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 yasirshabbirservices/Bricks-Builder-MCP --skill web-optimizationgit clone --depth 1 https://github.com/yasirshabbirservices/Bricks-Builder-MCPWrote 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/yasirshabbirservices/bricks-builder-mcp/web-optimization)<a href="https://agentmods.dev/skills/yasirshabbirservices/bricks-builder-mcp/web-optimization"><img src="https://agentmods.dev/badge/skills/yasirshabbirservices/bricks-builder-mcp/web-optimization/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/yasirshabbirservices/bricks-builder-mcp/web-optimization"><img src="https://agentmods.dev/badge/skills/yasirshabbirservices/bricks-builder-mcp/web-optimization.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 | $0.00000 | $0.01418 |
| Opus 5.5 | $0.00000 | $0.00567 |
| Sonnet 5.5 | $0.00000 | $0.00284 |
| Haiku 4.5 | $0.00000 | $0.00142 |
Grade A, and why
web-optimization 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 2mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Optimization — Accessibility, SEO, AEO & GEO
Use this skill when building, reviewing, or optimizing any page, template, or component for accessibility, search engine visibility, answer engine presence, or generative AI discoverability. Read the relevant reference file before starting work in that area.
Quick Rules (apply to EVERY page and component)
Accessibility — every user matters
Accessibility is not an afterthought or a checklist to run at the end. Build it into every element from the start.
- Every image needs meaningful
alttext (oralt=""if purely decorative) — set via Bricks element settings or_attributes - Every interactive element must be keyboard-accessible — focus states are required, not optional
- Color contrast must meet WCAG AA minimum: 4.5:1 for normal text, 3:1 for large text. The dark theme with orange accent needs careful checking — orange on dark backgrounds can fail contrast
- Use semantic HTML elements:
<nav>,<main>,<article>,<section>,<aside>,<header>,<footer>— Bricks lets you set the tag on containers - Heading hierarchy must be logical: one
<h1>per page, never skip levels (h1 → h3 is wrong) - Form inputs need associated
<label>elements oraria-labelattributes - Links must have descriptive text — never "click here" or bare URLs
- Touch targets minimum 44x44px on mobile
- Animations must respect
prefers-reduced-motion— wrap motion in@media (prefers-reduced-motion: no-preference) - Read
references/accessibility.mdfor the full WCAG checklist and Bricks-specific patterns
SEO — be found by search engines
Technical SEO is infrastructure. Get it right once and every page benefits.
- Every page needs a unique
<title>andmeta description— set via Yoast/RankMath or Bricks page settings - Use proper heading hierarchy for content structure — search engines use headings to understand page organization
- Structured data (JSON-LD) for local business, products, reviews, FAQ, breadcrumbs — WordPress plugins can handle most of this, but verify output
- Images need descriptive filenames (
screen-protector-9h-tempered.webpnotIMG_4521.jpg),alttext, and modern formats (WebP/AVIF with fallback) - Core Web Vitals: LCP under 2.5s, INP under 200ms, CLS under 0.1 — lazy-load below-fold images, preload above-fold, minimize layout shifts
- Internal linking between related content — every page should be reachable within 3 clicks
- Mobile-first indexing: Google indexes the mobile version — test mobile layout thoroughly
- Read
references/seo.mdfor technical SEO checklist, structured data schemas, and WordPress/Bricks specifics
What ships with it
3 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.
- 2mo ago First seen · 85 lines · 0 tokens per session scan A eff54c9c5549
web-optimization is a skill published in the GitHub repository yasirshabbirservices/Bricks-Builder-MCP (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,418 tokens. 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
cdp
Visual verification of a running page through Chrome's DevTools Protocol, capturing screenshots and measuring the rendered DOM. Use when a frontend change can only be confirmed once rendered, for layout, spacing, alignment, overflow, or theme tokens.
enhance-web-landing
Build landing pages, portfolios, and marketing sites that don't look AI-generated. Use for "landing page", "portfolio", "marketing site", "anti-slop", "Awwwards-style", "premium frontend", or a design that needs a point of view.
enhance-web-ux
NN/g-grounded fix of one existing page's flows. Use when "fix UX of /xxx" or "improve information density". Repo-wide slop plan → plan-antislop. Composition/type → enhance-web-ui. Reading level → enhance-readability. Heuristics only → audit-ux.
enhance-capacitor-ui
Separate desktop and mobile UI in hybrid apps shipped as PWA + iOS + Android (Capacitor, Tauri, Expo Web, Ionic, RN-Web). Use when a UI sweep "improved one surface and broke the other": desktop polished but mobile cramped, or the reverse.
enhance-web-ui
Polish an existing page's hierarchy, spacing, type, and visual personality. Use when "make this page polished/premium", "less crowded", or "better visual hierarchy". Readability → enhance-readability. Flow/IA → enhance-web-ux.
audit-uiux-design-system
Audit visual-system coherence: tokens, component variants, color, type, spacing, dark mode. Use for "design drift", inconsistent UI, or duplicate primitives. Per-page usability → audit-ux. Plan-only unification → plan-uiux-unification.