chatgpt-vue3-light-mvp: Skill for Claude Code

.agents/skills/uncodixfy/SKILL.md

uncodixfy is a skill for Claude Code, Codex from pdsuwwz/chatgpt-vue3-light-mvp. It costs 66 tokens per session (3,375 once invoked), scanned A, a copy of uncodixfy, MIT.

A set of rules for making frontend interfaces look deliberately designed instead of following common AI-generated patterns.

In plain words
What is it for?
It guides HTML, CSS, React, Vue, and Svelte UI work toward cleaner, more practical designs.
Why use it?
It helps avoid repetitive layouts, decorative effects, and styling choices that can make an interface feel generic.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is pdsuwwz/chatgpt-vue3-light-mvp's own configuration. It tells Claude Code and Codex how to work on chatgpt-vue3-light-mvp 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 chatgpt-vue3-light-mvp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pdsuwwz/chatgpt-vue3-light-mvp. 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/pdsuwwz/chatgpt-vue3-light-mvp/main/.agents/skills/uncodixfy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pdsuwwz/chatgpt-vue3-light-mvp

Made for: Claude Code, Codex.

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 uncodixfy

README.md
[![agentmods](https://agentmods.dev/badge/skills/pdsuwwz/chatgpt-vue3-light-mvp/uncodixfy/github.svg)](https://agentmods.dev/skills/pdsuwwz/chatgpt-vue3-light-mvp/uncodixfy)
Your own site
<a href="https://agentmods.dev/skills/pdsuwwz/chatgpt-vue3-light-mvp/uncodixfy"><img src="https://agentmods.dev/badge/skills/pdsuwwz/chatgpt-vue3-light-mvp/uncodixfy/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 uncodixfy

Your own site · 80×15
<a href="https://agentmods.dev/skills/pdsuwwz/chatgpt-vue3-light-mvp/uncodixfy"><img src="https://agentmods.dev/badge/skills/pdsuwwz/chatgpt-vue3-light-mvp/uncodixfy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,375 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 100% copy Near-identical to another mod 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 $0.00066 $0.03375
Opus 5 $0.00033 $0.01688
Sonnet 5 $0.00013 $0.00675
Haiku 4.5 $0.00007 $0.00337

Measured 13d ago against content hash efb88d150e40, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

uncodixfy 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 13d 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.

Origin

This is a copy

100% identical to uncodixfy — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/uncodixfy/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Uncodixify

This document exists to teach you how to act as non-Codex as possible when building UI.

Codex UI is the default AI aesthetic: soft gradients, floating panels, eyebrow labels, decorative copy, hero sections in dashboards, oversized rounded corners, transform animations, dramatic shadows, and layouts that try too hard to look premium. It's the visual language that screams "an AI made this" because it follows the path of least resistance.

This file is your guide to break that pattern. Everything listed below is what Codex UI does by default. Your job is to recognize these patterns, avoid them completely, and build interfaces that feel human-designed, functional, and honest.

When you read this document, you're learning what NOT to do. The banned patterns are your red flags. The normal implementations are your blueprint. Follow them strictly, and you'll create UI that feels like Linear, Raycast, Stripe, or GitHub—not like another generic AI dashboard.

This is how you Uncodixify.

Keep It Normal (Uncodexy-UI Standard)

  • Sidebars: normal (240-260px fixed width, solid background, simple border-right, no floating shells, no rounded outer corners)
  • Headers: normal (simple text, no eyebrows, no uppercase labels, no gradient text, just h1/h2 with proper hierarchy)
  • Sections: normal (standard padding 20-30px, no hero blocks inside dashboards, no decorative copy)
  • Navigation: normal (simple links, subtle hover states, no transform animations, no badges unless functional)
  • Buttons: normal (solid fills or simple borders, 8-10px radius max, no pill shapes, no gradient backgrounds)
  • Cards: normal (simple containers, 8-12px radius max, subtle borders, no shadows over 8px blur, no floating effect)
  • Forms: normal (standard inputs, clear labels above fields, no fancy floating labels, simple focus states)
  • Inputs: normal (solid borders, simple focus ring, no animated underlines, no morphing shapes)
  • Modals: normal (centered overlay, simple backdrop, no slide-in animations, straightforward close button)
  • Dropdowns: normal (simple list, subtle shadow, no fancy animations, clear selected state)
  • Tables: normal (clean rows, simple borders, subtle hover, no zebra stripes unless needed, left-aligned text)
  • Lists: normal (simple items, consistent spacing, no decorative bullets, clear hierarchy)
  • Tabs: normal (simple underline or border indicator, no pill backgrounds, no sliding animations)
  • Badges: normal (small text, simple border or background, 6-8px radius, no glows, only when needed)
  • Avatars: normal (simple circle or rounded square, no decorative borders, no status rings unless functional)
  • Icons: normal (simple shapes, consistent size 16-20px, no decorative icon backgrounds, monochrome or subtle color)
  • Typography: normal (system fonts or simple sans-serif, clear hierarchy, no mixed serif/sans combos, readable sizes 14-16px body)
  • Spacing: normal (consistent scale 4/8/12/16/24/32px, no random gaps, no excessive padding)
  • Borders: normal (1px solid, subtle colors, no thick decorative borders, no gradient borders)
  • Shadows: normal (subtle 0 2px 8px rgba(0,0,0,0.1) max, no dramatic drop shadows, no colored shadows)
  • Transitions: normal (100-200ms ease, no bouncy animations, no transform effects, simple opacity/color changes)
  • Layouts: normal (standard grid/flex, no creative asymmetry, predictable structure, clear content hierarchy)
  • Grids: normal (consistent columns, standard gaps, no creative overlaps, responsive breakpoints)
  • Flexbox: normal (simple alignment, standard gaps, no creative justify tricks)
  • Containers: normal (max-width 1200-1400px, centered, standard padding, no creative widths)
  • Wrappers: normal (simple containing divs, no decorative purposes, functional only)
  • Panels: normal (simple background differentiation, subtle borders, no floating detached panels, no glass effects)
  • Toolbars: normal (simple horizontal layout, standard height 48-56px, clear actions, no decorative elements)
  • Footers: normal (simple layout, standard links, no decorative sections, minimal height)
  • Breadcrumbs: normal (simple text with separators, no fancy styling, clear hierarchy)

Read the full file on GitHub · 195 lines

Files

What ships with it

1 file 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.

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. 13d ago First seen · 195 lines · 66 tokens per session scan A efb88d150e40

Subscribe to this mod's changes

uncodixfy is a skill published in the GitHub repository pdsuwwz/chatgpt-vue3-light-mvp (574 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 3,375 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to uncodixfy, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

cometchat-react-v7-customization

Theme and brand the React v7 UI Kit — light/dark mode, CSS custom-property design tokens, per-component style overrides. Triggers: 'change chat colors', 'dark mode chat', 'match my brand', 'customize cometchat theme', 'override message list styles'.

cometchat/cometchat-skills · 67 tokens

cometchat-angular-v5-customization

Brand and customize the CometChat Angular UI Kit — CSS variable tokens, light/dark via ThemeService, localization, date/time formats, global config, and swapping component regions with ng-template. Triggers: 'change the chat colours', 'match my brand angular', 'dark mode', 'translate the chat', 'change the date…

cometchat/cometchat-skills · 85 tokens

frontend-design

A design and coding guide for building distinctive web interfaces, including pages, dashboards, landing pages, and reusable components.

itmisx/deepx-code · 88 tokens

responsive-design-advisor

Design responsive layouts with breakpoints, mobile-first approach, and flexible grids. Use when creating responsive designs, implementing breakpoints, or optimizing for multiple screen sizes.

armanzeroeight/fastagent-plugins · 37 tokens

design-taste-frontend

Anti-slop frontend direction for landing pages, portfolios, editorial pages, and design-forward redesigns. Use after reading the brief to infer a fitting visual system, preserve existing product constraints, and run a strict pre-flight audit.

Amery2010/open-builder · 51 tokens

web-design-engineer

Build high-quality visual Web artifacts using HTML/CSS/JavaScript/React — web pages, landing pages, dashboards, interactive prototypes, HTML slide decks, animated demos, UI mockups, data visualizations, and more. Use this skill whenever the user's request involves a visual, interactive, or front-end deliverable…

TheSyart/emperor-agent · 210 tokens