Skip to content
Bhargav Tibadiya

Agent Design Protocol | Bhargav Tibadiya

Agent Design Protocol

Design systems that keep AI agents on-spec.

Agent Design Protocol is a curated catalog of complete, locked-down design systems for AI coding agents. You download two Markdown files per theme, tokens plus instructions, drop them into your rules folder, and your next prompt ships UI that stays on-spec instead of inventing a new look every time.

Systems live
11
Categories
18
Files per system
2
agent-design-protocol verify

$ agent-design-protocol verify

border-radius resolves from --ds-radius-none

colour resolves from --ds-color-primary

spacing snaps to the 2px scale

font pair locked: DM Sans / Space Mono

shadow matches the elevation scale

contrast ratio passes WCAG AA

6/6 checks passed. Shipping on-spec.

Why do AI agents invent a new design system every prompt?

Ask an AI agent to build a UI twice and it will give you two different border radii, two colour palettes, and two font pairings. Nothing enforces the last decision on the next prompt, unless you give it a locked-down contract.

CriterionWithout a protocolWith Agent Design Protocol
Border radiusA different value every prompt: 2px here, 8px there, 12px on the next screen.Locked to one token. Sharp is 0px everywhere; Rounded is 12px everywhere.
ColourNew hex values invented per session, never matching the last one.Every colour resolves from one CSS custom property sheet.
TypographyFont pairs drift across screens; weights and tracking are guessed.A two-font law enforced by instructions.md: no third font, ever.
Shadows & elevationRandom blur radii and opacities picked per component.One elevation scale, defined once, referenced everywhere.
Spacing & rhythmPadding eyeballed per component: 8px here, 14px there, nothing lines up.A single spacing scale, from a 2px base unit, used for every gap and inset.
Naming & tokensAd-hoc variables like --primary, --main-color, and --brand-blue-2 pile up.One token sheet per system, the same names referenced everywhere they're used.
Responsive behaviourBreakpoints guessed per screen; mobile padding is whatever still fits.Documented breakpoint behaviour and a responsive padding scale, spec'd once.
AccessibilityFocus states, contrast ratios, and ARIA roles are an afterthought, if that.Contrast ratios, focus-visible states, and ARIA patterns documented per component.
Many more: opacity, hover and active states, icon sizing, z-index layering, and every other decision a prompt could drift on.

Our working hypothesis: agents stay on-spec when tokens and instructions live as non-negotiable Markdown next to the project, not as vibes in the chat window.

What does every Agent Design Protocol theme include?

Two per-system Markdown files, a ready-made rules template, a live component showcase, and tokens scoped so systems never collide. Nothing to install, nothing to configure, you should download a theme and wire it into your agent the same day.

design-system.md

The full token sheet: colour palette, typography, spacing, radius, shadows, and component specs.

instructions.md

Design philosophy, anti-pattern lists, decision trees, and ready-to-paste AI prompting templates.

agent-design-protocol.md

A ready-made rules file that points any agent at the other two and marks them non-negotiable.

Live showcase

20+ components rendered live on the system's own page: buttons, forms, tables, modals, charts, and more.

Scoped tokens

Every token lives under its own data attribute, so systems never bleed into each other.

One-click downloads

Grab both Markdown files straight from the browser. No cloning the repo, no build step.

Contract format
Markdown (design-system.md + instructions.md)
Install step
None, copy files into your rules folder
License
MIT, free for commercial and personal use
Agent support
Cursor, Claude Code, Codex, Copilot, Windsurf, and others

How do you go from download to on-spec UI?

Four numbered steps: pick a system, download two files, drop them into your rules folder, then prompt with the contract loaded. See the full guidelines for tool-specific paths. Try this flow once, you should see consistent tokens on the next screen you generate.

  1. Pick a system

    Search or filter by category and mode, and preview the live component showcase before committing to one.

  2. Download two files

    design-system.md and instructions.md, no local setup of this site required.

  3. Drop into your rules folder

    .cursor/rules/ for Cursor. docs/design-system/ for everything else.

  4. Prompt with the contract loaded

    Point the agent at all three files before it writes a single line of UI code.

Works with the agent you already use.

Any tool that reads Markdown rule files works. There is no plugin to install and no proprietary format: point the agent at three plain files and the contract reads the same everywhere.

Cursor.cursor/rules/
Everything elsedocs/design-system/
Cursor
Claude Code
GitHub Copilot
Windsurf
Codex
Azure DevOps

What people say

I got tired of my own agents reinventing the UI every chat. Two Markdown files later, Sharp stays Sharp. That's why I put this protocol together.

Bhargav TibadiyaCreator · Agent Design Protocol

Should you lock your agent to a design system?

Yes, if you care that the fifth screen matches the first. On the other hand, if you are exploring throwaway prototypes, leave the contract out. For production SaaS UI, you should pick one system, load the two files, and treat drift as a bug.

  1. Open the catalog and pick a theme that matches your product tone.
  2. Download design-system.md and instructions.md for that theme.
  3. Place them where your agent reads rules (for example .cursor/rules/).
  4. Prompt with an explicit reminder that the contract is non-negotiable.

Ready when you are

Pick a system.
Ship consistent UI.

Browse the catalog, download two files, and give your next agent a contract it can't drift from.

License
MIT, free forever
Setup
Two files, no build step