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 skills add ivy00johns/Skill-Madness --skill class-extraction-guardgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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/ivy00johns/skill-madness/class-extraction-guard)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/class-extraction-guard"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/class-extraction-guard/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.
<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/class-extraction-guard"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/class-extraction-guard.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00218 | $0.01689 |
| Opus 5 | $0.00109 | $0.00844 |
| Sonnet 5 | $0.00044 | $0.00338 |
| Haiku 4.5 | $0.00022 | $0.00169 |
Grade A, and why
class-extraction-guard 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 9d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
class-extraction-guard
What this is
A deterministic, parse-once gate that flags utility-class soup: the same long
run of utility classes pasted inline across many call-sites instead of extracted
into a named class (@apply / a CSS component) or a shared UI component.
It exists because of a real gap. design-token-guard checks which values
styling uses — it catches a hardcoded #07090c that should be var(--token). But
a string like flex items-center gap-1.5 text-bone-faint hover:text-rune uses
perfectly valid tokens, so design-token-guard passes it by construction. Repeat
that string 9× across the codebase and you have a maintenance problem the value
gate was never built to see. And because the repeated version renders
identically to an extracted one, the pixel gates (render-sanity, ux-review)
can't see it either. The duplication lives only in source — exactly in the seam
between the value gate and the pixel gates. This is the missing organization
gate that closes that seam.
| gate | reads | catches |
|---|---|---|
| render-sanity / ux-review | pixels | broken pages, dead links, stale data, visual regressions |
| design-token-guard | source | hardcoded colors / inline styles bypassing the token system |
| class-extraction-guard | source | the same utility combo repeated inline instead of extracted |
None subsumes the others. A UI build wants all three.
Quick start
# Human-readable report
python3 ~/.claude/skills/class-extraction-guard/scripts/check_class_extraction.py --root .
# JSON for a gate (same gate contract as design-token-guard: exit codes +
# .summary.errors / .summary.warnings — the JSON key shapes differ)
python3 ~/.claude/skills/class-extraction-guard/scripts/check_class_extraction.py --root . --json
# -> { "summary": { "errors": 0, "warnings": 12, "files_scanned": 98 },
# "findings": [ { "rule": "...", "file": "...", "line": 93, "count": 9,
# "string": "...", "occurrences": [...], "suggestion": "..." } ] }
What ships with it
8 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.
- 9d ago First seen · 125 lines · 218 tokens per session scan A cbb7b7342e3c
class-extraction-guard is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed yesterday), licensed MIT. It adds 218 tokens to every session and 1,689 once invoked, about $0.0011 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.
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…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
waitlist-page
A simple waitlist page for collecting email addresses from people interested in a new product or early-access release.
tailwindcss
Tailwind CSS v4 conventions — semantic design tokens for theme-safe styling, mobile-first responsive layouts, and v4-first utilities. Use when styling components or writing className utilities with Tailwind. Don't use for plain CSS, CSS-in-JS (styled-components, emotion), or other utility frameworks.