What is gpu-ai-skills AGENTS.md?

Project instructions for Intel GPU AI Skills, a collection of focused guides for running, benchmarking, profiling, and fixing models on Intel graphics processors. Each skill is stored in its own directory and is selected based on the user's request.

Use it when working with AI models on Intel GPUs, especially for execution, performance measurement, profiling, or troubleshooting, and when maintaining the skill repository.

It explains how an agent should discover the right GPU guide and distinguishes published material from internal research files.

gpu-ai-skills AGENTS.md — Instructions file for Codex and OpenCode by intel: Project instructions for Intel GPU AI Skills, a collection…

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.

agentmods

npx agentmods add instructions/intel/gpu-ai-skills/agents-md

Clone the repo

git clone --depth 1 https://github.com/intel/gpu-ai-skills

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/intel/gpu-ai-skills/agents-md.svg)](https://agentmods.dev/instructions/intel/gpu-ai-skills/agents-md)

Your own site

<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="Measured on agentmods" height="20"></a>

Per session 650 This file is loaded in full into every session.

When invoked 650 The same file — it is already loaded in full.

Security scan C 1 finding. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00650	$0.00650
Opus 5	$0.00325	$0.00325
Sonnet 5	$0.00130	$0.00130
Haiku 4.5	$0.00065	$0.00065

Measured 4d ago against content hash edfa4b532f4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

rm -f` of unowned containers, or `rm -rf` outside a workspace path

AGENTS.md · 61 lines

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-smi on the host. Where a script needs more, the skill says so in compatibility.
All shell snippets are POSIX sh or explicitly bash. 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 -f of unowned containers, or rm -rf outside a workspace path the user provided.

Read the full file on GitHub · 61 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.

4d ago First seen · 61 lines · 650 tokens per session scan C edfa4b532f4c

Subscribe to this mod's changes

gpu-ai-skills AGENTS.md is an instructions file published in the GitHub repository intel/gpu-ai-skills (16 stars, last pushed 7d ago), licensed Apache-2.0. It adds 650 tokens to every session, about $0.0032 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.

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).

microsoft/vscode · 6,785 tokens

gpu-ai-skills AGENTS.md