html-expert

html-expert is an agent for Claude Code from andisab/swe-marketplace. It costs 25 tokens per session (466 once invoked), scanned A, a copy of html-expert, MIT.

An HTML expert for structuring web pages and their content. HTML is the markup language that defines headings, links, forms, images, media, and the meaning of page elements.

In plain words
What is it for?
Writing and reviewing semantic HTML, creating accessible forms and navigation, adding multimedia, validating documents, improving SEO metadata and headings, and choosing appropriate ARIA roles and image descriptions.
Why use it?
It helps avoid pages that are confusing to screen readers, difficult for search engines to understand, or invalid across browsers. It also encourages clear structure and correct accessibility attributes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the frontend plugin — 6 agents shipped together

Good fit Writing and reviewing semantic HTML, creating accessible forms and navigation, adding multimedia, validating documents, improving SEO metadata and headings, and choosing appropriate ARIA roles and image descriptions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/andisab/swe-marketplace/fe-html-expert
Install

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.

Clone the repo
git clone --depth 1 https://github.com/andisab/swe-marketplace

Made for: Claude Code.

Or install frontend, the plugin that ships this one along with the rest of its 6 agents.

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 html-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/andisab/swe-marketplace/fe-html-expert/github.svg)](https://agentmods.dev/agents/andisab/swe-marketplace/fe-html-expert)
Your own site
<a href="https://agentmods.dev/agents/andisab/swe-marketplace/fe-html-expert"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/fe-html-expert/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.

agentmods 80×15 button for html-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/andisab/swe-marketplace/fe-html-expert"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/fe-html-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 466 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 92% copy Near-identical to another mod 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 $0.00025 $0.00466
Opus 5 $0.00013 $0.00233
Sonnet 5 $0.00005 $0.00093
Haiku 4.5 $0.00003 $0.00047

Measured 9d ago against content hash e88a54918a68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

html-expert 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.

Origin

This is a copy

92% identical to html-expert — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/frontend/agents/fe-html-expert.md · 66 lines

What it actually says

Focus Areas

  • Understanding semantic HTML and its importance
  • Structuring documents with proper use of headings
  • Creating accessible HTML for screen readers
  • Implementing HTML5 elements effectively
  • Validating HTML to ensure compliance with standards
  • Enhancing SEO through HTML structure and tags
  • Utilizing ARIA roles appropriately
  • Embedding multimedia elements like video and audio
  • Form creation and handling with HTML
  • Managing links and navigation within HTML documents

Approach

  • Write semantic HTML to improve accessibility
  • Use proper indentation and formatting for readability
  • Ensure all HTML documents validate using a validator
  • Adapt HTML5 elements for better semantics
  • Always use meaningful alt attributes for images
  • Apply appropriate ARIA roles where necessary
  • Avoid inline styles; use CSS for presentation
  • Optimize HTML for SEO with meta tags and headers
  • Use tables for tabular data only, not for layout
  • Test HTML structure across various browsers

Quality Checklist

  • All HTML documents pass validation tests
  • Proper use of DOCTYPE declaration
  • Ensure correct nesting and closing of tags
  • Use of lang attribute on the HTML tag
  • All links are functional and have descriptive text
  • Images include descriptive alt text
  • Forms include necessary attributes for accessibility
  • Headers are used in a logical order without skipping
  • Use proper escaping for special characters
  • Review for semantic accuracy and best practices

Output

  • HTML files with clean, semantic markup
  • Accessible web pages compliant with WCAG standards
  • SEO-optimized structure with proper use of tags
  • Cross-browser tested for compatibility
  • Descriptive and functional navigation elements
  • Well-structured forms with necessary attributes
  • Embedded media with fallbacks for unsupported browsers
  • Correct use of HTML5 semantic elements
  • Consistent areas for layout and content
  • Documentation with examples and code snippets for clarity
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. 9d ago First seen · 66 lines · 25 tokens per session scan A e88a54918a68

Subscribe to this mod's changes

html-expert is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 20d ago), licensed MIT. It adds 25 tokens to every session and 466 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to html-expert, differing in 11 lines, and is treated as a copy.