prototype

prototype is a skill for Claude Code from mahmoudilyan/marmoui. It costs 119 tokens per session (1,421 once invoked), scanned C, original, MIT.

A workflow for building a shareable Marmo prototype: a standalone Vite, React, and Tailwind app that can be published to Netlify. It adds reviewer comments and lets the owner turn selected UI elements into prompts for Claude Code.

In plain words
What is it for?
Scaffolding onboarding or other shareable prototypes, publishing them to Netlify, collecting comments, and preparing AI-assisted edits.
Why use it?
It gives a prototype a way to collect inline feedback and connect review comments to specific files, lines, or page elements.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

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

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.

agentmods
npx agentmods add skills/mahmoudilyan/marmoui/prototype
Any agent
npx skills add mahmoudilyan/marmoui --skill prototype
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 prototype

README.md
[![agentmods](https://agentmods.dev/badge/skills/mahmoudilyan/marmoui/prototype.svg)](https://agentmods.dev/skills/mahmoudilyan/marmoui/prototype)
Your own site
<a href="https://agentmods.dev/skills/mahmoudilyan/marmoui/prototype"><img src="https://agentmods.dev/badge/skills/mahmoudilyan/marmoui/prototype.svg" alt="Measured on agentmods" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,421 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.00119 $0.01421
Opus 5 $0.00060 $0.00711
Sonnet 5 $0.00024 $0.00284
Haiku 4.5 $0.00012 $0.00142

Measured 6d ago against content hash ae1f3c8f246c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

prototype scanned grade C with 2 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 6d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /tmp/marmo-ui-template

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsS http://localhost:5173 > /dev/null && echo OK
tools/claude-plugin/plugins/marmo-ui/skills/prototype/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prototype scaffolding + review-overlay workflow

You are about to scaffold a brand-new Marmo prototype. A prototype is a standalone Vite + React + Tailwind 4 + @marmoui/ui app that lives outside the monorepo and ships to Netlify. The @marmoui/prototype-overlay package is pre-wired into the starter so reviewers can sign in with Claude and leave inline comments, and the owner can click an element, write a prompt, and copy a payload (file + line + selector + prompt) to the clipboard for paste into a local Claude Code session.

If the user just wants to add a UI component to an existing Marmo product app, use the marmo-ui skill instead — not this one.

Required steps (in order)

1. Verify the MCP is fresh

mcp__marmo-ui__get_knowledge_version

If this errors, surface it. Don't fall back to guessing component APIs.

2. Confirm prerequisites

Run in parallel:

  • node --version (need ≥ 20)
  • pnpm --version (need ≥ 9)
  • netlify --version (suggest npm i -g netlify-cli if missing)
  • echo $NPM_TOKEN | head -c 4 (must not be empty — required for GH Packages)
  • echo $MARMO_PROTOTYPE_OAUTH_CLIENT_ID | head -c 4
  • echo $MARMO_PROTOTYPE_COMMENTS_API | head -c 4

If either MARMO_PROTOTYPE_* env var is missing, print this and stop:

Set these once in your shell rc:

export MARMO_PROTOTYPE_COMMENTS_API="https://<proj>.supabase.co/functions/v1/comments-api"
export MARMO_PROTOTYPE_OAUTH_CLIENT_ID="<from anthropic console>"

Ask the Design Systems team for the current values.

3. Choose a target directory

Default: ~/Sites/marmo-prototype-<kebab-case-name-from-prompt>. If it exists and contains anything, ask for an alternative.

4. Copy the starter

Source = apps/prototype-starter/ inside the mahmoudilyan/marmoui monorepo. The user should have it cloned; if not, clone shallow:

git clone --depth 1 https://github.com/mahmoudilyan/marmoui /tmp/marmo-ui-template
cp -R /tmp/marmo-ui-template/apps/prototype-starter <target-dir>
rm -rf /tmp/marmo-ui-template

Read the full file on GitHub · 154 lines

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. 6d ago First seen · 154 lines · 119 tokens per session scan C ae1f3c8f246c

Subscribe to this mod's changes

prototype is a skill published in the GitHub repository mahmoudilyan/marmoui (41 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 1,421 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

react-aria

Build accessible UI components with React Aria Components. Use when developers mention React Aria, react-aria-components, accessible components, or need unstyled accessible primitives. Provides documentation for building custom accessible UI with hooks and components.

NextAdminHQ/nextjs-admin-dashboard · 49 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

sandbox-bench

Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app (rps, latency, p95; TTFB, RSS and document/Flight bytes when the Next side captures them) and, for React changes, through…

vercel/next.js · 212 tokens