What is rax AGENTS.md?

Project instructions for developing rax, including rules about instruction priority, technical rigor, and how the coding agent should operate.

Use them when an agent is planning, changing, reviewing, or explaining work in rax.

They provide the agent with the repository's engineering expectations and a way to resolve conflicting guidance.

How HexRaysSA/rax configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to HexRaysSA/rax. 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/HexRaysSA/rax/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/HexRaysSA/rax

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hexrayssa/rax/agents-md/github.svg)](https://agentmods.dev/instructions/hexrayssa/rax/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hexrayssa/rax/agents-md"><img src="https://agentmods.dev/badge/instructions/hexrayssa/rax/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hexrayssa/rax/agents-md"><img src="https://agentmods.dev/badge/instructions/hexrayssa/rax/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16,144 This file is loaded in full into every session.

When invoked 16,144 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.

Model	Per session	Once invoked
Fable 5.1	$0.16144	$0.16144
Opus 5.5	$0.06458	$0.06458
Sonnet 5.5	$0.03229	$0.03229
Haiku 4.5	$0.01614	$0.01614

Measured 18d ago against content hash 7c9a77d3ef71, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rax 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 18d 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 · 1,354 lines

How it starts

The opening of the file, as written. The whole thing — 1,354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAX Agent Engineering Guide

1. Purpose and scope

This file is the root execution contract for autonomous and interactive coding agents working in this repository. It applies to the entire tree unless a deeper AGENTS.md supplies more specific instructions. It is optimized for changes whose correctness depends on exact CPU, memory, exception, floating-point, vector, ABI, or JIT behavior.

RAX is a Rust 2024 multi-ISA emulator and virtual-machine monitor. Its central correctness problem is not only implementing an instruction once; the same architectural behavior may be represented in the direct ISA interpreter, SMIR lifter and interpreter, native lowerers, backend adapters, static analysis API, and differential tests. An agent must identify every affected representation.

Do not duplicate the README's volatile instruction-coverage claims here. For current advertised capabilities, consult README.md; for implementation truth, inspect source and executable tests.

2. Instruction priority and truth hierarchy

Apply instructions in this order:

System, developer, and current user instructions.
The nearest applicable AGENTS.md.
Repository configuration and executable behavior.
Current source and tests.
Current CI workflow definitions.
Derived design documents and historical reports.
Comments, issue prose, and names.

When sources disagree, do not silently select the convenient one. Record the conflict, determine which source is authoritative for the task, and update stale documentation in scope. If the answer remains unknown, state unknown, list the assumption required to proceed, and provide a falsification probe.

Repository-specific examples:

Cargo.toml is authoritative for feature names and Cargo test targets.
.github/workflows/*.yml is authoritative for current CI commands.
src/lib.rs and src/README.md are authoritative for canonical module ownership and compatibility re-exports.
Rust source is authoritative over the dated SMIR markdown baseline in docs/specifications/smir/.
ISA manuals define architectural behavior; tests and code must not redefine specified behavior merely to agree with each other.
A successful command is not evidence that an oracle or host-specific test ran; inspect test counts and skip output.

Read the full file on GitHub · 1,354 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.

18d ago Changed · +26 lines · +499 tokens per session 7c9a77d3ef71
22d ago Changed · +39 lines · +902 tokens per session 2f2a10fb8488
23d ago Changed · +203 lines · +2,679 tokens per session 081b535f03b3
1mo ago Changed · +4 lines · +167 tokens per session c0515daf03cd
1mo ago Changed · +3 lines · +42 tokens per session 39c14cc42595
2mo ago First seen · 1,079 lines · 11,855 tokens per session scan A 56053156e5fa

Subscribe to this mod's changes

rax AGENTS.md is an instructions file published in the GitHub repository HexRaysSA/rax (240 stars, last pushed today), licensed MIT. It adds 16,144 tokens to every session, about $0.0646 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.

rax AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rax AGENTS.mdHexRaysSA/rax	Instructions file	240	today	MIT	A	16,144	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

rax: Instructions file for Codex