ban-pattern

ban-pattern is a skill for Claude Code from tsubotax/melta-ui. It costs 67 tokens per session (2,777 once invoked), scanned A, original, MIT.

A design-system rule for recording interface patterns that should not be used because they make a UI look generic or AI-generated.

In plain words
What is it for?
Use it when reviewing a screenshot or UI and registering its specific styling pattern, CSS or Tailwind classes, and an approved replacement.
Why use it?
It keeps unwanted visual patterns from being reintroduced across the design system.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: names the AskUserQuestion tool; mentions AGENTS.md.

Install

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.

agentmods
npx agentmods add skills/tsubotax/melta-ui/ban-pattern
Any agent
npx skills add tsubotax/melta-ui --skill ban-pattern
Clone the repo
git clone --depth 1 https://github.com/tsubotax/melta-ui

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 ban-pattern

README.md
[![agentmods](https://agentmods.dev/badge/skills/tsubotax/melta-ui/ban-pattern.svg)](https://agentmods.dev/skills/tsubotax/melta-ui/ban-pattern)
Your own site
<a href="https://agentmods.dev/skills/tsubotax/melta-ui/ban-pattern"><img src="https://agentmods.dev/badge/skills/tsubotax/melta-ui/ban-pattern.svg" alt="Measured on agentmods" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,777 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00067 $0.02777
Opus 5 $0.00034 $0.01388
Sonnet 5 $0.00013 $0.00555
Haiku 4.5 $0.00007 $0.00278

Measured today against content hash 101f44113ae1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ban-pattern 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 today.

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.

skills/ban-pattern/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI生成UIに頻出する「それっぽい」装飾パターンを特定し、DS全体の禁止ルールとして登録する。

手順

Step 1: パターンを特定する

ユーザーの説明(テキスト or スクリーンショット)から、禁止対象のパターンを特定する。

以下を明確にする:

  • 何が問題か: どの視覚要素がAI生成っぽいのか
  • 該当する Tailwind クラス / CSS: 具体的な実装パターン(例: border-l-4, bg-gradient-to-r
  • 代替パターン: DS準拠の代わりの実装

不明点があれば AskUserQuestion で確認する。推測で進めない。

Step 2: 既存ルールと重複がないか確認する

以下を読み込む:

  • design/contracts/rules.jsonrules[]SSOT。機械可読版。同じ pattern / 趣旨のルールが無いか)
  • foundations/prohibited.md の「AI生成パターンの排除」セクション(人間向けミラー)

既に同じ or 類似のルールが存在する場合は、ユーザーに報告して既存ルールの更新で対応するか確認する。

Step 3: 禁止ルールを登録する

SSOT は design/contracts/rules.json。CI / MCP check_rule / PostToolUse hook はすべて rules.json を参照する。ここに機械可読ルールを足して初めて「ban → 即 enforcement」が成立する。 prohibited.md は人間向けの解説ミラーであり、enforcement の実体ではない。順序厳守:

3-1. design/contracts/rules.json — 機械可読ルールを追加(最優先)

rules[] 配列にルールオブジェクトを 1 件追加する。スキーマは design/schemas/rule.schema.json

detector の選び方(これで自動検出されるか・人手参照に留まるかが決まる):

detector いつ使う 必須フィールド
tailwind-class 単一の固定クラスを禁止 pattern(クラス名) border-l-4, shadow-2xl
tailwind-class-prefix 前方一致で複数バリアントを一網打尽 pattern(接頭辞)。任意値回避経路があれば prefixPatterns bg-gradient-
tailwind-class-segment クラスを - 分割したセグメント一致(色名等) matchPatterns(セグメント配列)、pattern: null purple/violet
manual 静的検出が原理的に不能(文脈判断) pattern: nullcontractLint: "skip" 「色だけで状態を伝達」

フィールド規約:

  • id: 大文字スネーク(^[A-Z][A-Z0-9_]+$)。AI生成装飾は AI_NO_*、特定コンポーネントは <COMPONENT>_NO_*
  • category: ai-pattern(AI装飾)/ または該当カテゴリ(color spacing form 等、schema の enum 参照)
  • severity: error(明確なNG)/ warn(文脈次第・段階導入)
  • alternative: DS準拠の代替実装(必須・具体的に)
  • contractLint: enforce(自動検出可・contract も検査)/ warn / skip(manual・html-attr・文脈依存)

テンプレ(自動検出する典型の AI パターン):

{
  "id": "AI_NO_GLASS_BLUR",
  "category": "ai-pattern",
  "severity": "error",
  "description": "ガラスモーフィズム(backdrop-blur)はAI生成UIの典型tell。安っぽく散漫に見える",
  "detector": "tailwind-class-prefix",
  "pattern": "backdrop-blur",
  "alternative": "不透明な bg-white / bg-slate-50 + border border-slate-200 で面を作る",
  "contractLint": "enforce"
}

Read the full file on GitHub · 166 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. today Changed · -4 lines 101f44113ae1
  2. 7d ago First seen · 170 lines · 67 tokens per session scan A 33835efa034c

Subscribe to this mod's changes

ban-pattern is a skill published in the GitHub repository tsubotax/melta-ui (196 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 2,777 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 2026-08-30.

Related

Other skills, from other repositories

morphous-catalog

Create or refresh Morphous website design-system/theme bundles from animal, insect, plant, landscape, mineral, weather, or other nature motifs. Use when Codex is asked to generate Morphous motif images, light/dark design-system boards, reusable image prompts, generated web assets, shadcn/tweakcn theme exports, or the…

Ameyanagi/morphos · 79 tokens

reimagine-it-lock

Design DNA capture — extracts palette, type stack, motifs, motion, and 3D signatures from a shipped HTML file and saves them as a reusable reference pack. Use when the user says /reimagine-it lock, "lock this design", "save design DNA", "capture this look", or wants to reuse a shipped design on a different target.…

Kayforkind/reimagine-it · 108 tokens

vibe-to-ui

Design systems, motion, mood boards, spatial layout, visual assets, Design Context profiles, and a global Inspiration Library from screenshots, website URLs, inspiration images, music, or fuzzy aesthetic intent. Classifies page archetype, explores 3 product-aware directions before locking tokens (unless exact…

MonkeyUI-dev/vibe-to-ui · 122 tokens

balsa-ui

Build, fix, review, install, and validate Balsa UI open-code components for Vue applications. Use for focused Balsa repository maintenance, Vue UI built from Balsa components, compositions or blocks, semantic tokens, registry metadata, accessibility behavior, and installed-source update safety. Scale the workflow from…

pedrobalsa/balsa-ui · 84 tokens

balsa-template-design

Create distinctive, production-ready Balsa UI templates, blocks, showcases, demos, and visually led Vue surfaces without generic AI-template aesthetics. Use with the balsa-ui skill when generating a new page-level composition, beautifying a Balsa interface, establishing art direction, or producing a polished one-shot…

pedrobalsa/balsa-ui · 88 tokens

generate-figma-screen

Kod veya açıklamadan Figma'da tam ekran/sayfa oluşturur. Yayınlanmış design system bileşenlerini arayıp instance olarak yerleştirir; hardcode değer yerine DS token'larını kullanır. "Figma'da ekran oluştur", "kodu Figma'ya çevir", "landing page çiz", "ekran tasarla", "generate screen", "UI'ı Figma'ya aktar"…

atezer/FMCP · 118 tokens