agentmods.dev

marmo-build

marmo-build is a command for Claude Code from mahmoudilyan/marmoui. It costs 27 tokens per session (370 once invoked), scanned A, original, MIT.

A command for building user interfaces with Marmo's internal design system and its connected UI guidance service. It covers choosing an icon library, finding suitable components, writing the UI, and reviewing the generated code.

In plain words
What is it for?
Use it in a Marmo product repository to build or revise UI screens, select components and icons, and validate the final code.
Why use it?
It provides a defined workflow for finding the right components and checking that imports and icons match the chosen design system. The command is intended for explicit requests to build something in the Marmo style.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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

not rated 19repo +2 3mo ago A scan 27 tokens original MIT

Good fit Use it in a Marmo product repository to build or revise UI screens, select components and icons, and validate the final code.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mahmoudilyan/marmoui/marmo-build
View source ↗ mahmoudilyan/marmoui marmoui.com
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 marmo-build

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/mahmoudilyan/marmoui/marmo-build"><img src="https://agentmods.dev/badge/commands/mahmoudilyan/marmoui/marmo-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 370 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 $0.00027 $0.00370
Opus 5.5 $0.00011 $0.00148
Sonnet 5.5 $0.00005 $0.00074
Haiku 4.5 $0.00003 $0.00037

Measured 2mo ago against content hash 3e6ab7a8eb17, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

marmo-build 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.

tools/claude-plugin/plugins/marmo-ui/commands/marmo-build.md · 21 lines

What it actually says

/marmo-ui:marmo-ui-build

Build UI using @marmoui/ui (Marmo's internal design system) and the marmo-ui MCP server bundled with this plugin. Run the full validated workflow regardless of how simple the request looks. Works in any Marmo product repo.

Steps

  1. Call mcp__marmo-ui__get_knowledge_version and log the result.
  2. Ask the user which icon library they want (default: phosphor / Phosphor Icons; also material, lucide, tabler, heroicons, feather). Then call mcp__marmo-ui__get_design_guidelines with that iconLibrary.
  3. If the user's request matches a known pattern, call mcp__marmo-ui__get_pattern with the closest patternId (and the same iconLibrary). Otherwise call mcp__marmo-ui__search_components with relevant keywords, then mcp__marmo-ui__get_component_info for each component selected.
  4. Write the code. UI imports only from @marmoui/ui; icons only from the chosen library (use the icon name map returned by get_design_guidelines).
  5. Call mcp__marmo-ui__review_generated_code on the final output with the same iconLibrary. Fix all errors (wrong-library icon imports are errors). Re-run until valid: true.
  6. Return the code with a one-line note describing which pattern/components and icon library were used.

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. 2mo ago First seen · 21 lines · 27 tokens per session scan A 3e6ab7a8eb17

Subscribe to this mod's changes

marmo-build is a command published in the GitHub repository mahmoudilyan/marmoui (19 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 370 once invoked, about $0.0001 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.

Design and UXFrontendai-agentsclaudecomponentsdesign-systemmcp
Related

Other commands, from other repositories

verify

Fidelity check — rebuild a page from the extracted tokens, pixel-diff it against the live site, and score how faithfully the tokens capture the design.

Manavarya09/design-extract · 31 tokens

design-tutorial

Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.

Adityaraj0421/naksha-studio · 28 tokens

ux-audit

Audit a Figma file against a design brief — checks page structure, frame naming, sizes, styles, components, and content compliance.

Adityaraj0421/naksha-studio · 27 tokens

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).

Adityaraj0421/naksha-studio · 56 tokens

critique-ux

Run a focused UX critique on a screen — affordances, information density, and hierarchy — and output a prioritised fix list.

Owl-Listener/designer-skills · 26 tokens

design-onboarding

Design a first-run experience end to end — activation path, progressive disclosure, and time to first value.

Owl-Listener/designer-skills · 21 tokens