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 MadAppGang/magus --skill frontend-implementgit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/frontend-implement)<a href="https://agentmods.dev/skills/madappgang/magus/frontend-implement"><img src="https://agentmods.dev/badge/skills/madappgang/magus/frontend-implement/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/madappgang/magus/frontend-implement"><img src="https://agentmods.dev/badge/skills/madappgang/magus/frontend-implement.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 | $0.00040 | $0.03377 |
| Opus 5.5 | $0.00016 | $0.01351 |
| Sonnet 5.5 | $0.00008 | $0.00675 |
| Haiku 4.5 | $0.00004 | $0.00338 |
Grade A, and why
frontend-implement 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 25d 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.
This is a copy
86% identical to ui-implement — 503 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend implementation: from a design review to a distinctive UI
This skill turns a design review's findings into code that makes a UI look designed for its product rather than generated. Its rules say what to change: composition, surface, type, motion, colour. The design system decides where each change goes. A new look means new or changed tokens in the theme and new variants in the component library, and screens only compose. Restyling a screen with inline values does not make the change. It hides the change where nobody can reuse or review it.
Done means: every issue in the review is addressed, or left with a stated reason; the direction is written down and visible in every area you changed; the diff passes the design-system audit; every new or changed variant has a story; the implementation log exists.
| Related | Role |
|---|---|
designer:ui-analyse (designer plugin) |
produces the review this skill applies |
designer:ui-style-format (designer plugin) |
schema of .claude/design-style.md, the direction when a project has one |
| design-system guardrails (dev plugin, sibling folder) | the rules every change here obeys |
Before you start
Read the design-system guardrails: ../design-system-guardrails/SKILL.md, relative to this
skill's directory (in the dev plugin, skills/frontend/design-system-guardrails/SKILL.md).
This skill assumes its five rules and its decision tree. Nothing below overrides them.
Collect the inputs:
| Input | Usually comes from | If it is missing |
|---|---|---|
| The review | /designer:review (writes summary.md), the designer:ui-analyse patterns, or a human reviewer. Each issue has a location, a severity and a recommendation. |
Get one first, for example /designer:review <screenshot>. This skill applies findings; it does not invent them. |
| The paths to change | the review's locations, or the caller | Trace them from the review's locations. Ask the caller only if a location matches more than one place. |
| The direction | .claude/design-style.md, a /designer:ui output directory (its tokens.css and components.md are a contract), or the user's brief |
Infer it from the product: audience, domain, existing brand assets. Record it in the log as an assumption. |
| Screenshots of the current state | the review, or the caller | Work from the code. |
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.
- 25d ago Changed · -30 lines d4c11ffb3876
- 1mo ago First seen · 333 lines · 40 tokens per session scan A 15ebfd699736
frontend-implement is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 3,377 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to ui-implement, differing in 503 lines, and is treated as a copy.
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.