strix-halo-gmktec-evo-x2: Instructions file for Claude Code

CLAUDE.md

strix-halo-gmktec-evo-x2 CLAUDE.md is an instructions file for Claude Code from pablo-ross/strix-halo-gmktec-evo-x2. It costs 5,547 tokens per session, scanned B, original, MIT.

Repository instructions for Claude Code, covering a specific Ubuntu computer and its setup for running large language models with llama.cpp and AMD software.

In plain words
What is it for?
Use them when configuring the system, following kernel and software requirements, or understanding how its shared CPU and graphics memory is used.
Why use it?
They give the coding agent the hardware details and setup requirements needed to work safely and correctly in that repository.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; built for continue.dev.

This is pablo-ross/strix-halo-gmktec-evo-x2's own configuration. It tells Claude Code how to work on strix-halo-gmktec-evo-x2 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything strix-halo-gmktec-evo-x2 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pablo-ross/strix-halo-gmktec-evo-x2. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pablo-ross/strix-halo-gmktec-evo-x2/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/pablo-ross/strix-halo-gmktec-evo-x2

Made for: Claude Code.

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 strix-halo-gmktec-evo-x2 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pablo-ross/strix-halo-gmktec-evo-x2/claude-md/github.svg)](https://agentmods.dev/instructions/pablo-ross/strix-halo-gmktec-evo-x2/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pablo-ross/strix-halo-gmktec-evo-x2/claude-md"><img src="https://agentmods.dev/badge/instructions/pablo-ross/strix-halo-gmktec-evo-x2/claude-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.

agentmods 80×15 button for strix-halo-gmktec-evo-x2 CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pablo-ross/strix-halo-gmktec-evo-x2/claude-md"><img src="https://agentmods.dev/badge/instructions/pablo-ross/strix-halo-gmktec-evo-x2/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,547 This file is loaded in full into every session.
When invoked 5,547 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.05547 $0.05547
Opus 5 $0.02773 $0.02773
Sonnet 5 $0.01109 $0.01109
Haiku 4.5 $0.00555 $0.00555

Measured 11d ago against content hash 9a39b65540d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

strix-halo-gmktec-evo-x2 CLAUDE.md scanned grade B 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 11d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt install rocm-hip-runtime-dev hipblas-dev
CLAUDE.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 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.

Repository Overview

This repository contains setup guides and configuration documentation for optimizing Ubuntu 24.04 on the GMKTEC EVO-X2 (AMD Ryzen AI Max+ 395 with Radeon 8060S) for LLM inference using llama.cpp with ROCm 7 RC and rocWMMA.

Hardware Context

Target System:

  • CPU: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S (32 threads)
  • GPU: AMD Radeon Graphics (gfx1151, RDNA 3.5, 40 CUs, Strix Halo)
  • RAM: 124 GiB system memory
  • GPU Memory: 1 GB VRAM (framebuffer) + 128 GB GTT (unified compute memory)

Critical Understanding: For this APU, GTT (Graphics Translation Table) is the primary compute memory pool for LLM inference, not VRAM. The system has ~120GB available for inference workloads.

Key Setup Steps Reference

System Configuration (from ROADMAP.md)

Kernel Requirements:

  • Minimum: Linux 6.16.9 (critical for >15GB VRAM access)
  • Current: 6.17.0-1028-oem

Note: Kernel 6.17 broke the KFD kernel/userspace ABI against the ROCm 7.0-rc HSA runtime used by the old distrobox container below, causing llama-server to segfault in libhsa-runtime64.so (see LLAMA_ISSUES_SUMMARY.md). The fix was to move off distrobox and run ROCm 7.2 + llama.cpp natively on the host (see "Building and Running llama.cpp" below), which matches the host kernel's KFD ABI.

Essential Kernel Parameters:

amd_iommu=off amdgpu.gttsize=131072 ttm.pages_limit=31457280

Critical Modprobe Configuration (/etc/modprobe.d/amdgpu_llm_optimized.conf):

options amdgpu gttsize=122800
options ttm pages_limit=31457280
options ttm page_pool_size=31457280

GPU Access (Ubuntu-specific): Must create udev rules in /etc/udev/rules.d/99-amd-kfd.rules:

SUBSYSTEM=="kfd", GROUP="render", MODE="0666", OPTIONS+="last_rule"
SUBSYSTEM=="drm", KERNEL=="card[0-9]*", GROUP="render", MODE="0666", OPTIONS+="last_rule"
SUBSYSTEM=="drm", KERNEL=="renderD[0-9]*", GROUP="render", MODE="0666", OPTIONS+="last_rule"

The renderD[0-9]* rule is critical - without it, ROCm will fail with HSA_STATUS_ERROR_OUT_OF_RESOURCES.

Read the full file on GitHub · 372 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. 11d ago First seen · 372 lines · 5,547 tokens per session scan B 9a39b65540d1

Subscribe to this mod's changes

strix-halo-gmktec-evo-x2 CLAUDE.md is an instructions file published in the GitHub repository pablo-ross/strix-halo-gmktec-evo-x2 (100 stars, last pushed 22d ago), licensed MIT. It adds 5,547 tokens to every session, about $0.0277 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens