ux-polish

ux-polish is a command for Claude Code from Laith0003/ux-skill. It costs 110 tokens per session (3,811 once invoked), scanned A, original, MIT.

A command for improving the visual details of an existing interface after its basic structure already works. It checks spacing, visual importance, design tokens, and signs that the result looks generic or machine-made.

In plain words
What is it for?
Use it on a URL, screenshot, file, or code snippet when tightening spacing, improving visual hierarchy, checking consistent design values, or making an interface look more deliberate.
Why use it?
It addresses interfaces that feel unfinished, uneven, or visually generic without redesigning their structure. It helps align spacing and styling details across the surface.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is || bash bin/ux-lint.sh <user-supplied-path>.

Part of the ux plugin — 25 commands, 5 agents shipped together

Good fit Use it on a URL, screenshot, file, or code snippet when tightening spacing, improving visual hierarchy, checking consistent design values, or making an interface look more deliberate.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Laith0003/ux-skill
agentmods
npx agentmods add commands/laith0003/ux-skill/ux-polish

Made for: Claude Code.

Or install ux, the plugin that ships this one along with the rest of its 25 commands, 5 agents.

Wrote 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.

agentmods badge for ux-polish

README.md
[![agentmods](https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-polish.svg)](https://agentmods.dev/commands/laith0003/ux-skill/ux-polish)
Your own site
<a href="https://agentmods.dev/commands/laith0003/ux-skill/ux-polish"><img src="https://agentmods.dev/badge/commands/laith0003/ux-skill/ux-polish.svg" alt="Measured on agentmods" height="20"></a>
Per session 110 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,811 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.03811
Opus 5 $0.00055 $0.01906
Sonnet 5 $0.00022 $0.00762
Haiku 4.5 $0.00011 $0.00381

Measured 8d ago against content hash feacb048213a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ux-polish 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 8d 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.

commands/ux-polish.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ux-polish

You are running the /ux-polish command from the ux plugin. The job is a cosmetic pass — the surface mostly works but feels rough, generic, or unfinished. Tighten spacing, sharpen hierarchy, kill AI-slop tells, and align loose tokens.

When to use

Triggers: "polish", "tighten this up", "remove the AI-slop", "make it premium", "make this less AI-looking", "the spacing feels off", "this looks generic", "needs more taste", "the design feels cheap".

Use when the structure is right but the execution is loose. Not for fundamental problems (use /ux-audit or /ux-design). Not for copy issues (use /ux-copy). Not for motion (use /ux-motion). Not for accessibility (use /ux-a11y).

If a /ux-critique or /ux-audit has surfaced structural issues, run those first — polish on a broken structure is wasted work.

Input

One of: a URL, an absolute file path containing the code, a screenshot, or a code snippet. Code is preferred for token consistency checks; a URL or screenshot is preferred for visual rhythm.

Process

1. Run the AI-slop tell list

Scan the surface for these specific tells. Each found tell is a Critical or High finding depending on visibility.

Typography slop
  • Inter where wrong: Inter is fine for utilitarian dashboards but feels generic on landing pages, marketing, brand surfaces. Look for Inter being used as the only typeface — that is the tell.
  • Generic sans pairing: Inter + a "modern serif" with no character (Playfair, Lora, default Google Fonts serif). Editorial surfaces need stronger pairings.
  • System UI without intent: defaulting to -apple-system, BlinkMacSystemFont when the surface needs voice.
  • Centered everything: every heading, every paragraph, every CTA centered. Even when there is no reason.
Color slop
  • Purple-blue gradients: the AI default. #6366f1 → #8b5cf6 or any variant. The single strongest tell.
  • Pure black: #000 or bg-black. Should be Zinc-950, Charcoal, Off-Black.
  • Saturated accent colors: anything over 80% saturation reads as generic.
  • Multiple chromatic accents: a brand uses one accent. Two is loud. Three is a tell.
  • Tailwind defaults uncustomized: bg-blue-500, text-gray-500 everywhere. Even the colors are confessing.

Read the full file on GitHub · 277 lines

Changes

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.

  1. 8d ago First seen · 277 lines · 110 tokens per session scan A feacb048213a

Subscribe to this mod's changes

ux-polish is a command published in the GitHub repository Laith0003/ux-skill (68 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 3,811 once invoked, about $0.0006 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.