What is strix-halo-guide AGENTS.md?

A guide for agents working on an evidence-based setup and benchmark project for AMD Strix Halo and Ryzen AI MAX+ 395 local AI systems.

Use it to assess new models, drivers, firmware, AI tools, regressions, fixes, reproducibility risks, and evidence needed for hardware recommendations.

It keeps technical updates tied to real setup, performance, compatibility, and buyer questions instead of unsupported benchmark claims.

How hogeheer499-commits/strix-halo-guide configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hogeheer499-commits/strix-halo-guide. 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/hogeheer499-commits/strix-halo-guide/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hogeheer499-commits/strix-halo-guide

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/hogeheer499-commits/strix-halo-guide/agents-md/github.svg)](https://agentmods.dev/instructions/hogeheer499-commits/strix-halo-guide/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hogeheer499-commits/strix-halo-guide/agents-md"><img src="https://agentmods.dev/badge/instructions/hogeheer499-commits/strix-halo-guide/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hogeheer499-commits/strix-halo-guide/agents-md"><img src="https://agentmods.dev/badge/instructions/hogeheer499-commits/strix-halo-guide/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,053 This file is loaded in full into every session.

When invoked 2,053 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.02053	$0.02053
Opus 5.5	$0.00821	$0.00821
Sonnet 5.5	$0.00411	$0.00411
Haiku 4.5	$0.00205	$0.00205

Measured 2mo ago against content hash 8ddb30b78a8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

strix-halo-guide AGENTS.md 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 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.

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.

AGENTS.md · 147 lines

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.

AGENTS.md

Operational instructions for Codex agents working in this repository.

Core Project Lens

strix-halo-guide is primarily an evidence-backed AMD Strix Halo / Ryzen AI MAX+ 395 local-AI setup and benchmark guide.

The project now also has a vendor / partner / sponsor-facing direction: benchmark work should show how the guide reduces adoption friction for AMD Strix Halo / Ryzen AI MAX+ local-AI hardware.

When the user asks "is er nieuws?", "updates?", "wat moeten we testen?", or anything similar, evaluate updates through two layers:

Technical value:
- new models
- new llama.cpp, Ollama, ROCm, Mesa, vLLM, driver, BIOS, or tooling changes
- benchmark regressions or improvements
- new blockers, fixes, or reproducibility risks
Adoption / commercial value:
- what buyer uncertainty does this remove?
- what setup friction does this reduce?
- what vendor/OEM/reviewer/product question does this answer?
- what evidence would make someone more confident buying, recommending, supporting, or reviewing the hardware?
- what missing hardware, firmware, driver support, vendor contact, or community data is needed to prove the next thing?

Higher t/s is useful, but it is not the only priority. Treat benchmarks as the proof layer and vendor/partner/sponsor docs as the leverage layer.

Documentation Style

Write in clear, professional English.
Keep the repo primarily useful to developers, buyers, and benchmark contributors.
Keep vendor-facing language credible, independent, and evidence-based.
Prefer links to existing evidence over duplicating long benchmark sections.
Use TODO placeholders for missing stats, contact details, quotes, traffic, sponsors, or evidence.
Preserve negative results, caveats, and failed paths.
Do not make the README feel like an advertisement.
Keep machine-specific workflow, local services, ports, account operations, and private maintainer procedures out of public docs.

Do-Not-Invent Rules

Read the full file on GitHub · 147 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.

2mo ago First seen · 147 lines · 2,053 tokens per session scan A 8ddb30b78a8a

Subscribe to this mod's changes

strix-halo-guide AGENTS.md is an instructions file published in the GitHub repository hogeheer499-commits/strix-halo-guide (369 stars, last pushed 16d ago), licensed MIT. It adds 2,053 tokens to every session, about $0.0082 per session on Opus 5.5. 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.

LLM amd benchmark gfx1151 llama-cpp local-llm

strix-halo-guide AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
strix-halo-guide AGENTS.mdhogeheer499-commits/strix-halo-guide	Instructions file	369	16d ago	MIT	A	2,053	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	today	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

strix-halo-guide: Instructions file for Codex