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 ariadoss/superskills --skill design-driftgit clone --depth 1 https://github.com/ariadoss/superskillsWrote 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/ariadoss/superskills/design-drift)<a href="https://agentmods.dev/skills/ariadoss/superskills/design-drift"><img src="https://agentmods.dev/badge/skills/ariadoss/superskills/design-drift/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/ariadoss/superskills/design-drift"><img src="https://agentmods.dev/badge/skills/ariadoss/superskills/design-drift.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 | $0.00102 | $0.01397 |
| Opus 5 | $0.00051 | $0.00698 |
| Sonnet 5 | $0.00020 | $0.00279 |
| Haiku 4.5 | $0.00010 | $0.00140 |
Grade A, and why
design-drift 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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Drift
I find where the UI has quietly diverged from its own design system and pull it back — consolidating one-off values into tokens, collapsing duplicate component variants, and promoting recurring exceptions into the system before they calcify into debt.
This is not a taste audit. design-audit asks "does this look good?" I ask "is this consistent with the system that already exists, and what should be normalized or promoted?" Drift is a refactor problem, not an aesthetics problem.
Core Principle
Every visual value in the codebase is one of three things:
- On-system — references a token (
var(--space-4),theme.colors.primary). Leave it. - Drift to normalize — a hardcoded value that is close to an existing token (
padding: 15pxnext to a16pxscale,#3b82f7vs the brand#3b82f6). Snap it back to the token. - Drift to promote — a hardcoded value that recurs deliberately and has no token (
#0a0a0aused in 14 places). It's a real system value that was never named. Add it to the system, then reference it.
The skill is deciding which bucket each value falls in — never blindly find-and-replacing.
Evidence First — No Guessing
I report only drift I can point to. Every finding cites file:line and a count. If I can't locate the design system's source of truth, I stop and ask rather than inventing tokens.
- Locate the system. Find the token source:
tailwind.config.*,theme.ts,:rootcustom properties,tokens.json, aDESIGN_SYSTEM.md, Style Dictionary, etc. This is ground truth. If there is no system, this skill doesn't apply yet — recommendinterface-designorhigh-end-visual-designto establish one first. - Scan for raw values. Grep the styling surface (CSS/SCSS, styled-components, Tailwind arbitrary values
[...], inlinestyle=, RNStyleSheet) for:- Color: hex,
rgb(,hsl(, named colors outside the token layer - Spacing: raw
px/remin padding/margin/gap not drawn from the scale - Type:
font-size/font-weight/line-heightliterals off the type scale - Radii & shadows:
border-radiusandbox-shadowliterals - Z-index: bare integers (a classic drift hotspot)
- Breakpoints: media queries with literal widths
- Color: hex,
- Cluster by proximity. Group near-identical values (
#fafafa,#fbfbfb,#f9f9f9→ one cluster). The cluster size is the signal: how many shades of gray actually ship? - Find duplicate components. Look for
Button2,CardNew,PrimaryButtonV2, copy-pasted variants, and components that reimplement an existing primitive with slightly different values.
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.
- 10d ago First seen · 74 lines · 102 tokens per session scan A 7787e908013b
design-drift is a skill published in the GitHub repository ariadoss/superskills (9 stars, last pushed 3d ago), licensed MIT. It adds 102 tokens to every session and 1,397 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
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 $ralph 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.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
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.