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.
git clone --depth 1 https://github.com/mahmoudilyan/marmouiWrote 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.
[](https://agentmods.dev/commands/mahmoudilyan/marmoui/design-md)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
- Call
mcp__marmo-ui__get_design_md(defaultformat: "markdown"). The result is the full DESIGN.md content as a string. - Write that content verbatim to a
DESIGN.mdfile at the project root. Overwrite any existingDESIGN.md. - Treat
DESIGN.mdas the source of truth for all subsequent UI generation in this session: use its brand color, typography, tokens, component inventory, and usage rules. - 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:initinstead — it detects or interviews for brand basics and writes a starterDESIGN.mdlocally.
User request
$ARGUMENTS
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.
- 10d ago First seen · 25 lines · 30 tokens per session scan A 95ca67115c97
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.
Other commands, from other repositories
critique-screen
Run all seven visual critiques on a screen and output a prioritised fix list.
critique-ux
Run a focused UX critique on a screen — affordances, information density, and hierarchy — and output a prioritised fix list.
design-onboarding
Design a first-run experience end to end — activation path, progressive disclosure, and time to first value.
frame-problem
Structure an ambiguous design challenge into a clear problem definition with constraints and criteria.
strategize
Develop a complete UX strategy for a product or feature area.
discover
Run a full user research cycle — persona creation, empathy mapping, and journey mapping for a product or feature.