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.
npx agentmods add skills/bahayonghang/my-ai-cli-toolkit/html-artifactnpx skills add bahayonghang/my-ai-cli-toolkit --skill html-artifactgit clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkitWrote 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.
[](https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/html-artifact)<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/html-artifact"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/html-artifact.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.04207 |
| Opus 5 | $0.00040 | $0.02103 |
| Sonnet 5 | $0.00016 | $0.00841 |
| Haiku 4.5 | $0.00008 | $0.00421 |
Grade A, and why
html-artifact 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.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML Artifact
Create a browser-viewable HTML artifact when complex work needs a richer review surface than a wall of Markdown. Default to one self-contained file; use a split bundle when the planned content is too large for a reviewable single page.
Core rule
Use HTML artifacts for complex, visual, comparison-heavy, reviewable, or shareable outputs. Keep ordinary Markdown for short answers, simple commands, commit messages, tiny summaries, and routine implementation reports unless the user explicitly asks for an artifact.
Output contract
Every artifact must be:
- Single-file by default; split bundle when oversized: create one
.htmlor.htmfile unless the pre-build size gate says to split. When split, createdocs/artifacts/<slug>/index.htmlplus self-contained part pages such aspart-01-overview.html. - Self-contained: no CDN, remote fonts, remote stylesheets, remote scripts,
fetch, XHR, beacons, WebSockets, or automatic network requests. - Offline per page: every split-bundle HTML page must independently include its own CSS and any small vanilla JS; do not share external assets between pages.
- Semantic: include
<!doctype html>,<html>,<head>,<meta charset="utf-8">,<meta name="viewport">,<title>,<main id="main">, and one clear<h1>. - Accessible: skip link, visible focus state, keyboard-operable controls, text alternatives for diagrams, color plus text for status, and
prefers-reduced-motionsupport. - Reviewable: structure content into navigable sections, cards, tables, timelines, or diagrams; do not dump raw long Markdown into a styled box.
- Navigable when split: split bundles must include an index page plus previous/next/back-to-index links on each part page.
- Free of unfinished placeholders: remove
[填这里], Lorem ipsum, TBD, and other fill-in markers before delivery. - Truthful about data: do not invent measurements, statistics, customers, sources, or outcomes.
- Explicit about missing data: mark a real gap as
[数据待补:说明]and explain what evidence is needed.
What ships with it
35 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.
- assets/components/badge.html 1.1 KB
- assets/components/checklist.html 2.0 KB
- assets/components/code-block.html 1.1 KB
- assets/components/comparison-table.html 1.2 KB
- assets/components/data-table.html 1.2 KB
- assets/components/details.html 1.5 KB
- assets/components/metric-card.html 1.8 KB
- assets/components/quote-card.html 974 B
- assets/components/timeline.html 1.9 KB
- assets/demo-all.html 33 KB
- assets/starter-template.html 42 KB
- assets/style-tokens.css 12 KB
- evals/evals.json 15 KB
- evals/README.md 5.1 KB
- references/accessibility-and-security.md 3.9 KB
- references/charts-cookbook.md 24 KB
- references/design-review-checklist.md 5.0 KB
- references/diagram-cookbook.md 34 KB
- references/interaction-cookbook.md 21 KB
- references/size-and-splitting.md 3.8 KB
- references/svg-cookbook.md 13 KB
- references/tables-cookbook.md 14 KB
- references/template-selection.md 3.7 KB
- references/templates/architecture-atlas.md 4.5 KB
- references/templates/component-specimen-sheet.md 1.6 KB
- references/templates/decision-matrix-studio.md 3.4 KB
- references/templates/evidence-dossier.md 3.5 KB
- references/templates/incident-timeline.md 2.4 KB
- references/templates/interactive-editor.md 2.0 KB
- references/templates/narrative-deck.md 1.8 KB
- references/templates/review-workbench.md 2.0 KB
- references/templates/status-brief.md 2.6 KB
- references/templates/strategy-blueprint.md 3.5 KB
- scripts/check_html_artifact.py 18 KB runs code
- tests/check-html-artifact.test.mjs 17 KB runs code
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.
- 5d ago First seen · 253 lines · 80 tokens per session scan A bebcc8000f24
html-artifact is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 4,207 once invoked, about $0.0004 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.
Other skills, from other repositories
html-report
Nested swiss-knife reference for standalone HTML deliverables. Produce polished, self-contained HTML deliverables (research memos, literature maps, dashboards, audit reports, side-by-side comparisons) that humans open in a browser or receive as Telegram/email attachments. Covers a standalone HTML skeleton, math…
reimagine-it
Content-Derived Design — reads existing HTML and writes a stronger standalone page from headings, facts, names, dates, numbers, links, emails, and colors already in that file. CLI: npx reimagine-it --auto -i page.html -o out.html; also variations, lock, and audit. Use when the user says /reimagine-it, "reimagine it"…
convert-checkout-page
Author checkout-page micro-copy + trust signals: order summary, form-field copy, bump slot, button label, guarantee restatement, and friction-reduction patterns. Emits brief + paste-ready HTML/CSS scaffold (payment-processor-agnostic). Use when the user needs a conversion-optimized checkout page where every word and…
Accessibility Audit Helper
Reviews UI code and components for WCAG 2.1 accessibility violations and provides specific fixes.
web-design
UI review against Web Interface Guidelines. Use when asked to review UI, check accessibility, or audit design.
claude-design
Design one-off HTML artifacts (landing, deck, prototype).