design-os: Instructions file for Codex

AGENTS.md

design-os AGENTS.md is an instructions file for Codex, OpenCode from buildermethods/design-os. It costs 2,035 tokens per session, scanned A, original, MIT.

Instructions for working in Design OS, a planning tool for defining a product, shaping its data, designing screens, and preparing files for implementation. It explains the difference between the planning application and the product being designed.

In plain words
What is it for?
Use it when editing Design OS, creating product screen designs, updating product definitions, or preparing implementation exports.
Why use it?
It prevents changes intended for the planned product from being confused with changes to the Design OS application itself.

Instructions file for CodexOpenCode

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

This is buildermethods/design-os's own configuration. It tells Codex and OpenCode how to work on design-os 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 design-os configures →

About the project

Design OS is a product-planning and interface-design tool that guides an idea through product definition, data modeling, design-system choices, screen design, and implementation handoff. Teams use it to give coding agents a clear specification before development begins. Its catalogue add-ons support the guided planning and design workflow.

buildermethods/design-os · 1,876 stars · on GitHub

Reuse

Borrowing it

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

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 design-os AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/buildermethods/design-os/agents-md"><img src="https://agentmods.dev/badge/instructions/buildermethods/design-os/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,035 This file is loaded in full into every session.
When invoked 2,035 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 $0.02035 $0.02035
Opus 5.5 $0.00814 $0.00814
Sonnet 5.5 $0.00407 $0.00407
Haiku 4.5 $0.00203 $0.00203

Measured 2mo ago against content hash eca2f3bb640d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-os 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 2mo 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 · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Directives for Design OS

Design OS is a product planning and design tool that helps users define their product vision, sketch out their data shape, design their UI, and prepare export packages for implementation in a separate codebase.

Important: Design OS is a planning tool, not the end product codebase. The screen designs and components generated here are meant to be exported and integrated into your actual product's codebase.


Understanding Design OS Context

When working in Design OS, be aware of two distinct contexts:

1. Design OS Application

The React application that displays and manages planning files. When modifying the Design OS UI itself:

  • Files live in src/ (components, pages, utilities)
  • Uses the Design OS design system (stone palette, DM Sans, etc.)
  • Provides the interface for viewing specs, screen designs, exports, etc.

2. Product Design (Screen Designs & Exports)

The product you're planning and designing. When creating screen designs and exports:

  • Screen design components live in src/sections/[section-name]/ and src/shell/
  • Product definition files live in product/
  • Exports are packaged to product-plan/ for integration into a separate codebase
  • Follow the design requirements specified in each section's spec

Getting Started — The Planning Flow

Design OS follows a structured planning sequence:

1. Product Vision (/product-vision)

Define your product overview, roadmap sections, and data shape — all in one conversational flow. After answering clarifying questions, all three files are generated automatically. Output: product/product-overview.md, product/product-roadmap.md, product/data-shape/data-shape.md

Use /product-roadmap, /data-shape individually to update those files after initial creation.

2. Design System (/design-tokens)

Choose your color palette (from Tailwind) and typography (from Google Fonts). These tokens are applied to all screen designs. Output: product/design-system/colors.json, product/design-system/typography.json

Read the full file on GitHub · 213 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. 2mo ago First seen · 213 lines · 2,035 tokens per session scan A eca2f3bb640d

Subscribe to this mod's changes

design-os AGENTS.md is an instructions file published in the GitHub repository buildermethods/design-os (1,876 stars, last pushed 1mo ago), licensed MIT. It adds 2,035 tokens to every session, about $0.0081 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

design-os AGENTS.md compared with instructions from other repositories

design-os AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
design-os AGENTS.mdbuildermethods/design-osInstructions file1.9k1mo agoMITA2,035Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode