmods.dev/badge/skills/intel/gpu-ai-skills/xpu-profile-unitrace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,612 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 137
    Potential security issue detected. Manual review is recommended.
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
Origin original 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 $0.00127 $0.01612
Opus 5 $0.00063 $0.00806
Sonnet 5 $0.00025 $0.00322
Haiku 4.5 $0.00013 $0.00161

Measured 10d ago against content hash 8d1386de5797, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

xpu-profile-unitrace 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 10d 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.

plugins/intel-gpu-ai-skills/skills/xpu-profile-unitrace/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

xpu-profile-unitrace

unitrace profiles XPU workloads at the SYCL / Level Zero kernel level — captures per-kernel timing, memcopy bytes, oneCCL/MPI events, and hardware counters that PyTorch profilers can't see.

Use when:

  • A PyTorch-level profiler identified a hot op and you need to know which SYCL kernel inside it is the cost.
  • You need Level Zero command-list events, oneCCL collectives, exact memcopy bytes, kernel launch geometry, or HW counters.
  • Multi-XPU run with per-rank oneCCL visibility needed.
  • Workload is raw SYCL / oneAPI (not PyTorch).

Prefer torch-xpu-profile or vllm-xpu-profile first; their output usually answers the question without going to SYCL level.

Install: check, then build if missing

command -v unitrace && unitrace --version

Most public XPU images don't ship unitrace. To build from source inside the target image:

source /opt/intel/oneapi/setvars.sh --force >/dev/null
git clone --depth 1 https://github.com/intel/pti-gpu.git /opt/pti-gpu
cd /opt/pti-gpu/tools/unitrace
mkdir build && cd build
cmake -DCMAKE_BUILD_TYPE=Release ..
make -j"$(nproc)"
export PATH="/opt/pti-gpu/tools/unitrace/build:$PATH"
unitrace --version          # confirm
unitrace --device-list      # confirm sees XPU

Prerequisites: CMake 3.22+, C++17 compiler, oneAPI Base Toolkit (present in vllm/vllm-openai-xpu:latest and any sglang-xpu image). Add -DBUILD_WITH_MPI=1 for multi-GPU collective profiling; -DCMAKE_INSTALL_PREFIX=/opt/unitrace && make install for an installable layout. Verified clean on vllm/vllm-openai-xpu:latest against unitrace 2.3.0.

If you profile often, bake this into a Dockerfile extending the runtime image so you don't rebuild every session.

Quickstart capture

cd /work       # working dir is where the trace lands
unitrace \
    --chrome-call-logging \
    --chrome-kernel-logging \
    python3 my_workload.py

Closing log lines name the exact paths:

[INFO] Log is stored in /work/python3.<PID>.json
[INFO] Timeline is stored in python3.<PID>.json

Read the full file on GitHub · 159 lines

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. 10d ago First seen · 159 lines · 127 tokens per session scan A 8d1386de5797

Subscribe to this mod's changes

xpu-profile-unitrace is a skill published in the GitHub repository intel/gpu-ai-skills (21 stars, last pushed 5d ago), licensed Apache-2.0. It adds 127 tokens to every session and 1,612 once invoked, about $0.0006 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 skills, from other repositories

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

hsb-flash

Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…

NVIDIA/skills · 94 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens