html-artifacts

html-artifacts is a skill for Claude Code, Codex from joshuadavidthomas/agent-skills. It costs 112 tokens per session (2,162 once invoked), scanned A, original, MIT.

A guide for creating standalone HTML documents such as reports, interactive explainers, visual walkthroughs, and slide decks.

In plain words
What is it for?
Use it when turning research or codebase findings into a self-contained HTML file with inline styles, scripts, data, and essential assets.
Why use it?
It sets requirements for grounding the document in source material, keeping it usable offline, and ensuring the main explanation works without interaction.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when turning research or codebase findings into a self-contained HTML file with inline styles, scripts, data, and essential assets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/joshuadavidthomas/agent-skills/html-artifacts
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.

Any agent
npx skills add joshuadavidthomas/agent-skills --skill html-artifacts
Clone the repo
git clone --depth 1 https://github.com/joshuadavidthomas/agent-skills

Made for: Claude Code, Codex.

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-artifacts

README.md
[![agentmods](https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/html-artifacts.svg)](https://agentmods.dev/skills/joshuadavidthomas/agent-skills/html-artifacts)
Your own site
<a href="https://agentmods.dev/skills/joshuadavidthomas/agent-skills/html-artifacts"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/html-artifacts.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,162 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00112 $0.02162
Opus 5 $0.00056 $0.01081
Sonnet 5 $0.00022 $0.00432
Haiku 4.5 $0.00011 $0.00216

Measured 8d ago against content hash e9a635525f30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

html-artifacts 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/inline-components.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

html-artifacts/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HTML Artifacts

Generate a visual document that earns its use of HTML: the result should be easier to look at, compare, or manipulate than prose alone. Default to a self-contained local .html document, not a website, dashboard, or slide deck.

Non-Negotiables

  • Ground first. Read the source material and trace the relevant behavior before designing the artifact.
  • Default to document mode. The artifact must stand on its own for an asynchronous reader. Use presentation mode only when explicitly requested or clearly intended for a live talk.
  • Keep the static story complete. Interaction may deepen the explanation; it must not be required to discover the main conclusion.
  • Make interaction answer a question. Every control must satisfy: reader question → action → immediate visible answer. Remove controls that do not.
  • Produce one true offline file by default. Inline CSS, JavaScript, SVG, data, and essential assets. Do not rely on CDNs, remote fonts, fetch, or a server.
  • Keep it local unless asked. Artifacts may expose source code, architecture, or review findings. Do not publish, upload, or create a public URL without explicit permission.
  • Validate the final file in a browser. Do not call an artifact finished from source inspection alone.

Choose the Mode

Mode Use for Shape
Document (default) Codebase, feature, PR, plan, incident, or research explanation Scrollable, skimmable, complete prose, stable anchors, citations, print-friendly
Explorable document Causal mechanisms, parameter tradeoffs, before/after states, coupled representations Complete default state plus a few local controls with immediate feedback
Presentation A live walkthrough where a speaker supplies context One idea per view, keyboard navigation, explicit progress, speaker notes or captions

If HTML adds no useful spatial comparison, diagram, or interaction, say so. If the user explicitly requested HTML, honor the request and make a restrained document rather than inventing spectacle.

Read the full file on GitHub · 167 lines

Files

What ships with it

7 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. 8d ago First seen · 167 lines · 112 tokens per session scan A e9a635525f30

Subscribe to this mod's changes

html-artifacts is a skill published in the GitHub repository joshuadavidthomas/agent-skills (50 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 2,162 once invoked, about $0.0006 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.

Related

Other skills, from other repositories