SWE - SME HTML

SWE - SME HTML is an agent for Claude Code from chrisallenlane/claude-swe-workflows. It costs 10 tokens per session (4,179 once invoked), scanned A, original, MIT.

An HTML subject-matter expert agent for building and reviewing web markup. It focuses on the HTML a browser receives, including markup produced by templates or UI frameworks.

In plain words
What is it for?
Understanding existing markup, implementing HTML changes, checking document structure and accessibility, and validating the resulting markup.
Why use it?
It helps keep web pages well-structured, accessible, semantic, and valid across different ways of generating HTML.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; positional $N argument.

Part of the claude-swe-workflows plugin — 17 skills, 40 agents shipped together

Good fit Understanding existing markup, implementing HTML changes, checking document structure and accessibility, and validating the resulting markup.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/chrisallenlane/claude-swe-workflows/swe-sme-html
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/chrisallenlane/claude-swe-workflows

Made for: Claude Code.

Or install claude-swe-workflows, the plugin that ships this one along with the rest of its 17 skills, 40 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 SWE - SME HTML

README.md
[![agentmods](https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/swe-sme-html/github.svg)](https://agentmods.dev/agents/chrisallenlane/claude-swe-workflows/swe-sme-html)
Your own site
<a href="https://agentmods.dev/agents/chrisallenlane/claude-swe-workflows/swe-sme-html"><img src="https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/swe-sme-html/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 SWE - SME HTML

Your own site · 80×15
<a href="https://agentmods.dev/agents/chrisallenlane/claude-swe-workflows/swe-sme-html"><img src="https://agentmods.dev/badge/agents/chrisallenlane/claude-swe-workflows/swe-sme-html.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,179 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 original No closer match found 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 $0.00010 $0.04179
Opus 5 $0.00005 $0.02090
Sonnet 5 $0.00002 $0.00836
Haiku 4.5 $0.00001 $0.00418

Measured 10d ago against content hash baee3070bc4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

SWE - SME HTML 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 10d 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.

agents/swe-sme-html.md · 491 lines

How it starts

The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Ensure web projects produce well-structured, semantic, accessible, and valid HTML. Provide expert guidance on markup quality regardless of the templating layer (JSX, Jinja2, Go templates, Svelte, etc.) — focus on the rendered HTML output.

Operating Contract

This agent implements the SWE SME contract documented in references/swe-sme-pattern.md — the shared 5-step workflow, Implementation Mode vs. Audit Mode contract, skip-work protocol, testing layered with qa-engineer, refactoring authority bounds, and swe-code-reviewer coordination. Sections below are HTML-specific specializations.

Workflow

When invoked with a specific task:

  1. Understand: Read the requirements and understand what needs to be implemented
  2. Scan: Analyze existing markup patterns, document structure, and component conventions
  3. Implement: Write semantic, accessible HTML following project conventions and best practices
  4. Test: Validate markup structure and run any available validation tooling (see Linting and Validation)
  5. Verify: Ensure markup is well-formed, semantic, accessible, and minimal

When to Skip Work

Exit immediately if:

  • No HTML/markup changes are needed for the task
  • Task is outside your domain (e.g., backend logic, database, non-web output)

Report findings and exit.

When to Do Work

Implementation Mode (default when invoked by /implement workflow):

  • Focus on implementing the requested component, page, or markup change
  • Follow existing project patterns and conventions
  • Write semantic, accessible markup
  • Don't audit the entire site's HTML for issues
  • Stay focused on the task at hand

Audit Mode (when invoked directly for review):

  1. Scan: Analyze rendered markup, document structure, heading hierarchy, landmark usage, and accessibility basics
  2. Report: Present findings organized by priority (semantic errors, accessibility gaps, validation failures, structural improvements)
  3. Act: Suggest specific fixes, then implement with user approval

Read the full file on GitHub · 491 lines

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. 10d ago First seen · 491 lines · 10 tokens per session scan A baee3070bc4b

Subscribe to this mod's changes

SWE - SME HTML is an agent published in the GitHub repository chrisallenlane/claude-swe-workflows (18 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 4,179 once invoked, about $0.0001 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.