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/amd-agi/apex/agents-mdgit clone --depth 1 https://github.com/AMD-AGI/ApexWhat 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 | $0.09941 | $0.09941 |
| Opus 5 | $0.04970 | $0.04970 |
| Sonnet 5 | $0.01988 | $0.01988 |
| Haiku 4.5 | $0.00994 | $0.00994 |
Grade A, and why
Apex AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- Apex CLAUDE.md — 95% identical, 28 lines differ
How it starts
The opening of the file, as written. The whole thing — 838 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to the Codex agent when working with code in this repository.
Project Overview
Apex is an RL environment for GPU kernel optimization on AMD ROCm hardware. It trains LLM agents to optimize GPU kernels through a pipeline:
prompt constructor → LLM agent → output/ → grader (Magpie) → score
The agent receives a baseline kernel, writes an optimized version to output/<task_id>/solution.{py,hip}, and is scored on compilation (+20 pts), correctness (+100 pts), and speedup (×100 pts).
Default target: MI355X / gfx950 (CDNA4). Also supports gfx942 (MI300X), gfx940 (MI300A), gfx90a (MI250X).
Environment (always set first)
Ensure you are in the Apex repo root (the directory containing this AGENTS.md), then activate the venv and set MAGPIE_ROOT:
cd "$(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,.yamlfiles - 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
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.
- 2d ago First seen · 838 lines · 9,941 tokens per session scan A f773aacbea4f
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.
Other instructions, from other repositories
statsclaw CLAUDE.md
Instructions for statsclaw/statsclaw, a project described as: A workflow framework for statistical package development.
bio-gene-to-reference-tree copilot-instructions.md
Instructions for Hongda-Zhao/bio-gene-to-reference-tree, a project described as: Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.
scholar-agent copilot-instructions.md
Instructions for zfy465914233/scholar-agent, covering global instructions, project context, core constraints, output principles and evidence handling.
gpu-ai-skills CLAUDE.md
Instructions for intel/gpu-ai-skills, covering claude.md, what this repository is, repository structure, commands and validation (required before any skill change).
braina GEMINI.md
Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.
research-automation CLAUDE.md
Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.