html-artifact-guide

html-artifact-guide is a skill for Claude Code from ClawEnable/html-artifact-best-practices. It costs 62 tokens per session (1,542 once invoked), scanned A, original, Apache-2.0.

A guide for creating, reviewing, and improving standalone HTML files with inline CSS and plain JavaScript. These are self-contained web pages that can be shared without a build system or external libraries.

In plain words
What is it for?
Use it for comparison tables, dashboards, timelines, visual explainers, research summaries, and interactive checklists.
Why use it?
It helps decide when HTML is useful and checks that interactive pages remain readable, accessible, and reviewable.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the clawenable plugin — 1 skill shipped together

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.

agentmods
npx agentmods add skills/clawenable/html-artifact-best-practices/html-artifact-guide
Any agent
npx skills add ClawEnable/html-artifact-best-practices --skill html-artifact-guide
Clone the repo
git clone --depth 1 https://github.com/ClawEnable/html-artifact-best-practices

Made for: Claude Code.

Or install clawenable, the plugin that ships this one along with the rest of its 1 skill.

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-artifact-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/clawenable/html-artifact-best-practices/html-artifact-guide.svg)](https://agentmods.dev/skills/clawenable/html-artifact-best-practices/html-artifact-guide)
Your own site
<a href="https://agentmods.dev/skills/clawenable/html-artifact-best-practices/html-artifact-guide"><img src="https://agentmods.dev/badge/skills/clawenable/html-artifact-best-practices/html-artifact-guide.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,542 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00062 $0.01542
Opus 5 $0.00031 $0.00771
Sonnet 5 $0.00012 $0.00308
Haiku 4.5 $0.00006 $0.00154

Measured 5d ago against content hash 7a18a18c7e65, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

html-artifact-guide 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.

skills/html-artifact-guide/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HTML Artifact Best Practices

Produce readable, interactive, shareable, and reviewable single-file HTML artifacts. Avoid treating HTML as a visual wrapper for Markdown or as a substitute for proper frontend engineering.

Purpose

This skill covers four capabilities:

  1. Judge — Decide whether HTML is appropriate, or whether Markdown suffices.
  2. Create — Generate standalone single-file HTML artifacts using inline CSS and vanilla JS.
  3. Review — Audit existing HTML artifacts for quality, accessibility, and anti-patterns.
  4. Improve — Refine information architecture, interaction quality, and remove decorative waste.

This skill does NOT use React, Vue, Tailwind, Vite, shadcn/ui, or any framework. If the task requires complex multi-component UIs with state management, use the web-artifacts-builder skill instead. These skills are complementary, not interchangeable.

When to Use

Use this skill when:

  • Multi-option comparison with filtering, collapsing, or side-by-side layout
  • Interactive reports, dashboards, or visual explanations
  • Decision support pages with risk matrices or priority sorting
  • Roadmap or timeline views for team review
  • Research synthesis requiring non-linear navigation
  • Review surfaces for multi-round agent collaboration outputs
  • Any output where the user needs to scan, compare, filter, or interact

Do NOT use this skill when:

  • Short explanations, notes, or documentation
  • Long-term knowledge base articles
  • Content needing frequent human editing
  • Content primarily consumed by other agents or tools
  • Simple tables and lists that Markdown handles well
  • Meeting minutes without visual complexity

Decision Rule

Before generating HTML, apply this decision flow:

  1. Does the task involve human review, comparison, interaction, or sharing?
    • No → Use Markdown. Stop here.
    • Yes → Continue.
  2. Is Markdown sufficient for the user's goal?
    • Yes → Use Markdown. Explain why.
    • No → Use HTML artifact. Continue to creation workflow.

Read the full file on GitHub · 117 lines

Files

What ships with it

4 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.

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. 5d ago First seen · 117 lines · 62 tokens per session scan A 7a18a18c7e65

Subscribe to this mod's changes

html-artifact-guide is a skill published in the GitHub repository ClawEnable/html-artifact-best-practices (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,542 once invoked, about $0.0003 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.