VibeOS CLAUDE.md

VibeOS CLAUDE.md is an instructions file for Claude Code from kaansenol5/VibeOS. It costs 4,883 tokens per session, scanned A, original, MIT.

Project instructions for VibeOS, a hobby operating system built from scratch for ARM64 computers and tested in QEMU, a program that emulates a computer. They describe its design, current state, and rules for working on it.

In plain words
What is it for?
Understanding the operating system’s architecture, checking what is already implemented, and following its build and run workflow.
Why use it?
They give the coding agent the project context and firm working rules, reducing the risk of using the wrong build steps or changing the project’s intended direction.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

About the project

VibeOS is a hobby operating system written from scratch for ARM64 computers, including QEMU and Raspberry Pi Zero 2W. It is for exploring operating-system development through a custom kernel, desktop, networking, and built-in applications, and the catalogue instruction relates to working with the project.

kaansenol5/VibeOS · 1,527 stars · on GitHub

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/kaansenol5/vibeos/claude-md
Clone the repo
git clone --depth 1 https://github.com/kaansenol5/VibeOS

Made for: Claude Code.

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 VibeOS CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kaansenol5/vibeos/claude-md.svg)](https://agentmods.dev/instructions/kaansenol5/vibeos/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kaansenol5/vibeos/claude-md"><img src="https://agentmods.dev/badge/instructions/kaansenol5/vibeos/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,883 This file is loaded in full into every session.
When invoked 4,883 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 5.1 $0.04883 $0.04883
Opus 5 $0.02441 $0.02441
Sonnet 5 $0.00977 $0.00977
Haiku 4.5 $0.00488 $0.00488

Measured 6d ago against content hash 53e96db2e813, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

VibeOS 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 6d 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.

CLAUDE.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeOS - Claude Context

IMPORTANT DISK RULES:

  • Never look at the disk
  • The disk always works
  • make run is the only way to compile and run the code - the user will run it
  • Trust make run - the user will tell you if it is broken
  • Do NOT use hdiutil for anything

Project Overview

VibeOS is a hobby operating system built from scratch for aarch64 (ARM64), targeting QEMU's virt machine. This is a science experiment to see what an LLM can build.

The Vibe

  • Aesthetic: Modern macOS-inspired (draggable windows, dock, menu bar)
  • Philosophy: Simple, educational, nostalgic
  • NOT trying to be: Linux, production-ready, or modern

Current State (Last Updated: Session 40)

  • Bootloader (boot/boot.S) - Sets up stack, clears BSS, jumps to kernel
  • Minimal kernel (kernel/kernel.c) - UART output working
  • Linker script (linker.ld) - Memory layout for QEMU virt
  • Makefile - Builds and runs in QEMU
  • Boots successfully! Prints to serial console.
  • Memory management (kernel/memory.c) - malloc/free working, dynamic heap sizing
  • DTB parsing (kernel/dtb.c) - Detects RAM size at runtime from Device Tree
  • String functions (kernel/string.c) - memcpy, strlen, strcmp, strtok_r, etc.
  • Printf (kernel/printf.c) - %d, %s, %x, %p working
  • Framebuffer (kernel/fb.c) - ramfb device, 800x600
  • Bitmap font (kernel/font.c) - 8x16 VGA-style font
  • Console (kernel/console.c) - Text console with colors on screen
  • Virtio keyboard (kernel/keyboard.c) - Full keyboard with shift support
  • Shell (kernel/shell.c) - In-kernel shell with commands
  • VFS (kernel/vfs.c) - Now backed by FAT32, falls back to in-memory
  • Coreutils - ls, cd, pwd, mkdir, touch, rm, cat, echo (with > redirect)
  • ELF loader (kernel/elf.c) - Loads PIE binaries with full relocation support
  • Process management (kernel/process.c) - Process table, context switching, scheduler
  • Cooperative multitasking - yield(), spawn() in kapi, round-robin scheduler
  • Kernel API (kernel/kapi.c) - Function pointers for programs to call kernel
  • Text editor (kernel/vi.c) - Modal vi clone with normal/insert/command modes
  • Virtio block device (kernel/virtio_blk.c) - Read/write disk sectors
  • FAT32 filesystem (kernel/fat32.c) - Read/write, full LFN (long filename) support
  • Persistent storage - 64MB FAT32 disk image, mountable on macOS
  • Interrupts - GIC-400 working! Keyboard via IRQ, boots at EL3 (Secure)
  • Timer - 10ms tick (100Hz), used for uptime tracking
  • System Monitor - GUI app showing uptime and memory usage
  • TextEdit - GUI text editor with Save As modal
  • RTC - PL031 real-time clock at 0x09010000, shows actual date/time
  • Date command - /bin/date shows current UTC date/time
  • Menu bar - Apple menu with About/Quit, File menu, Edit menu
  • About dialog - Shows VibeOS version, memory, uptime
  • Power management - WFI-based idle, mouse interrupt-driven, 100Hz UI refresh
  • Virtio Sound - Audio playback via virtio-sound device, WAV and MP3 support
  • Music Player - GUI music player with album/track browser, pause/resume, progress bar
  • Floating point - FPU enabled, context switch saves/restores FP regs, calc uses doubles
  • Networking - virtio-net driver, Ethernet, ARP, IP, ICMP working!
  • Ping command - /bin/ping can ping internet hosts (1.1.1.1, etc.)
  • UDP + DNS - hostname resolution via QEMU's DNS server (10.0.2.3)
  • TCP - full TCP state machine with 3-way handshake, send/recv, close
  • HTTP client - /bin/fetch can make HTTP requests to real websites!
  • Web Browser - /bin/browser GUI browser with HTML rendering, works on HTTP sites
  • TLS 1.2 - Full HTTPS support via TLSe library, ECC key exchange working!
  • HTTPS client - /bin/fetch can make HTTPS requests to google.com, etc!
  • Raspberry Pi Zero 2W support - boots on real hardware!
  • Pi SD card (EMMC) driver - FAT32 filesystem works, userspace runs!
  • Pi USB host (DWC2) - Device enumeration working, HID keyboard via hub works!

Read the full file on GitHub · 261 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. 6d ago First seen · 261 lines · 4,883 tokens per session scan A 53e96db2e813

Subscribe to this mod's changes

VibeOS CLAUDE.md is an instructions file published in the GitHub repository kaansenol5/VibeOS (1,527 stars, last pushed 7mo ago), licensed MIT. It adds 4,883 tokens to every session, about $0.0244 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

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

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 · 5,182 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

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

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

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