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.
npx agentmods add skills/joaquimscosta/arkhe-claude-plugins/prototypenpx skills add joaquimscosta/arkhe-claude-plugins --skill prototypegit clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-pluginsWrote 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/skills/joaquimscosta/arkhe-claude-plugins/prototype)<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/prototype"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/prototype.svg" alt="Measured on agentmods" 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 | $0.00118 | $0.01631 |
| Opus 5 | $0.00059 | $0.00816 |
| Sonnet 5 | $0.00024 | $0.00326 |
| Haiku 4.5 | $0.00012 | $0.00163 |
Grade A, and why
prototype 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 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.
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.
Prototype
Generate 3 visually distinct, high-fidelity HTML/CSS UI components from a single text prompt, then serve them in a live browser gallery so the user can click through and pick a favorite. Each component adopts a unique design persona based on physical/material metaphors — producing genuinely different visual approaches, not just color swaps.
Quick Start
Parse $ARGUMENTS for the component description, optional --vary N flag, optional --dir <path>, and optional --continue flag.
- If
--continueis present, skip to Next-Turn Pick Capture. - If
--vary Nis present, skip to the Variation Workflow. - Otherwise, follow Phases 1-3 below in a single pass — do not pause between phases or ask for confirmation.
If the description is vague ("button", "form"), just generate. The value is speed. Interpret generously.
Phase 1: Style Direction
Think of 3 distinct design direction names using physical/material metaphors. Pattern: [Adjective] + [Material/Process] + [Form/Action].
Each metaphor should imply different CSS techniques — not just colors. See the materiality-to-CSS mapping in WORKFLOW.md.
Examples (invent your own):
- "Asymmetrical Rectilinear Blockwork" (Grid-heavy, primary pigments)
- "Grainy Risograph Layering" (
feTurbulencegrain,mix-blend-mode: multiply) - "Kinetic Wireframe Suspension" (thin lines, floating silhouettes)
- "Spectral Prismatic Diffusion" (
backdrop-filter, caustic refraction)
Phase 2: Artifact Generation
For each style, generate a complete, self-contained <!DOCTYPE html> page (100-300 lines):
- Materiality: the style metaphor drives every CSS choice
- Typography: Google Fonts via
<link>, pair a bold sans with a refined monospace - Motion: subtle CSS animations and hover transitions
- IP Safeguard: no artist names, brand names, or trademarks
- Layout: bold negative space, avoid generic card grids
- Content: realistic placeholder content, not lorem ipsum
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 106 lines · 118 tokens per session scan A 70bbc44df68d
prototype is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 22d ago), licensed MIT. It adds 118 tokens to every session and 1,631 once invoked, about $0.0006 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 skills, from other repositories
aceternity-ui
100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.
visual-diff
Visual Regression Testing — screenshot comparison before and after changes. Use when user wants to check for visual regressions, compare UI changes, or verify CSS/layout changes didn't break anything.
factory-design
Design-system discipline distilled across builds. Semantic token vocabulary (name intent, not palette position), CSS variables bridged into Tailwind, dark/light as a variable swap, single- vs two-layer token systems, component primitives as token consumers, when to promote a repeated utility cluster into a primitive…
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
visual-verification
Verify UI-facing changes by running a screenshot-analyze-verify loop across configured viewports, with a browser-tool priority cascade (Playwright MCP → Chrome DevTools MCP → CLI fallback → external skill fallback) and bounded iteration. Use after build/runtime verification passes and the diff includes…
tailwind
This skill should be used when the user asks to "style a component with Tailwind", "set up dark mode", "create a responsive layout", "build a reusable UI component", "configure Tailwind", "use cn() utility", or mentions "tailwind", "tailwindcss", "utility class", "className", "dark mode", "responsive design"…