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.
npx agentmods add skills/coinyak/onchainai/tailwindnpx skills add Coinyak/onchainai --skill tailwindgit clone --depth 1 https://github.com/Coinyak/onchainaiWrote 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.
[](https://agentmods.dev/skills/coinyak/onchainai/tailwind)<a href="https://agentmods.dev/skills/coinyak/onchainai/tailwind"><img src="https://agentmods.dev/badge/skills/coinyak/onchainai/tailwind.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00034 | $0.00582 |
| Opus 5 | $0.00017 | $0.00291 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
tailwind 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 4d 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.
What it actually says
You are a Tailwind CSS v4 expert that detects and reports anti-patterns such as incorrect spacing, inconsistent sizing, desktop-first breakpoints, and non-GPU-accelerated animations.
Targets the current project by default — or specify a path to audit a subset of files.
Read individual rule files in rules/ for detailed explanations and code examples.
Rules Overview
| Rule | Impact | File |
|---|---|---|
| Spacing direction | HIGH | rules/spacing-direction.md |
| Equal dimensions | HIGH | rules/equal-dimensions.md |
| 8px grid | HIGH | rules/8px-grid.md |
| Mobile-first responsive | MEDIUM | rules/mobile-first.md |
| Logical shorthands | MEDIUM | rules/logical-shorthands.md |
| GPU-accelerated animations | MEDIUM | rules/gpu-animations.md |
Workflow
Step 1: Audit
Scan the target scope for violations of each rule in rules/. Search patterns:
mt-*/pt-*classes (spacing direction)h-X w-Xpairs where both values match (equal dimensions)- Odd spacing values like
p-1,gap-3,m-5(8px grid) - Desktop-first breakpoints (mobile-first)
- Verbose individual sides where shorthands apply (logical shorthands)
transition-allusage (GPU animations)
Step 2: Report
List all findings grouped by rule:
## Tailwind CSS Audit Results
### HIGH Severity
- `src/components/Card.tsx:15` - `mt-4` → use `mb-4` or `gap` on parent
- `src/components/Avatar.tsx:12` - `h-10 w-10` → `size-10`
### MEDIUM Severity
- `src/components/Button.tsx:8` - `p-3` (12px) → use `p-2` (8px) or `p-4` (16px)
### Summary
| Rule | Violations | Files |
|------|-----------|-------|
| Spacing direction | X | N |
| Equal dimensions | Y | N |
| **Total** | **Z** | **N** |
Step 3: Fix
Apply fixes. For each fix:
- Verify the change preserves visual appearance
- Keep changes minimal — only fix the identified issue
- Adjust surrounding elements when changing spacing direction
What ships with it
6 files 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.
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.
- 4d ago First seen · 65 lines · 34 tokens per session scan A 1d41ad5eb7b2
tailwind is a skill published in the GitHub repository Coinyak/onchainai (1 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 582 once invoked, about $0.0002 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.
Other skills, from other repositories
kiranism-shadcn-dashboard
Guide for building features, pages, tables, forms, themes, and navigation in this Next.js 16 shadcn dashboard template. Use this skill whenever the user wants to add a new page, create a feature module, build a data table, add a form, configure navigation items, add a theme, set up RBAC access control, or work with…
sandbox
Visual HTML canvas sandbox for agent-driven UI and live previews.
omd:feel
디자인·프론트 업계가 '감'으로 쓰던 인터페이스 디테일을 수치화한 규칙으로 적용(APPLY)하거나 감사(AUDIT)한다. Jakub Krehel의 make-interfaces-feel-better 철학을 계승 + HIG/Material/WCAG/DS 토큰/실무자 리서치로 확장한 17축·113규칙(provenance 등급별). 모션 타이밍·이징·동심원 radius·tabular-nums·44px 타깃·focus ring·prefers-reduced-motion 등. 'feel 좋게 다듬어줘', '인터페이스 디테일 적용', 'feel 점검', '마이크로 인터랙션…
omd:landing
Scroll-native one-page landing that overwhelms — concept, composition, asset placement, and scroll choreography derived from DESIGN.md and the measured landing-craft codex. Trigger: '랜딩 페이지', '원페이지', 'landing page', 'one-pager', 'hero to footer', '스크롤 랜딩', 'affinity.studio 같은'.
omd:aphrodite
Maximum-craft one-page landing — the wow bar. omd:landing 의 구조 위에 마감(서체 조달·그레인·깊이·색보정·스크롤 타임라인)과 최고급 에셋을 얹고, 랜딩 검사 전 항목 통과를 합격선으로 삼는다. Trigger: '와우', '압도적인', '최고급', '쇼케이스용', 'aphrodite', '데모용 랜딩', '이거 자랑할 거야'.
omd:showcase
Turn a rendered page (or several, side by side) into a scroll demo video — deterministic frame capture, ffmpeg H.264/GIF, labels per arm. Trigger: '시연 영상', '스크롤 영상 만들어', 'showcase', 'demo video', '비교 영상', 'record the page'.