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/roninforge/roninforge-tailwind-v4/tw-validatenpx skills add RoninForge/roninforge-tailwind-v4 --skill tw-validategit clone --depth 1 https://github.com/RoninForge/roninforge-tailwind-v4Wrote 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/roninforge/roninforge-tailwind-v4/tw-validate)<a href="https://agentmods.dev/skills/roninforge/roninforge-tailwind-v4/tw-validate"><img src="https://agentmods.dev/badge/skills/roninforge/roninforge-tailwind-v4/tw-validate.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 5.1 | $0.00035 | $0.00968 |
| Opus 5 | $0.00017 | $0.00484 |
| Sonnet 5 | $0.00007 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
tw-validate 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Tailwind v4 Project
When to Use
Use this skill when:
- Verifying a project is fully migrated to Tailwind v4
- Checking for v3 patterns that may have been missed during migration
- Auditing a project before deployment to catch Tailwind issues
- A project is behaving unexpectedly and version mixing may be the cause
Instructions
-
Determine the project's Tailwind version by reading
package.json. Look for:tailwindcssversion (v4.x confirms v4)- Presence of
@tailwindcss/viteor@tailwindcss/postcss(confirms v4 tooling) - Presence of
autoprefixer(unnecessary in v4, suggests incomplete migration) - Presence of
postcss-import(unnecessary in v4)
-
Check the CSS entry point for version indicators:
@import "tailwindcss"= v4 syntax (correct)@tailwind base; @tailwind components; @tailwind utilities;= v3 syntax (needs migration)- Both present = version mixing (critical issue)
-
Check for
tailwind.config.jsortailwind.config.ts:- If it exists AND the CSS uses
@import "tailwindcss": check if@configdirective is present in CSS - If
@configis missing: the JS config is being ignored (likely a bug) - If
@configis present: this is a valid migration bridge, but flag for future conversion to@theme
- If it exists AND the CSS uses
-
Check PostCSS config:
- Should contain only
@tailwindcss/postcss(or no PostCSS if using Vite plugin) - Flag
autoprefixer,postcss-import,postcss-nestingas unnecessary
- Should contain only
-
Search all template files for deprecated v3 patterns. For each pattern found, report the file, line number, and suggested fix:
Critical (will break or produce wrong output):
bg-opacity-*,text-opacity-*,border-opacity-*,divide-opacity-*,ring-opacity-*,placeholder-opacity-*!at beginning of class names (should be at end in v4)[--for arbitrary CSS variables (should be(--in v4)
High (renamed classes - may produce unexpected output):
shadow-sm(should beshadow-xs)blur-sm(should beblur-xs)rounded-sm(should berounded-xs)outline-none(preferoutline-hiddenfor accessibility;outline-nonestill works)overflow-ellipsis(should betext-ellipsis)flex-grow/flex-shrink(should begrow/shrink)
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.
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.
- 5d ago First seen · 77 lines · 35 tokens per session scan A eaff2d9d2ccd
tw-validate is a skill published in the GitHub repository RoninForge/roninforge-tailwind-v4 (2 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 968 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
Responsive Layout Reviewer
Reviews HTML/CSS or component code for responsive design issues across mobile, tablet, and desktop breakpoints.
uikit-expert
Write, review, or improve UIKit code following best practices for view controller lifecycle, Auto Layout, collection views, navigation, animation, memory management, and modern iOS 18–26 APIs. Use when building new UIKit features, refactoring existing views or view controllers, reviewing code quality, adopting modern…
tinted-ui-tokens-skills
从一个品牌色生成完整、可直接上线的设计 Token 系统：让每一个中性表面（背景、边框、文字、阴影、语义色、渐变、图标、暗色模式）都带上一小撮品牌色的温度，而不是使用纯中性色。当用户想用品牌色 / hex 生成、构建或设计 UI 颜色 Token、设计系统、CSS 变量、染色配色或品牌主题，或想通过修正扁平中性色让现有 UI 显得更高级时使用。触发语示例：给我生成一套设计Token、用这个品牌色出一套配色、UI颜色太廉价了、生成染色中性色系统、build a design system from #XXXXXX、tinted neutral palette。.
premium-ui-craft
Linear/Stripe/Apple-grade UI craft. Use for Product Designer / @Design, dashboards, shadcn, or generic SaaS UI.
Dark Mode Testing Patterns
Systematic dark mode testing covering color contrast, theme switching, persistence, media query respect, component-level theming, and image adaptation.
compose-modernize-build
Modernize an Android project's Gradle build: bump to Kotlin 2.x with kotlin-compose plugin (replace kotlinCompilerExtensionVersion), migrate kapt to KSP, introduce Version Catalogs (libs.versions.toml), use the Compose BOM, switch to Material 3.