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/jjilli/fable-flow/frontend-aestheticsnpx skills add jjilli/fable-flow --skill frontend-aestheticsgit clone --depth 1 https://github.com/jjilli/fable-flowWrote 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/jjilli/fable-flow/frontend-aesthetics)<a href="https://agentmods.dev/skills/jjilli/fable-flow/frontend-aesthetics"><img src="https://agentmods.dev/badge/skills/jjilli/fable-flow/frontend-aesthetics.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 | $0.00100 | $0.01171 |
| Opus 5 | $0.00050 | $0.00585 |
| Sonnet 5 | $0.00020 | $0.00234 |
| Haiku 4.5 | $0.00010 | $0.00117 |
Grade A, and why
frontend-aesthetics 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 5d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend aesthetics
Claude converges on safe, generic frontends unless told not to — the "AI slop" look (Inter on white, a purple gradient, evenly-timid spacing). Distinctive, polished UI comes from explicit, committed choices on a few dimensions, plus a visual check because a green test suite never sees a layout regression. Distilled from the official guide (https://platform.claude.com/cookbook/coding-prompting-for-frontend-aesthetics) and hard-won pipeline experience.
State the design direction before writing code
Pick a cohesive aesthetic that fits the product's context and commit to it in one or two sentences before touching CSS: the mood, the type, the palette, the one motion moment. A security console, a garden-planning app, and a fintech dashboard should not look like the same starter template. Decisiveness reads as "designed"; hedging reads as generic.
The four dimensions to steer explicitly
- Typography — the fastest quality signal. Choose distinctive fonts and avoid Inter, Roboto, Open Sans, Lato, system-ui. Pair with high contrast (a characterful display against a clean technical sans; add a mono for data). Use extreme weight ranges (200 vs 800, not 400 vs 600) and large size jumps (3x, not 1.5x). Good picks by mood: code — JetBrains Mono, Space Grotesk; editorial — Fraunces, Playfair Display; distinctive — Bricolage Grotesque, Clash Display; technical — the IBM Plex family.
- Color — commit to one cohesive palette via CSS variables. A dominant color with a sharp accent beats an evenly-distributed, timid spread. Draw from a real reference (an IDE theme, a cultural aesthetic) rather than a generic wheel. Give the accent a job (brand + one semantic each for ok/attention/alert). Avoid the clichés: purple-on-white gradients, the default Bootstrap/Tailwind blues.
- Motion — one well-orchestrated moment beats scattered micro-interactions.
Stagger the page-load reveal with
animation-delay. CSS-only for plain HTML; the Motion library for React when it's already a dependency. Always honorprefers-reduced-motion. - Backgrounds — atmosphere, not a flat fill. Layer subtle gradients, a faint texture or grid, a contextual glow that matches the theme. Depth signals care.
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.
- 5d ago First seen · 85 lines · 100 tokens per session scan A 5e02a3f6c2e5
frontend-aesthetics is a skill published in the GitHub repository jjilli/fable-flow (2 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 1,171 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
motion-animations
Use when building website animations, scroll effects, entrance reveals, layout transitions, gesture interactions, parallax, hero choreography, or any animated UI component. Auto-trigger on any website build or frontend feature that involves motion, transitions, or animated elements.
design-taste-frontend
Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.
ui-refactor
Tactical user interface design guide for fixing layouts, selecting colors/fonts, and creating professional UIs. Use when the user asks to "make this look better," needs help with CSS/styling decisions, wants to create a design system, or needs to fix a cluttered interface.
eval-ui-ux
Specialized UI/UX evaluator for the Evaluate-Loop. Use this for evaluating UI shell tracks, design system tracks, screen implementation tracks, or any track where the primary deliverable is visual/interactive UI. Checks design system adherence, visual consistency, layout structure, responsive behavior, component…
frontend-audit
ProductionOS frontend quality scanner. Auto-activates when editing React/Vue/Svelte components, CSS, or layout files. Checks accessibility, responsive design, performance, and design system consistency.
design-patterns
Modern design system patterns for 2025. Covers design tokens, OKLCH color systems, fluid typography, animations, dark mode, shadcn/ui components, and Figma handoff. Use when implementing UI styles, theming, accessibility, and visual polish.