markdown-ticket: Skill for Claude Code

.agents/skills/mdt-frontend/SKILL.md

mdt-frontend is a skill for Claude Code, Codex from andkirby/markdown-ticket. It costs 59 tokens per session (2,821 once invoked), scanned A, original, MIT.

Project-specific instructions for building and changing React user-interface components in the MDT codebase, including CSS, modals, tabs, and other screens.

In plain words
What is it for?
Use it when creating or refactoring components, writing CSS, or changing modal and tab interfaces in the project’s src directory.
Why use it?
It reduces build failures and inconsistent styling by requiring the project’s existing design rules, shared classes, and Tailwind 3 constraints to be followed.

Skill for Claude CodeCodex

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

This is andkirby/markdown-ticket's own configuration. It tells Claude Code and Codex how to work on markdown-ticket 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 markdown-ticket configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is CONTRACT_ONLY=1 node .git/info/lefthook-remotes/agent-commit-hooks/scripts/enforce-semantic-classes.mjs <file>.

Reuse

Borrowing it

Nothing to install: this file belongs to andkirby/markdown-ticket. 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/andkirby/markdown-ticket/main/.agents/skills/mdt-frontend/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/andkirby/markdown-ticket

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 mdt-frontend

README.md
[![agentmods](https://agentmods.dev/badge/skills/andkirby/markdown-ticket/mdt-frontend.svg)](https://agentmods.dev/skills/andkirby/markdown-ticket/mdt-frontend)
Your own site
<a href="https://agentmods.dev/skills/andkirby/markdown-ticket/mdt-frontend"><img src="https://agentmods.dev/badge/skills/andkirby/markdown-ticket/mdt-frontend.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,821 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 $0.00059 $0.02821
Opus 5 $0.00030 $0.01411
Sonnet 5 $0.00012 $0.00564
Haiku 4.5 $0.00006 $0.00282

Measured 7d ago against content hash 5cf2755dc199, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mdt-frontend 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 7d 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.

.agents/skills/mdt-frontend/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDT Frontend Developer

Project-specific conventions for writing frontend code in src/. Generic React/TypeScript knowledge is assumed — this skill only covers MDT-specific rules that break builds or create inconsistency.

Mandatory reads

Before touching CSS or a modal component, read these files:

  1. src/STYLING.md — CSS rules: BEM naming, inline-vs-extract decision tree, surface contract
  2. src/THEME.md — token reference (colors, spacing, radius, gap, typography, z-index)
  3. src/PRIMITIVES.md — shared CSS class inventory (what already exists; check before inventing)
  4. src/ITCSS.md — ITCSS layer architecture, nesting contract, token-gap registry
  5. src/MODALS.md — three modal patterns, spacing standard, close button rules

Critical rules

1. Tailwind 3 @apply cannot chain custom classes

This is the #1 build breaker. Tailwind 3 cannot resolve custom classes (defined in @layer components) inside @apply within the same layer.

/* ❌ BREAKS BUILD — .btn is a custom class in @layer components */
.btn-primary {
  @apply btn bg-primary text-primary-foreground;
}

/* ✅ CORRECT — inline the base utilities */
.btn-primary {
  @apply inline-flex items-center justify-center rounded-md text-sm font-medium
    bg-primary text-primary-foreground;
  border: 1px solid oklch(var(--border));
}

Only Tailwind utility classes work in @apply. If you need to "extend" a base class, copy the utilities and add your own.

2. Use tokens — never invent sizes, colors, spacing, or radii

Tokens are the single source of truth. Before writing any hardcoded value (8px, 0.5rem, #hex, oklch(0.5 …)), check src/THEME.md for an existing token. If a token exists, use it. If you need a value that doesn't exist as a token, add the token to src/styles/design-tokens.css (both :root and .dark) — don't hardcode it where you need it.

Concern Token scale (consume via bare var()) Examples
Spacing / gap --gap-xs (4px), --gap-sm (8px), --gap-md (16px default), --gap-lg (24px) gap: var(--gap-md); between header elements
Border radius --radius-input (8px), --radius-card (8px), --radius-xs (4px), --radius-pill (999px) border-radius: var(--radius-input);
Card density --pad-y, --pad-x, --fs-xs, --fs-md (driven by CardDensity pref) driven by useCardDensity — don't hardcode card padding
Icon / control sizing --sz-icon (16px glyph), --sz-control (32px hit target) glyph beside ticket key
Colors --bg-subtle/muted/elevated, --text-muted/subtle, --primary-text, --border-strong, status/priority/type tokens background: var(--bg-elevated);
Border oklch(var(--border)) (shadcn channel set) border-color: oklch(var(--border));

Read the full file on GitHub · 222 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. 7d ago First seen · 222 lines · 59 tokens per session scan A 5cf2755dc199

Subscribe to this mod's changes

mdt-frontend is a skill published in the GitHub repository andkirby/markdown-ticket (5 stars, last pushed 22d ago), licensed MIT. It adds 59 tokens to every session and 2,821 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

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…

chakra-ui/chakra-ui · 214 tokens

ui-checkstyle

Run the exact ESLint + Prettier + organize-imports sequence that CI's UI Checkstyle workflow runs — on just the files the PR changed — and fail the task if any file ends up with a diff. Invoke after authoring or modifying any .ts, .tsx, .js, .jsx, or .json file under openmetadata-ui/src/main/resources/ui/src/…

open-metadata/OpenMetadata · 122 tokens

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.

microsoft/skills · 48 tokens

21st-ui

Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.

21st-dev/magic-mcp · 63 tokens

moai-design-tools

Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.

modu-ai/moai-adk · 45 tokens

byted-util-vite-react-tailwind

A setup guide for building frontend projects with Vite, React, Tailwind CSS, TypeScript, and Lucide icons.

bytedance/agentkit-samples · 64 tokens