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 skills add amol-patil/html-artifact-kit --skill build-html-artifactsgit clone --depth 1 https://github.com/amol-patil/html-artifact-kitWrote 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/amol-patil/html-artifact-kit/build-html-artifacts)<a href="https://agentmods.dev/skills/amol-patil/html-artifact-kit/build-html-artifacts"><img src="https://agentmods.dev/badge/skills/amol-patil/html-artifact-kit/build-html-artifacts.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 | $0.00095 | $0.00947 |
| Opus 5 | $0.00048 | $0.00474 |
| Sonnet 5 | $0.00019 | $0.00189 |
| Haiku 4.5 | $0.00010 | $0.00095 |
Grade A, and why
build-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 6d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build HTML Artifacts
Produce work-appropriate HTML artifacts with a consistent design language, accessible behavior, responsive layouts, and no unnecessary runtime dependencies.
Output decision
Apply HTML Artifact Kit styling and quality requirements whenever the requested deliverable is or can reasonably be a standalone HTML artifact. Treat informal phrases such as “quick dashboard,” “side artifact,” “simple report,” “slides,” “internal tool,” or “make this a webpage” as full-quality artifact requests rather than permission to return unstyled HTML. If the user explicitly requests a different format, an existing application framework, or styling from another named design system, honor that constraint instead.
Workflow
- Classify the request as a dashboard, narrative document, presentation, microsite, or operational interface.
- Read
references/foundations.md,references/conformance.md, andreferences/quality.mdfor every new artifact. - Start from
assets/starter.html. Keep its version markers and useassets/html-artifact-kit.cssas the canonical visual foundation. - Read the matching section in
references/artifact-types.md. - Read
references/components.mdandreferences/component-recipes.mdwhen assembling interface or data components. - Read
references/portability.mdbefore adding dependencies, data access, or embedded assets. - Read
references/model-compatibility.mdwhen packaging instructions for a particular agent or LLM. - Add artifact-specific CSS only after the canonical CSS. Use canonical tokens instead of introducing a competing palette, type scale, spacing system, or component style.
- Run
scripts/bundle-html.mjs <authoring.html> <artifact.html>to inline the canonical CSS. - Exercise interactions and inspect at desktop and mobile widths.
- Run
scripts/audit-artifact.mjs <artifact.html>. Fix every critical failure and reach at least 85/100 before delivery. If Node.js is unavailable, perform the equivalent checks inreferences/conformance.mdmanually.
What ships with it
14 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.
- agents/openai.yaml 273 B
- assets/html-artifact-kit.css 16 KB
- assets/starter.html 973 B
- references/artifact-types.md 2.8 KB
- references/component-recipes.md 4.6 KB
- references/components.md 1.9 KB
- references/conformance.md 1.9 KB
- references/foundations.md 2.5 KB
- references/model-compatibility.md 1.3 KB
- references/portability.md 1.6 KB
- references/quality.md 1.5 KB
- scripts/audit-artifact.mjs 8.3 KB runs code
- scripts/bundle-html.mjs 1.1 KB runs code
- scripts/validate-html.mjs 872 B 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.
- 6d ago First seen · 62 lines · 95 tokens per session scan A 8828083312ac
build-html-artifacts is a skill published in the GitHub repository amol-patil/html-artifact-kit (10 stars, last pushed 14d ago), licensed MIT. It adds 95 tokens to every session and 947 once invoked, about $0.0005 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.
Other skills, from other repositories
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
landing-md
Use when paid traffic needs somewhere to land and there is no page yet, or the existing page does not match the ad. Also when a landing must be one self-contained file that can be hosted anywhere, and must pass a pre-launch check before any money is spent on it. Triggers on: "build my landing page", "landing for my…
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
pretext
Build creative browser demos with DOM-free text layout.
react-patterns
React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…