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/init)<a href="https://agentmods.dev/commands/mahmoudilyan/marmoui/init"><img src="https://agentmods.dev/badge/commands/mahmoudilyan/marmoui/init/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/init"><img src="https://agentmods.dev/badge/commands/mahmoudilyan/marmoui/init.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 | $0.00039 | $0.01240 |
| Opus 5.5 | $0.00016 | $0.00496 |
| Sonnet 5.5 | $0.00008 | $0.00248 |
| Haiku 4.5 | $0.00004 | $0.00124 |
Grade A, and why
init 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/marmo-ui:init
Bootstrap this project's design identity. If a DESIGN.md (or design.md) already exists at the project root, read it, report its brand name + primary color, and stop — never overwrite without an explicit ask. Otherwise: detect what you can, interview for what you can't, then write DESIGN.md.
The file follows the Stitch DESIGN.md structure (YAML frontmatter with design tokens, prose body with usage rules) so any agent — Claude, Cursor, Codex, Gemini — can generate on-brand UI from it. For Pro tenants the same file is what workspace ingestion uploads to the MCP.
Step 1 — Detect before asking
Scan the project and pre-fill every token you can. Do not ask about anything you detected:
- Colors —
:rootcustom properties in global CSS,tailwind.config.*theme.extend.colors, existingtokens.css/tokens.json. - Typography —
next/fontimports,@fontsource/*deps, Google Fonts<link>s,fontFamilyin Tailwind config. - Radius / spacing —
--radius-*/--space-*custom properties, TailwindborderRadius/spacingextensions. - Layout — presence of a sidebar shell (
SidebarProvider,app-shellpattern) vs. topbar marketing layout in existing routes. - Dark mode —
.darkclass usage,next-themes,prefers-color-schemeblocks.
Step 2 — Interview for the gaps
Ask only the unanswered essentials, in one batch (AskUserQuestion if available; plain questions otherwise). Main questions, in priority order:
- Brand name — what should the system be called?
- Primary color — one hex value (or "pick for me" → propose 3 anchored options).
- Fonts — display + body (or "system" / "pick for me").
- Layout — app-with-sidebar, topbar-marketing, or both?
- Corner rounding — sharp (2–4px), soft (6–10px), or pill-heavy?
- Spacing density — compact, comfortable, or airy?
- Dark mode — required, later, or never?
Accept partial answers; infer skipped fields from the brand color's temperature and the project's genre, and state every inference in your reply so the user can redirect.
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.
- 2mo ago First seen · 106 lines · 39 tokens per session scan A 343a01f0fe3f
init is a command published in the GitHub repository mahmoudilyan/marmoui (19 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 1,240 once invoked, about $0.0002 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.
Other commands, from other repositories
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
ux-audit
Audit a Figma file against a design brief — checks page structure, frame naming, sizes, styles, components, and content compliance.
gen-video
Generate video output in one of three modes: Remotion (programmatic React-based video), Gen-AI (shot prompt pack for Runway/Kling/Sora/Pika/Luma), or Remotion+Gen-AI (programmatic scaffold with AI footage embedded).
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.