agentos: Instructions file for Codex

AGENTS.md

agentos AGENTS.md is an instructions file for Codex, OpenCode from jordanhubbard/agentos. It costs 1,057 tokens per session, scanned A, original, BSD-2-Clause.

Repository instructions for agentOS, a bare-metal operating system for AI agents built on the seL4 Microkit system.

In plain words
What is it for?
Use them when developing the operating system, its low-level components, or services that communicate through seL4 message passing.
Why use it?
They explain that the project is not Linux or a container system and set boundaries such as no human-facing interface in the repository.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; names the TodoWrite tool.

This is jordanhubbard/agentos's own configuration. It tells Codex and OpenCode how to work on agentos 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 agentos configures →

Reuse

Borrowing it

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

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 agentos AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jordanhubbard/agentos/agents-md"><img src="https://agentmods.dev/badge/instructions/jordanhubbard/agentos/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,057 This file is loaded in full into every session.
When invoked 1,057 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 $0.01057 $0.01057
Opus 5.5 $0.00423 $0.00423
Sonnet 5.5 $0.00211 $0.00211
Haiku 4.5 $0.00106 $0.00106

Measured 1mo ago against content hash ee0fbf8a83f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentos 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 1mo 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 · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agentOS — Agent Development Guidelines

Mandatory. Violations are rejected. Full constitution: CLAUDE.md. TCB: docs/TCB.md. Plan: PLAN.md.


What This Project Is

agentOS is a seL4 OS that owns devices in user mode and hosts Linux and FreeBSD as virtio guests. QEMU pretends to be a board. The real target is bare metal.

There is no POSIX userland. There is no "ring 1–5". seL4 is EL2. Our PDs are EL0. Guest kernels are EL1 and are hostile.

If you do not understand seL4 IPC and sDDF queues, read the seL4 Microkit manual and libvmm/dep/sddf/docs/network/network.md before writing I/O code.


The Rules

1. TCB first

Only PDs in docs/TCB.md may own a device frame or IRQ. Museum PDs listed there must not be extended.

2. No human UI here

No HTML, JavaScript, CSS, interactive terminal UI, or generated browser artifact belongs in this repository. External consumers may build UIs from the contracts; repository skills remain text-only.

3. C / Rust / ASM only

First-party target code, host tools, tests, and skill helpers use C, Rust, or Assembly. Python and other interpreted-language helpers are not exceptions.

4. Guests speak virtio that we emulate

Use libvmm virtio device backends (virtio_mmio_net_init, blk, console). Do not map QEMU virtio-mmio into the guest. Host virtio is for the driver PD.

5. Contracts before callers

Queue layout in platform/include/platform/. IPC in kernel/agentos-root-task/include/contracts/. Tests must assert outputs.

6. Make is the interface

If a Makefile rule exists, use it (make build, make test, make gate).


How to Add I/O (the only new "PD" path that matters)

  1. Driver PD owns the physical (or QEMU-stand-in) device.
  2. Virtualizer PD muxes sDDF queues to N clients.
  3. VMM calls libvmm virtio_mmio_*_init at a guest IPA that faults.
  4. Guest DTB describes that emulated device, not the host MMIO.
  5. Host test for the pump/mux; QEMU test that the guest sees the device.

Read the full file on GitHub · 128 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. 1mo ago Changed · +1 lines · +2 tokens per session ee0fbf8a83f5
  2. 1mo ago Changed · -243 lines · -2,579 tokens per session be1ba51daba1
  3. 1mo ago First seen · 370 lines · 3,634 tokens per session scan A bbfc0eae87fd

Subscribe to this mod's changes

agentos AGENTS.md is an instructions file published in the GitHub repository jordanhubbard/agentos (53 stars, last pushed 8d ago), licensed BSD-2-Clause. It adds 1,057 tokens to every session, about $0.0042 per session on Opus 5.5. 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 · 9,715 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 · 7,581 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens