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/psd401/psd-claude-plugins/html-artifactnpx skills add psd401/psd-claude-plugins --skill html-artifactgit clone --depth 1 https://github.com/psd401/psd-claude-pluginsWrote 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/psd401/psd-claude-plugins/html-artifact)<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/html-artifact"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/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 | $0.00136 | $0.02005 |
| Opus 5 | $0.00068 | $0.01002 |
| Sonnet 5 | $0.00027 | $0.00401 |
| Haiku 4.5 | $0.00014 | $0.00200 |
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 3d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML Artifact
Produce a single, self-contained HTML file with impeccable taste. HTML beats Markdown for specs, reports, reviews, and explorations: it is denser, more readable, more shareable, and people actually read it. This skill makes HTML that does not look like a machine made it.
The one rule everything serves
If someone could look at the output and say "AI made that" without a doubt, it failed.
Recognizability over default aesthetics. Every choice below exists to defeat the
"visual maximum common denominator" of AI training data (Inter + purple gradient +
beige/brass + eyebrow-on-every-section + ghost cards). Read references/anti-slop-bans.md
to know exactly what those tells are and how to refuse them.
Workflow
Run these in order. Skip nothing in steps 1, 7, and 8.
1. Emit a design read (one line, before any code)
State your interpretation so the user can correct it cheaply:
Reading this as:
<page kind>for<audience>, with a<vibe>language, leaning toward<direction>.
Examples:
- "Reading this as: an internal engineering spec for the platform team, with a calm document language, leaning toward a two-column reading layout with a sticky TOC."
- "Reading this as: a consumer landing page for a coffee subscription, with a warm editorial language, leaning toward a split hero + one saturated accent."
Use AskUserQuestion ONLY if page-kind, audience, or output format is genuinely
ambiguous. Otherwise infer and proceed; the user can redirect after the design read.
2. Set three dials
Infer 1–10 values from the brief; they gate downstream choices:
DESIGN_VARIANCE(1 = perfect symmetry, 10 = artsy chaos)MOTION_INTENSITY(1 = static, 10 = cinematic)VISUAL_DENSITY(1 = airy, 10 = packed data)
Signal presets: minimalist/calm/editorial → ~5 / 3 / 3 · data report/dashboard → ~5 / 3 / 7 ·
marketing/agency → ~8 / 7 / 4 · public-sector/trust-first → ~3 / 2 / 5. When DESIGN_VARIANCE > 4,
do not use a centered hero — go split-screen, asymmetric, or left-aligned.
What ships with it
12 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/base-scaffold.html 4.3 KB
- assets/chart-snippets.html 8.7 KB
- references/anti-slop-bans.md 5.6 KB
- references/dashboard-patterns.md 4.2 KB
- references/data-viz.md 5.2 KB
- references/document-patterns.md 3.5 KB
- references/interactive-patterns.md 2.8 KB
- references/multivariant.md 2.0 KB
- references/preflight-audit.md 4.3 KB
- references/psd-branding.md 3.4 KB
- references/taste-core.md 6.3 KB
- scripts/open.sh 515 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.
- 3d ago First seen · 154 lines · 136 tokens per session scan A 46d64f0ba772
html-artifact is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 136 tokens to every session and 2,005 once invoked, about $0.0007 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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.
traceway-setup
Analyze and instrument repositories for Traceway observability. Use when the user wants to plan, add, migrate, or verify Traceway or OpenTelemetry monitoring for backend, browser, full-stack, mobile or iOS, or AI-agent software, including project topology and user-approved setup-plan creation. Backends use OTLP/HTTP…