roundhouse: Instructions file for Codex

AGENTS.md

roundhouse AGENTS.md is an instructions file for Codex, OpenCode from rubys/roundhouse. It costs 1,647 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Roundhouse, a tool that reads Ruby on Rails code and produces projects in other programming languages, along with code-understanding tools.

In plain words
What is it for?
Use them when working on Roundhouse’s compiler pipeline, generated-language targets, Rails inputs, inference tools, or contributor workflow.
Why use it?
They help contributors find the authoritative project status, understand the development workflow, and avoid breaking important design rules.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

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 roundhouse AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rubys/roundhouse/agents-md"><img src="https://agentmods.dev/badge/instructions/rubys/roundhouse/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,647 This file is loaded in full into every session.
When invoked 1,647 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 $0.01647 $0.01647
Opus 5.5 $0.00659 $0.00659
Sonnet 5.5 $0.00329 $0.00329
Haiku 4.5 $0.00165 $0.00165

Measured 5d ago against content hash eaa668c6e49e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

roundhouse 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 5d 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 · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working on Roundhouse (agents & contributors)

Roundhouse reads Rails source and emits standalone projects in ~12 target languages, plus an inference engine (LSP/MCP/in-browser IDE) that types Rails without annotations. This file is the orientation an AI agent or new contributor needs before touching the code: where to look, and the invariants not to break.

Current implementation and executed CI are authoritative for behavior. RELEASES.md records dated snapshot claims, not a live main status page. The user guide describes product usage; the bench page carries measurements.

Start here

You want… Read
What the project is README.md — the landing page
Release snapshots and their known gaps RELEASES.md
Using it (check / editor / MCP / transpile / Spinel) docs/guide/
Set up a checkout docs/development/README.md
Choose tests or use bin/rh verify docs/development/testing.md
Inspect AST, IR, or emitted output docs/development/debugging.md
Change IR, lowering, runtime, or an emitter docs/development/compiler-changes.md
Read/request hosted checks docs/ci/README.md
Pipeline internals (analyze / lower / specialization / emit / runtime / verification) docs/pipeline/ — architecture, not status
Compiler inputs (Ruby+ERB, schema/routes/seeds, method catalog, DB adapter) docs/data/
Why do this at all (the argument, option value) WHY.md
Why this attempt is different (lineage, the three bets, risks) BETS.md

Pipeline shape: Ruby AST → analyze (typed IR) → lower (target-neutral IR) → emit (per-target project + runtime/<target>/ glue). The ownership map locates each stage.

Read the full file on GitHub · 113 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. 5d ago Changed · -2 tokens per session eaa668c6e49e
  2. 15d ago Changed · +8 lines · +148 tokens per session 991afd90dce3
  3. 25d ago Changed · +2 tokens per session 877f68bf0a57
  4. 1mo ago Changed · -27 lines · -460 tokens per session 6118c080f2df
  5. 1mo ago Changed · +7 lines · +112 tokens per session d9598684b600
  6. 1mo ago Changed · +16 lines · +246 tokens per session e209d2a07e47
  7. 1mo ago Changed · +16 lines · +264 tokens per session 7efec74ac670
  8. 1mo ago Changed · +5 lines · +117 tokens per session d59948050369
  9. 2mo ago First seen · 88 lines · 1,220 tokens per session scan A fc82d5562116

Subscribe to this mod's changes

roundhouse AGENTS.md is an instructions file published in the GitHub repository rubys/roundhouse (517 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,647 tokens to every session, about $0.0066 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

roundhouse AGENTS.md compared with instructions from other repositories

roundhouse AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
roundhouse AGENTS.mdrubys/roundhouseInstructions file5175d agoApache-2.0A1,647Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode