Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install devWrote 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/design-system-guardrails)<a href="https://agentmods.dev/skills/madappgang/magus/design-system-guardrails"><img src="https://agentmods.dev/badge/skills/madappgang/magus/design-system-guardrails/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/design-system-guardrails"><img src="https://agentmods.dev/badge/skills/madappgang/magus/design-system-guardrails.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 | $0.00055 | $0.02479 |
| Opus 5.5 | $0.00022 | $0.00992 |
| Sonnet 5.5 | $0.00011 | $0.00496 |
| Haiku 4.5 | $0.00006 | $0.00248 |
Grade A, and why
design-system-guardrails 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 1mo 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System Guardrails
Every application UI has exactly two sources of truth:
- The theme (design tokens) — every color, spacing, radius, font, and shadow is defined once.
- The component library (workshopped in Storybook) — every component is defined and styled once, with all its variants and states.
Application screens only compose. They never define appearance.
Why this matters: when tokens and components live in one place, a rebrand is a one-file change, a component fix propagates everywhere, and there is never a third slightly-different implementation of the same button. Every hardcoded hex value or call-site restyle silently creates a second source of truth that someone else (human or agent) will later copy. These rules exist to make drift impossible, not to slow you down.
The five rules
Rule 1 — Tokens are the only styling values
All styling values come from the theme as semantic tokens (named by role: primary, surface, destructive), never as raw values and never as primitive names (blue-500). Semantic names survive rebrands and make dark mode a token swap instead of a rewrite.
- Never hardcode: hex (
#3b82f6),rgb()/hsl()/oklch()literals, magic pixel values, or Tailwind arbitrary values (w-[347px],text-[#ff0000],bg-[rgb(0,0,0)]). - If the value you need doesn't exist, add a token to the theme first, then use it. Never inline it "just this once" — that's how every drifted codebase started.
// ❌ Three new sources of truth
<div className="bg-[#1a56db] p-[13px] rounded-[5px]">
// ✅ Tokens only
<div className="bg-primary p-3 rounded-md">
/* ❌ */ .card { background: #ffffff; border-radius: 8px; }
/* ✅ */ .card { background: var(--color-surface); border-radius: var(--radius-md); }
Rule 2 — Components are defined once, in the library
Every reusable component lives in the component library (e.g. src/components/ui/ or the design-system package) — never inside a screen, page, or feature folder. Every library component has stories covering every variant and interactive state (default, hover, focus, disabled, loading, error, empty).
What ships with it
8 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.
- assets/eslint.guardrails.example.mjs 4.2 KB runs code
- assets/stylelint.guardrails.example.cjs 1.2 KB runs code
- references/component-patterns.md 6.4 KB
- references/design-tokens.md 5.4 KB
- references/enforcement.md 7.3 KB
- references/storybook-structure.md 7.1 KB
- scripts/audit-ui.test.ts 8.4 KB runs code
- scripts/audit-ui.ts 18 KB runs 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.
- 1mo ago First seen · 162 lines · 55 tokens per session scan A 7569ab952c8f
design-system-guardrails is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 2,479 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 2026-09-04.
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.
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.
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…