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 instructions/intel/gpu-ai-skills/claude-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/claude-md)<a href="https://agentmods.dev/instructions/intel/gpu-ai-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/intel/gpu-ai-skills/claude-md.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 | $0.01541 | $0.01541 |
| Opus 5 | $0.00771 | $0.00771 |
| Sonnet 5 | $0.00308 | $0.00308 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade C, and why
gpu-ai-skills CLAUDE.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 4d 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.
- No `pkill`, `docker rm -f` of unowned containers, `rm -rf` outside workspace How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repository is
A collection of Agent Skills for running, benchmarking, and profiling arbitrary Hugging Face safetensors models on Intel GPUs (Arc, Arc Pro, Battlemage, Data Center GPU Max). Covers PyTorch + Transformers, vLLM-XPU, and SGLang-XPU stacks.
The skills follow the Agent Skills standard and work with any compliant agent (Claude Code, opencode, Cursor, GitHub Copilot CLI, Gemini CLI, Qwen Code, Kimi Code, Hermes Agent, OpenClaw).
Repository structure
plugins/intel-gpu-ai-skills/skills/ # One directory per skill
<skill-name>/
SKILL.md # Skill definition (required)
scripts/ # Helper scripts referenced by SKILL.md
data/ # Supporting data files
scripts/ # Repo tooling (install, validation)
agents/ # Generated AGENTS.md bundle
tests/ # Static validation suite
template/ # SKILL.md template for contributors
.claude-plugin/ # Claude Code plugin marketplace manifests
.cursor-plugin/ # Cursor plugin manifests
Commands
Validation (required before any skill change)
# Run full static validation suite
bash tests/static.sh
# Run repo checker + external skill-validator (if installed)
bash scripts/check-skills.sh
# External validator (optional)
# install: https://github.com/agent-ecosystem/skill-validator
The static gate validates:
- JSON manifests parse correctly
- Every SKILL.md has
nameanddescriptionfrontmatter - Skill name matches parent directory (Agent Skills spec requirement)
- Python helpers compile
- Shell scripts parse
agents/AGENTS.mdis in sync with generator- Claude marketplace entries cover every skill
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.
- 4d ago First seen · 176 lines · 1,541 tokens per session scan C 24e0a1958e10
gpu-ai-skills CLAUDE.md is an instructions file published in the GitHub repository intel/gpu-ai-skills (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,541 tokens to every session, about $0.0077 per session on Opus 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.