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 PaulRBerg/agent-skills --skill html-playgroundgit clone --depth 1 https://github.com/PaulRBerg/agent-skillsWrote 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/paulrberg/agent-skills/html-playground)<a href="https://agentmods.dev/skills/paulrberg/agent-skills/html-playground"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/html-playground/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/paulrberg/agent-skills/html-playground"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/html-playground.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00500 |
| Opus 5 | $0.00015 | $0.00250 |
| Sonnet 5 | $0.00006 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
html-playground 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 9d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML Playground Builder
Build a self-contained interactive HTML explorer with controls, live preview, and a copyable natural-language prompt.
Workflow
- Infer the audience, decisions, and required states. Existing design systems and explicit requirements override these defaults.
- Read exactly one closest template and adapt it:
templates/design-playground.mdtemplates/data-explorer.mdtemplates/concept-map.mdtemplates/document-critique.mdtemplates/diff-review.mdtemplates/code-map.md
- Write one HTML file with inline CSS and JavaScript and no external runtime dependencies.
- Open it in a desktop browser, interact with every control and preset, and verify live preview, prompt output, copy feedback, empty/error states, and keyboard usability. Fix rendered defects before completion.
Opinionated Defaults
Use these when product context does not indicate otherwise:
- controls beside a live preview, with prompt output below;
- a desktop-browser layout; do not implement or inspect responsive/mobile behavior unless requested;
- a polished light theme, system UI font, monospace code/values, minimal chrome;
- sensible non-empty initial state and 3–5 cohesive named presets;
- one state object, one update path, and immediate preview/prompt refresh;
- controls grouped by concern, with advanced controls collapsed;
- prompt text that explains the desired outcome in natural language and mentions only non-default choices.
Invariants
- No Apply button: relevant changes render immediately.
- The prompt is actionable without seeing the playground and is not a raw state dump.
- Copy has visible transient feedback and a usable fallback when the Clipboard API fails.
- Standardize copy microcopy as
Copy prompt, thenCopied; on failure showCopy failed — select the prompt below. - Presets update controls, preview, and prompt consistently.
- Do not add controls that do not affect either the preview or the generated prompt.
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.
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.
- 9d ago First seen · 51 lines · 30 tokens per session scan A dca22befb7f5
html-playground is a skill published in the GitHub repository PaulRBerg/agent-skills (70 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 500 once invoked, about $0.0002 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
webgl-particle-galaxy
A real-time particle galaxy — tens of thousands of additive-blended GPU points spiraling around a bright core, their orbits solved entirely in the vertex shader (from glVertexID), so the whole cloud draws in one call. Rendered as a single self-contained index.html. Use when the brief asks for a "particle field"…
webgl-liquid-metal
A real-time liquid-metal shader — a domain-warped noise field shaded as molten chrome, with a sweeping specular highlight over an iridescent thin-film (cosine-palette) sheen. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "liquid metal", "molten chrome", "iridescent"…
webgl-neon-grid
A real-time synthwave scene — a perspective floor grid scrolling toward a banded retro sun under a neon starfield, all from one fragment shader. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "synthwave", "outrun", "retro 80s", "neon grid", "perspective grid", "vaporwave", or…
webgl-depth-gallery
A scroll-reactive 3D image gallery in Three.js: Z-stacked images crossfade over per-image mood backgrounds with velocity breath, a glowing cursor trail and an editorial CMYK/RGB/HEX/PMS color card.
webgl-horizontal-parallax
A horizontal-scroll WebGL gallery (Three.js): frames glide sideways with lerp smoothing and each image parallaxes its texture (UV shift) by its position in the viewport.
webgl-distortion-grain
A vertical gallery (Three.js) where planes bend with scroll velocity, ripple under the cursor via simplex noise, and carry a film grain.