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 markoblogo/abvx-agent-skills --skill frontend-taste-layergit clone --depth 1 https://github.com/markoblogo/abvx-agent-skillsWrote 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/markoblogo/abvx-agent-skills/frontend-taste-layer)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/frontend-taste-layer"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/frontend-taste-layer/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/markoblogo/abvx-agent-skills/frontend-taste-layer"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/frontend-taste-layer.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 | $0.00078 | $0.01319 |
| Opus 5 | $0.00039 | $0.00660 |
| Sonnet 5 | $0.00016 | $0.00264 |
| Haiku 4.5 | $0.00008 | $0.00132 |
Grade A, and why
frontend-taste-layer 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Taste Layer
Raise the taste level without turning the work into a random aesthetic stunt.
Use this after the task is understood and the surface register is known. If the project still lacks design context, start with design-register-bootstrap.
Best Fit
- landing pages;
- portfolios;
- brand-forward promo pages;
- redesigns where the current UI feels boilerplate or interchangeable;
- hero sections and first-screen composition work.
Not The Best Fit
- dense dashboards;
- table-heavy app UI;
- settings forms where utility matters more than expressive styling;
- projects that must preserve a strict existing enterprise design system.
Route Before Styling
- For marketing, editorial, portfolio, and brand-forward pages, continue with this skill.
- For dashboards, settings, onboarding, checkout, paywalls, and other product UI, use Lazyweb evidence first, then
user-experience,design-critique-polish, or the project's product-specific skill. - If one page mixes both registers, apply this skill only to the marketing/editorial regions. Product-task clarity wins at the seam.
Design Read
Before changing code, state one sentence:
Reading this as: <surface> for <audience>, with a <vibe> language, leaning toward <design family>.
Do not skip this. Most generic output comes from styling before the read is explicit.
Creator Intent Check
Before widening into polish, state briefly:
- what the person is actually trying to make possible;
- what must remain recognizably theirs;
- which single decision most changes first-use experience.
If the answer is still too vague to guide a real choice, ask one sharp clarifying question, not a survey. If ambiguity does not block a real choice, move.
Three Dials
Set these as relative directions for the pass; do not impose universal numeric defaults:
variance: symmetry versus surprise;motion: static versus cinematic;density: airy versus packed.
Use them to keep decisions consistent. Do not expose a pile of disconnected visual tweaks.
What ships with it
2 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.
- 10d ago First seen · 149 lines · 78 tokens per session scan A a3598c29424e
frontend-taste-layer is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,319 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
web-design-reviewer
This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage…
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.
mulmoterminal-theme
Build a colour scheme of your own for MulmoTerminal — one that joins Midnight, Nord, Daylight and Solarized in Settings' theme picker and can then be pinned per project. Writes themes in /.mulmoterminal/config.json, the whole-app palette (panels, borders, accent, text), which has no UI for creating one — Settings only…
taste
Use when improving the visual taste, positioning, polish, trust, and conversion clarity of a website or product UI. Runs a category-first visual audit, applies a decisive design pass, and verifies the result with screenshots rather than subjective vibes.
ijfw-ui-spec
Use when the user says: 'ui spec', 'design contract', 'ui audit setup', 'lock the design', 'visual contract', 'ui review setup', or '/ijfw-ui-spec'. Produces UI-SPEC.md as the visual design contract before any frontend or visual-artifact build, and dispatches ijfw-ui-auditor as the final 6-pillar gate.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build landing pages, websites, dashboards, web components, or any frontend UI. Generates creative, polished code that avoids generic AI aesthetics.