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 kBashar/myagentskills --skill ui-tastegit clone --depth 1 https://github.com/kBashar/myagentskillsWrote 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/kbashar/myagentskills/ui-taste)<a href="https://agentmods.dev/skills/kbashar/myagentskills/ui-taste"><img src="https://agentmods.dev/badge/skills/kbashar/myagentskills/ui-taste/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/kbashar/myagentskills/ui-taste"><img src="https://agentmods.dev/badge/skills/kbashar/myagentskills/ui-taste.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 | $0.00082 | $0.02616 |
| Opus 5.5 | $0.00033 | $0.01046 |
| Sonnet 5.5 | $0.00016 | $0.00523 |
| Haiku 4.5 | $0.00008 | $0.00262 |
Grade A, and why
ui-taste 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 2d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UI taste
Overview
These are the user's design values for product UIs. They come from the user's review comments on real designs.
Core principle: every element must earn its place. A quiet, compact screen that shows each thing once is better than a full screen that shows everything.
This skill sets values, not a theme. A direct request from the user is more important than any rule here.
Theme: take it from the product
Colours, fonts, radius, and light or dark mode do not come from this skill.
- Find the product's design tokens: the theme file, the CSS variables, or the component library config.
- Use those tokens. Do not bring in a different design system.
- If the product has no theme, ask the user. If you cannot ask, pick a neutral theme and say so.
Terms
| Term | Meaning |
|---|---|
| Top line | The single header line of a page: title or breadcrumb, page actions, clock and global switches. |
| Quiet control | A small text button with a dotted underline. It takes the accent colour on hover. No fill, no border. |
| Tint | A background tone of the accent colour. It marks the selected item. |
| Context | The text that "Copy context" puts on the clipboard: ids, status, exact error, log query or link. |
Page recipes
A list page is the top line, the summary cards, and one table. Nothing else.
Jobs Copy context Logs ↗ Tue 27 Oct · 09:14 UTC
┌──────────────────────────────────────────────────────┐
│ All jobs 1 204 ◉ Failed 7 ◉ Stuck 2 ◉ Running 3 │ ← a click on a number filters the table
└──────────────────────────────────────────────────────┘
Id ⌕ Status ▾ Customer Started UTC ↓
3f9c2a71 failed acme 27 Oct 02:14
8b01d4e2 running globex 27 Oct 02:10
A details page is the top line, one facts card, and one log card. Nothing else.
Jobs / 3f9c2a71 Copy context Logs ↗ Tue 27 Oct · 09:14 UTC
┌───────────────────────────────────────┬──────────────────────┐
│ Status failed │ fetch done │
│ Job id 3f9c2a71 ← a click copies │ parse done │
│ Type import │ write failed │
│ Customer acme │ notify – │
│ Started 27 Oct 02:14 UTC │ │
└───────────────────────────────────────┴──────────────────────┘
┌ Key lines Errors and warnings All ─────────────────────────┐
│ 02:14:03 fetch done, 12 400 rows │
│▌ 02:15:12 invalid date "31/02" in row 12 401 │ ← error text, thin left edge
│ ▸ Traceback (38 lines) │ ← a click opens it
└────────────────────────────────────────────────────────────────┘
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.
- 2d ago First seen · 187 lines · 82 tokens per session scan A a8b45afd790b
ui-taste is a skill published in the GitHub repository kBashar/myagentskills (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 82 tokens to every session and 2,616 once invoked, about $0.0003 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 2026-10-28.
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.
open-design-setup
Prepare or repair a project's prototyping environment so open-design can build prototypes with the project's own component library and render them through the project's toolchain. Use when the library target is needed and docs/design/prototyping.md is missing, stale, or failing; excludes HTML-only design work and…
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…