xLSTM-metal: Instructions file for Codex

AGENTS.md

xLSTM-metal AGENTS.md is an instructions file for Codex, OpenCode from MLXPorts/xLSTM-metal. It costs 1,075 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for xLSTM-metal, an Apple Silicon machine-learning project using MLX and Metal acceleration. They describe the main files, tests, documentation, and production coding rules.

In plain words
What is it for?
Use them when developing or reviewing this repository, especially around its generation script, MLX/Metal implementation, tests, and documentation.
Why use it?
They guide agents toward the existing implementation and enforce rules such as avoiding fake production code and reusing code before rebuilding it.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is MLXPorts/xLSTM-metal's own configuration. It tells Codex and OpenCode how to work on xLSTM-metal 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 xLSTM-metal configures →

Reuse

Borrowing it

Nothing to install: this file belongs to MLXPorts/xLSTM-metal. 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/MLXPorts/xLSTM-metal/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/MLXPorts/xLSTM-metal

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.

agentmods badge for xLSTM-metal AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mlxports/xlstm-metal/agents-md/github.svg)](https://agentmods.dev/instructions/mlxports/xlstm-metal/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mlxports/xlstm-metal/agents-md"><img src="https://agentmods.dev/badge/instructions/mlxports/xlstm-metal/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.

agentmods 80×15 button for xLSTM-metal AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mlxports/xlstm-metal/agents-md"><img src="https://agentmods.dev/badge/instructions/mlxports/xlstm-metal/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,075 This file is loaded in full into every session.
When invoked 1,075 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01075 $0.01075
Opus 5 $0.00537 $0.00537
Sonnet 5 $0.00215 $0.00215
Haiku 4.5 $0.00108 $0.00108

Measured 10d ago against content hash b6b6ed2d9cf5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

xLSTM-metal 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 10d 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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent and Developer Guide

This repo implements xLSTM for Apple Silicon using MLX with Metal Accelerated Dispatch (MAD). These guidelines ensure production-safe development.

Quick Reference

Primary Entry Point: generate.py - Production runner using MLX backend
Core Implementation: xlstm_metal/ - MAD wiring, blocks, and inference
Tests: run_pytest.py - Test suite runner
Documentation: docs/ - Technical documentation by component

CLAUDE Guidance (Read Me First)

This repo runs on Apple Silicon with MLX-first compiled backends. These rules are strict so your help stays production-safe and useful.

Zero-Mock Policy (Production Code)

  • Don’t add mocks, stubs, or fake implementations to production paths. Use real implementations or leave TODOs in comments with precise next steps.
  • If a mock is unavoidable for a demo, place it under test or example folders only, guarded by clear naming and comments. Never wire a mock into default execution.

Always Reuse Before Rebuilding

  • Before implementing anything, search the repo for existing code:
    • rg -n "symbol|filename|keyword" to locate reuse targets.
    • Scan xlstm_metal/, scripts/, and docs/ for prior art and conventions.
  • Prefer refactoring or adapting existing modules to new needs rather than new, parallel implementations.
  • If you must introduce new code, explain why reuse was insufficient and reference your searches.

Lead With Vulnerability

  • Be explicit about what you don’t know or what isn’t working yet.
  • State assumptions and risks up front. Offer a short plan with checkpoints.
  • After changes, verify and report limits (“what this didn’t solve”).

Respect the Shell and Filesystem

  • Use OS tools for file ops; avoid dumping large files into the terminal:
    • Copy/rename: cp, mv (not read‑and‑reprint).
    • Search: rg (ripgrep) for speed and focus.
    • Inspect selectively: sed -n '1,200p' <file> (chunked views only).
  • Don’t stream giant artifacts or model weights to stdout. If you need to show something, quote only the relevant lines.

Read the full file on GitHub · 107 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. 10d ago First seen · 107 lines · 1,075 tokens per session scan A b6b6ed2d9cf5

Subscribe to this mod's changes

xLSTM-metal AGENTS.md is an instructions file published in the GitHub repository MLXPorts/xLSTM-metal (11 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,075 tokens to every session, about $0.0054 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

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

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

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