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.
Borrowing it
Nothing to install: this file belongs to intel/gpu-ai-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/intel/gpu-ai-skills/main/AGENTS.mdgit 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/instructions/intel/gpu-ai-skills/agents-md)<a href="https://agentmods.dev/instructions/intel/gpu-ai-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/intel/gpu-ai-skills/agents-md/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.
<a href="https://agentmods.dev/instructions/intel/gpu-ai-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/intel/gpu-ai-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00650 | $0.00650 |
| Opus 5.5 | $0.00260 | $0.00260 |
| Sonnet 5.5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade C, and why
gpu-ai-skills AGENTS.md scanned grade C with 1 finding 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -f` of unowned containers, or `rm -rf` outside a workspace path How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Contract
This file documents how a coding agent should consume this repository.
What this repo is
A pack of Agent Skills for
running, benchmarking, profiling, and fixing models on Intel GPUs.
Each skill is a self-contained directory under skills/.
How to discover skills
Read plugins/intel-gpu-ai-skills/skills/<skill>/SKILL.md. The YAML frontmatter has a name and a
description that tells you when to use it. Load the body when the
description matches the user's intent.
If the host agent supports the Claude Code plugin marketplace, prefer
that install path (.claude-plugin/marketplace.json). Otherwise copy
the skill directory into the agent's standard skills location.
What ships vs what is internal
research/ is an internal scratchpad used while authoring. It is
excluded from published archives via .gitattributes (export-ignore).
Skills must not reference paths under research/ — every claim a
skill makes has to be verifiable from public sources or from a
"verify locally" recipe inlined in the skill body.
Conventions in this repo
- Skill names are kebab-case and match the parent directory.
- Skills do not assume a specific orchestrator. They do not depend on Kintsugi, evidence bundles, or any private container runner.
- Skills assume Docker (or a Docker-compatible runtime) and
xpu-smion the host. Where a script needs more, the skill says so incompatibility. - All shell snippets are POSIX
shor explicitlybash. No fish syntax even though the host shell may be fish. - All Intel-specific knobs (image tags,
ZE_AFFINITY_MASK, dtype preferences) live in skills, not in tooling, so they stay current without code changes.
What this pack avoids
ipex-llm,intel-extension-for-pytorch,intel/llm-scaler-vllm. Upstream PyTorch and upstream vLLM are the supported paths.- Hardcoded container names. Skills accept a container name or image tag as input; they do not assume one is already running.
- Destructive operations. Nothing in this pack does
pkill,docker rm -fof unowned containers, orrm -rfoutside a workspace path the user provided.
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.
- 2mo ago First seen · 61 lines · 650 tokens per session scan C edfa4b532f4c
gpu-ai-skills AGENTS.md is an instructions file published in the GitHub repository intel/gpu-ai-skills (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 650 tokens to every session, about $0.0026 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
gpu-ai-skills AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gpu-ai-skills AGENTS.mdintel/gpu-ai-skills | Instructions file | 49 | yesterday | Apache-2.0 | C | 650 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |