design-md

design-md is a command for Claude Code from mahmoudilyan/marmoui. It costs 30 tokens per session (337 once invoked), scanned A, original, MIT.

A command that creates a portable DESIGN.md file containing a project's brand color, typography, design tokens, and component inventory. The file gives AI tools a written description of the project's visual system.

In plain words
What is it for?
Use it to generate or refresh a project's design brief and record its brand settings, reusable components, and visual usage rules.
Why use it?
It preserves the key design guidance in a file that other agents can read, even without the Marmo UI tool connection. This helps generated interfaces follow the same visual rules.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions Codex.

Part of the marmo-ui plugin — 2 skills, 5 commands, 1 hook shipped together

Good fit Use it to generate or refresh a project's design brief and record its brand settings, reusable components, and visual usage rules.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mahmoudilyan/marmoui/design-md
Install

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.

Clone the repo
git clone --depth 1 https://github.com/mahmoudilyan/marmoui

Made for: Claude Code.

Or install marmo-ui, the plugin that ships this one along with the rest of its 2 skills, 5 commands, 1 hook.

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-md

README.md
[![agentmods](https://agentmods.dev/badge/commands/mahmoudilyan/marmoui/design-md/github.svg)](https://agentmods.dev/commands/mahmoudilyan/marmoui/design-md)
Your own site
<a href="https://agentmods.dev/commands/mahmoudilyan/marmoui/design-md"><img src="https://agentmods.dev/badge/commands/mahmoudilyan/marmoui/design-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-md

Your own site · 80×15
<a href="https://agentmods.dev/commands/mahmoudilyan/marmoui/design-md"><img src="https://agentmods.dev/badge/commands/mahmoudilyan/marmoui/design-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 337 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00030 $0.00337
Opus 5 $0.00015 $0.00169
Sonnet 5 $0.00006 $0.00067
Haiku 4.5 $0.00003 $0.00034

Measured 10d ago against content hash 95ca67115c97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

design-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 10d 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.

tools/claude-plugin/plugins/marmo-ui/commands/design-md.md · 25 lines

What it actually says

/marmo-ui:design-md

Generate a portable DESIGN.md for this project using the marmo-ui MCP server. The file captures the design system's brand color, typography, tokens, and component inventory in one agent-readable brief — the free, portable wedge that lets any agent (Claude, Cursor, Codex) generate on-brand UI without the MCP.

Steps

  1. Call mcp__marmo-ui__get_design_md (default format: "markdown"). The result is the full DESIGN.md content as a string.
  2. Write that content verbatim to a DESIGN.md file at the project root. Overwrite any existing DESIGN.md.
  3. Treat DESIGN.md as the source of truth for all subsequent UI generation in this session: use its brand color, typography, tokens, component inventory, and usage rules.
  4. Report the path written, the brand name and primary color, and the number of components captured.

Notes

  • Do not edit the generated content — it is deterministic and matches the authenticated tenant's theme.
  • If you need structured data instead of markdown (e.g. to drive a script), call the tool with format: "json".
  • No MCP auth / no tenant yet? Use /marmo-ui:init instead — it detects or interviews for brand basics and writes a starter DESIGN.md locally.

User request

$ARGUMENTS

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. 10d ago First seen · 25 lines · 30 tokens per session scan A 95ca67115c97

Subscribe to this mod's changes

design-md is a command published in the GitHub repository mahmoudilyan/marmoui (41 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 337 once invoked, about $0.0002 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.