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/claude-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 | $0.10025 | $0.10025 |
| Opus 5 | $0.05012 | $0.05012 |
| Sonnet 5 | $0.02005 | $0.02005 |
| Haiku 4.5 | $0.01002 | $0.01002 |
Grade A, and why
Apex CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
95% identical to Apex AGENTS.md — 28 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 838 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Apex is an RL environment for GPU kernel optimization on AMD ROCm hardware. It trains LLM agents to optimize GPU kernels through a pipeline:
prompt constructor → LLM agent → output/ → grader (Magpie) → score
The agent receives a baseline kernel, writes an optimized version to output/<task_id>/solution.{py,hip}, and is scored on compilation (+20 pts), correctness (+100 pts), and speedup (×100 pts).
Default target: MI355X / gfx950 (CDNA4). Also supports gfx942 (MI300X), gfx940 (MI300A), gfx90a (MI250X).
Environment (always set first)
Ensure you are in the Apex repo root (the directory containing this CLAUDE.md), then activate the venv and set MAGPIE_ROOT:
cd "$(dirname "$(readlink -f CLAUDE.md)" 2>/dev/null || pwd)"
source .venv/bin/activate
export MAGPIE_ROOT=$(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.
- 3d ago First seen · 838 lines · 10,025 tokens per session scan A 5747bece1fd7
Apex CLAUDE.md is an instructions file published in the GitHub repository AMD-AGI/Apex (76 stars, last pushed 6d ago), licensed MIT. It adds 10,025 tokens to every session, about $0.0501 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to Apex AGENTS.md, differing in 28 lines, and is treated as a copy.
Other instructions, from other repositories
kernel-skills CLAUDE.md
Claude Code instructions for tensormux/kernel-skills, covering claude.md, kernel-skills, repository mission, what this repository is and product scope for v1.
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).
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.
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.
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.
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).