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.
npx agentmods add instructions/buildermethods/design-os/agents-mdgit clone --depth 1 https://github.com/buildermethods/design-osWhat 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 | $0.02035 | $0.02035 |
| Opus 5 | $0.01018 | $0.01018 |
| Sonnet 5 | $0.00407 | $0.00407 |
| Haiku 4.5 | $0.00203 | $0.00203 |
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 2d 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.
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]/andsrc/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
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.
- 2d ago First seen · 213 lines · 2,035 tokens per session scan A eca2f3bb640d
design-os AGENTS.md is an instructions file published in the GitHub repository buildermethods/design-os (1,845 stars, last pushed 3d ago), licensed MIT. It adds 2,035 tokens to every session, about $0.0102 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.
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit 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.
langchain 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.