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 skills add xobotyi/cc-foundry --skill frontend-designgit clone --depth 1 https://github.com/xobotyi/cc-foundryWrote 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/xobotyi/cc-foundry/frontend-design)<a href="https://agentmods.dev/skills/xobotyi/cc-foundry/frontend-design"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/frontend-design/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/skills/xobotyi/cc-foundry/frontend-design"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/frontend-design.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 | $0.00046 | $0.03269 |
| Opus 5.5 | $0.00018 | $0.01308 |
| Sonnet 5.5 | $0.00009 | $0.00654 |
| Haiku 4.5 | $0.00005 | $0.00327 |
Grade A, and why
frontend-design 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 14d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A default is a decision nobody made, and an interface nobody looked at is unverified. Interfaces go wrong at those two points. A value arrives from the model's habits or from a framework's stock settings and ships unexamined. Then the result is checked by reading markup instead of looking at the page.
Fix the design, not the detection. A pattern is a defect when nothing chose it, never because it resembles other sites. The navigation, the form, and the table a user already knows are what make an interface usable.
Find what already decides
Before any visible choice, establish what has already made it. Take the first that holds.
- What the user specified for this change — an instruction, an approved mockup, a reference site or screenshot, a brand, a named direction. It governs every axis it names, also where it departs from the existing design or names a look from the stock list below. Say where it departs. An answer covers only the question it answered.
- The project's own design — its tokens, theme, design document, the component kit as the project themed it, and the neighboring screens. Build from its parts. Never place a color, font, radius, shadow, or spacing value beside an existing scale, and never write a component the project already has. It governs even where its values are a kit's shipped defaults: changing those is a restyle, and a restyle is requested, never volunteered.
- A host application — when the work is injected into an interface the project does not own, as an extension, an embedded widget, or a plugin does, the host's controls, classes, spacing, and separators are the system. Write a component of your own only where the host has none.
- The subject — with none of the above, derive the choices from what the product is, who uses it, and the material of its domain. Ask once for a reference when a person is there to answer and the surface has no design to inherit. Without an answer, state the direction before building it.
Where the project has a token source or a neighboring screen, read it before writing a style. A system recalled from a framework's documentation is not the project's system.
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.
- 14d ago First seen · 203 lines · 46 tokens per session scan A 33c1944c650d
frontend-design is a skill published in the GitHub repository xobotyi/cc-foundry (22 stars, last pushed 7d ago), licensed MIT. It adds 46 tokens to every session and 3,269 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 2026-10-07.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
frontend-visual-qa
Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.