todox: Skill for Claude Code

.claude/skills/ui-conventions/SKILL.md

ui-conventions is a skill for Claude Code from beydemirfurkan/todox. It costs 52 tokens per session (1,172 once invoked), scanned A, original, MIT.

A set of interface rules for building and changing the todox application's pages, components, styles, and mobile layouts.

In plain words
What is it for?
Use it when creating screens, choosing shared UI helpers, writing Tailwind styles, or making layouts work on small screens.
Why use it?
It helps keep new interface work consistent with existing components and prevents common phone-layout bugs.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is beydemirfurkan/todox's own configuration. It tells Claude Code how to work on todox itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything todox configures →

Reuse

Borrowing it

Nothing to install: this file belongs to beydemirfurkan/todox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/beydemirfurkan/todox/main/.claude/skills/ui-conventions/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/beydemirfurkan/todox

Made for: Claude Code.

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 ui-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/beydemirfurkan/todox/ui-conventions/github.svg)](https://agentmods.dev/skills/beydemirfurkan/todox/ui-conventions)
Your own site
<a href="https://agentmods.dev/skills/beydemirfurkan/todox/ui-conventions"><img src="https://agentmods.dev/badge/skills/beydemirfurkan/todox/ui-conventions/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.

agentmods 80×15 button for ui-conventions

Your own site · 80×15
<a href="https://agentmods.dev/skills/beydemirfurkan/todox/ui-conventions"><img src="https://agentmods.dev/badge/skills/beydemirfurkan/todox/ui-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,172 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 $0.00052 $0.01172
Opus 5 $0.00026 $0.00586
Sonnet 5 $0.00010 $0.00234
Haiku 4.5 $0.00005 $0.00117

Measured 9d ago against content hash 6efc1348d38e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ui-conventions 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 9d 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.

.claude/skills/ui-conventions/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UI conventions

Tailwind v4, CSS-first: there is no tailwind.config. Tokens and helpers live in app/globals.css under @theme inline.

Reach for what exists first

Helper For
.sticker / .sticker-flat the card, and the quieter card inside it
.btn / .btn-quiet buttons
.pill nav, report period and language pills
.link-more the wavy-underline text button
.lift hover raise
.pop entry animation, staggered with an inline animationDelay
.row-action an action that appears on hover and on touch
.searchbox the search field frame
.on-fill dark text on a bright fill
.display / .mono the two non-body typefaces
.prose 68ch measure for body copy

Components: app/components/ (Panel, Empty, Chip, Counter, Field, StatusDot, Blob) via the barrel app/components/index.ts. Client-side pieces: app/features/.

Mobile rules

These are written down because every one of them was a bug on a real phone.

  • Every flex row that holds more than two controls needs flex-wrap. The header, the panel header and the status rows each shipped without it and each made the page scroll sideways.
  • flex-1 is a basis of zero, so a box with flex-1 min-w-0 will squeeze to one word per line rather than let the row wrap. If it should wrap, give it a real min-w-[…]. If it should not shrink, give the siblings shrink-0.
  • No bare fixed widths. w-[210px] belongs behind sm:; on a phone use w-full min-w-0 or flex-1 min-w-0.
  • Touch targets are 44px. .btn, .link-more and .pill get min-height under max-width: 640px in globals.css — use those classes rather than restyling a control from scratch. min-height and not padding, because several call sites override padding with !py-[3px].
  • Hover is not available. Anything revealed on :hover must also be revealed under (hover: none); .row-action already is.
  • Inputs are 16px on mobile. Below that, iOS Safari zooms on focus and does not zoom back.
  • Long unbroken text breaks or truncates. Paths, e-mails, tokens and model ids: truncate with a title, or break-all. Prose in a <pre> gets break-words, not break-all.
  • html, body { overflow-x: clip } is in globals.css as a net for the entry animation's rotation. It is not a licence to leave an overflow unfixed — find the element and fix it there.

Read the full file on GitHub · 94 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. 9d ago First seen · 94 lines · 52 tokens per session scan A 6efc1348d38e

Subscribe to this mod's changes

ui-conventions is a skill published in the GitHub repository beydemirfurkan/todox (2 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 1,172 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

one-design-language

Constrains UI work to the shared design token vocabulary. Use when creating or modifying any component — new CSS values local to one screen are forbidden; every visual decision comes from the existing tokens (spacing, radii, colors, type scale) in globals.css.

lahkiri/xeo-forge · 56 tokens

design-taste-frontend

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

dmae97/omk · 61 tokens

design-taste-frontend-v1

The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

dmae97/omk · 61 tokens

high-end-visual-design

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

dmae97/omk · 53 tokens

gpt-taste

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

dmae97/omk · 72 tokens

openclaw-color-palette

Design-grade color processing suite — generate harmonious palettes from any seed color, check WCAG 2.1 AA/AAA contrast accessibility, convert between hex/RGB/HSL/HSV/CMYK, simulate 8 color blindness types, and extract dominant colors from images. Use when: (1) user says 'generate a color palette' or 'give me a color…

yedanyagamiai-cmd/openclaw-mcp-servers · 207 tokens