Apex AGENTS.md

A set of project instructions for coding agents working on Apex, a research system that trains agents to improve GPU code on AMD hardware.

In plain words
What is it for?
Use it when working in the Apex repository to understand its training and scoring workflow, supported AMD GPUs, environment setup, and read-only restrictions.
Why use it?
It gives the agent the required setup steps and project rules, including which environment to use and that the codebase must not be changed.

Instructions file for CodexOpenCode

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/amd-agi/apex/agents-md
Clone the repo
git clone --depth 1 https://github.com/AMD-AGI/Apex

Made for: Codex, OpenCode.

Per session 9,941 This file is loaded in full into every session.
When invoked 9,941 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5 $0.09941 $0.09941
Opus 5 $0.04970 $0.04970
Sonnet 5 $0.01988 $0.01988
Haiku 4.5 $0.00994 $0.00994

Measured 2d ago against content hash f773aacbea4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Apex 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 838 lines

How it starts

The opening of the file, as written. The whole thing — 838 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to the Codex agent when working with code in this repository.

Project Overview

Apex is an RL environment for GPU kernel optimization on AMD ROCm hardware. It trains LLM agents to optimize GPU kernels through a pipeline:

prompt constructor → LLM agent → output/ → grader (Magpie) → score

The agent receives a baseline kernel, writes an optimized version to output/<task_id>/solution.{py,hip}, and is scored on compilation (+20 pts), correctness (+100 pts), and speedup (×100 pts).

Default target: MI355X / gfx950 (CDNA4). Also supports gfx942 (MI300X), gfx940 (MI300A), gfx90a (MI250X).

Environment (always set first)

Ensure you are in the Apex repo root (the directory containing this AGENTS.md), then activate the venv and set MAGPIE_ROOT:

cd "$(dirname "$(readlink -f AGENTS.md)" 2>/dev/null || pwd)"
source .venv/bin/activate
export MAGPIE_ROOT=$(cd ../Magpie && pwd)

All commands below assume this working directory (APEX_ROOT).

CRITICAL: Read-Only Codebase

Do NOT modify any files in this repository or in the Magpie directory ($MAGPIE_ROOT). This includes:

  • This repo (Apex) — all .py, .sh, .md, .yaml files
  • The Magpie repo ($MAGPIE_ROOT) — all files including benchmark scripts
  • The Python virtual environment

You may only write to:

  • Your designated results directory (passed via -r)
  • Temporary directories under /tmp/
  • The output/<task_id>/ directories inside your results directory

If a benchmark script or pipeline step fails, do NOT patch the source code. Instead, work around it via environment variables, command-line flags, or report the issue.

GPU cleanup (only if needed)

Before launching a GPU workload, check if GPUs are free. Skip cleanup entirely if rocm-smi already shows ~0% VRAM on the target GPU(s).

Only if GPUs are busy, run:

pkill -9 -f 'vllm serve' 2>/dev/null
pkill -9 -f 'VLLM::EngineCore' 2>/dev/null
pkill -9 -f 'multiprocessing.resource_tracker' 2>/dev/null
sleep 3

Read the full file on GitHub · 838 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. 2d ago First seen · 838 lines · 9,941 tokens per session scan A f773aacbea4f

Subscribe to this mod's changes

Apex AGENTS.md is an instructions file published in the GitHub repository AMD-AGI/Apex (76 stars, last pushed 5d ago), licensed MIT. It adds 9,941 tokens to every session, about $0.0497 per session on Opus 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.

Related

Other instructions, from other repositories