html-artifacts

A guide for producing self-contained HTML documents when content benefits from layout, colour, diagrams, interaction, or editing. It treats HTML as the finished document instead of using plain Markdown.

In plain words
What is it for?
Use it for reports, plans, specifications, explainers, comparisons, flowcharts, module maps, timelines, and other documents where visual layout or interaction matters.
Why use it?
It avoids flattening comparisons, diagrams, timelines, and interactive material into hard-to-read linear text. It helps make the structure of longer content visible.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 222 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,191 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 $0.00222 $0.02191
Opus 5 $0.00111 $0.01095
Sonnet 5 $0.00044 $0.00438
Haiku 4.5 $0.00022 $0.00219

Measured 2d ago against content hash fe18f0049290, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

skill/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HTML Artifacts

Markdown is the default agent output, but for anything longer than a handful of sentences it's a poor format. It can't show two options side by side, can't render a real diagram, can't be interactive, and can't be shared by link. HTML can do all of those — and when the artifact is the deliverable rather than something you'll skim and forget, the difference between "a document I'd skim" and "a document I'd actually read" is enormous.

The use cases below are not the only places HTML helps, but they cover most of the territory. The pattern in every category is the same: the agent picks a layout that makes the shape of the content visible, instead of flattening it into linear prose.

When to reach for HTML

Reach for HTML when any of the following is true. Don't wait for the user to ask explicitly.

  • Comparison. Two or more options/approaches/designs the reader needs to weigh against each other. Side-by-side beats stacked.
  • Spatial information. Diffs, call graphs, module maps, flowcharts, timelines, before/after — anything where position carries meaning.
  • Interaction matters. Animations, easing curves, parameter tuning, state transitions — things the reader needs to feel, not read about.
  • Reference material. A document the reader will navigate non-linearly: tabs, collapsible sections, glossary in the margin, jump links.
  • Color or hierarchy carries meaning. Severity tags, status colors, syntax highlighting, design tokens.
  • One-off editor. The reader needs to manipulate a thing (drag tickets, toggle flags, tune a prompt) and round-trip the result back into a prompt or a commit.
  • The reader will share it. A spec going to leadership, a PR writeup going to reviewers, a status report going to a team. People are dramatically more likely to actually read an HTML page than a markdown file.
  • Length. Anything longer than ~100 lines in markdown becomes hard to read. HTML's navigation and layout earn their keep past that threshold.

Read the full file on GitHub · 95 lines

Files

What ships with it

8 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. 2d ago First seen · 95 lines · 222 tokens per session scan A fe18f0049290

Subscribe to this mod's changes

html-artifacts is a skill published in the GitHub repository dogum/html-artifacts (140 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 222 tokens to every session and 2,191 once invoked, about $0.0011 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens