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.
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.
npx agentmods add skills/intel/gpu-ai-skills/xpu-runtime-preflightnpx skills add intel/gpu-ai-skills --skill xpu-runtime-preflightgit clone --depth 1 https://github.com/intel/gpu-ai-skillsWrote 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.
[](https://agentmods.dev/skills/intel/gpu-ai-skills/xpu-runtime-preflight)<a href="https://agentmods.dev/skills/intel/gpu-ai-skills/xpu-runtime-preflight"><img src="https://agentmods.dev/badge/skills/intel/gpu-ai-skills/xpu-runtime-preflight.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00098 | $0.01371 |
| Opus 5 | $0.00049 | $0.00685 |
| Sonnet 5 | $0.00020 | $0.00274 |
| Haiku 4.5 | $0.00010 | $0.00137 |
Grade A, and why
xpu-runtime-preflight 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xpu-runtime-preflight
Use this as the shared readiness gate before Intel GPU/XPU skills in
this pack. It answers "is this host/container ready for the requested
skill path?", reports a READY / READY WITH WARNINGS / BLOCKED
verdict, and routes failures to focused skills. It does not start model
servers, run benchmarks, capture profiles, restart Docker, pull large
images, edit system configuration, or validate generated content.
When To Use
Run this before a model run, benchmark, profile, or container workflow
when readiness depends on more than GPU discovery. Use xpu-discover
for device inventory and driver health; use this skill for the broader
go/no-go path: /dev/dri, groups, Docker, shared memory, disk, proxy
and network checks, plus optional container XPU visibility.
If preflight finds a blocker, follow the generated SUMMARY.md handoff.
Do not duplicate routing guidance in this skill body.
Quick start
plugins/intel-gpu-ai-skills/skills/xpu-runtime-preflight/scripts/check_runtime_preflight.sh \
--target-gpu 0 \
--out-dir .out/skills/xpu-runtime-preflight
Add an already-local image when the next skill path runs in a container:
plugins/intel-gpu-ai-skills/skills/xpu-runtime-preflight/scripts/check_runtime_preflight.sh \
--target-gpu 0 \
--image <already-local-image>
When downloads or image builds are part of the next step, add a network check:
plugins/intel-gpu-ai-skills/skills/xpu-runtime-preflight/scripts/check_runtime_preflight.sh \
--env-file .env \
--target-gpu 0 \
--network-check
The script writes:
.out/skills/xpu-runtime-preflight/SUMMARY.md
.out/skills/xpu-runtime-preflight/status.tsv
.out/skills/xpu-runtime-preflight/preflight.log
It also writes per-check evidence files such as
xpu-smi-discovery.txt, xpu-smi-precheck.txt,
xpu-smi-diag-target.txt, xpu-smi-stats-target.txt,
target-driver.txt, dev-dri.txt, docker-info.txt, and, when
--image is supplied, image-preflight.txt.
What ships with it
1 file 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.
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.
- 5d ago First seen · 147 lines · 98 tokens per session scan A eadfd1ac23f8
xpu-runtime-preflight is a skill published in the GitHub repository intel/gpu-ai-skills (21 stars, last pushed today), licensed Apache-2.0. It adds 98 tokens to every session and 1,371 once invoked, about $0.0005 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.
Other skills, from other repositories
integrated-browser
Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under src/vs/platform/browserView and src/vs/workbench/contrib/browserView.
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…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
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…
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…
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…