agentos CLAUDE.md

agentos CLAUDE.md is an instructions file for coding agents from jordanhubbard/agentos. It costs 1,629 tokens per session, scanned A, original, BSD-2-Clause.

A repository rulebook for AI coding agents working on agentOS, a secure operating system built on the seL4 microkernel. It defines the project’s purpose, allowed languages, and non-negotiable rules.

In plain words
What is it for?
Use it before changing, deleting, or proposing code in the agentOS repository. It guides decisions about the operating system, its security model, and permitted technologies.
Why use it?
It prevents agents from misunderstanding the project or proposing code that conflicts with its architecture and language policy.

Instructions file

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/jordanhubbard/agentos/claude-md
Clone the repo
git clone --depth 1 https://github.com/jordanhubbard/agentos

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 agentos CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jordanhubbard/agentos/claude-md.svg)](https://agentmods.dev/instructions/jordanhubbard/agentos/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jordanhubbard/agentos/claude-md"><img src="https://agentmods.dev/badge/instructions/jordanhubbard/agentos/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,629 This file is loaded in full into every session.
When invoked 1,629 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 $0.01629 $0.01629
Opus 5 $0.00814 $0.00814
Sonnet 5 $0.00326 $0.00326
Haiku 4.5 $0.00163 $0.00163

Measured yesterday against content hash 491b5355186a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agentos 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 yesterday.

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 · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentOS — Project Constitution for AI Agents

This document is binding. Read docs/TCB.md first. Do not make exceptions.


What agentOS Is

agentOS is a bootable, capability-secured operating system on the seL4 microkernel. It is the I/O and isolation platform for:

  • Linux and FreeBSD as guests (in-tree virtio drivers only)
  • Native purpose-driven PDs / agents that never run a legacy OS

QEMU is a hardware emulator for fast prototyping. The same driver PDs that own QEMU virtio-mmio as a stand-in NIC/disk will own real devices on bare metal.

agentOS is not a thin hypervisor slave to QEMU. It is not a web app. It is not a dashboard. It boots on bare metal.


Trusted Computing Base

See docs/TCB.md. Short form:

  • seL4 is the only kernel-mode code. Never modify it.
  • Root task distributes untyped memory, CSpace, VSpace, and initial caps. It does not enforce policy after spawn.
  • Driver PDs own exactly one device class (frame + IRQ).
  • Virtualizer PDs mux that class over sDDF-shaped shared-memory queues.
  • VMM PDs run vCPUs/vGIC and emulate virtio for guests.
  • Everyone else is a client or is quarantined (docs/TCB.md museum list).

There is no "Ring 1–5". Those numbers mixed Intel rings with ARM ELs with seL4 PDs and were wrong. Guest userspace runs in the guest VSpace.


Language Policy

On-target (PDs, libvmm backends, root task)

C, Rust, Assembly only. Freestanding. No Python runtime in a PD. No JavaScript. No Go, Zig, or other languages unless the project owner approves in writing.

Host composition (skills/, tools/)

Python is required for skill helpers and generators. Helpers must stay small: they compute (graphs, DTB/ELF/virtio inspection, topology) and print HTML (or another structured dump) for LLM agents. That HTML is not a product UI and must not be served by any PD.

CMake / Make orchestrate builds. Shell is CI glue and one-line wrappers.

WASM is a guest/agent binary format only. WASM runtime is C or Rust. WASM is not a NIC, disk, or UART.

Read the full file on GitHub · 190 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. yesterday Changed · -96 lines · -2,075 tokens per session 491b5355186a
  2. 5d ago First seen · 286 lines · 3,704 tokens per session scan A c3cbbdf08fe4

Subscribe to this mod's changes

agentos CLAUDE.md is an instructions file published in the GitHub repository jordanhubbard/agentos (25 stars, last pushed today), licensed BSD-2-Clause. It adds 1,629 tokens to every session, about $0.0081 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

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 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

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

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