What is generative_ui?

A guide to rendering interactive HTML components directly in chat or as standalone files. These components can include diagrams, charts, controls, walkthroughs, and small interactive experiences.

Use it to create visualizations, educational interfaces, interactive controls, diagrams, and other rich web-based displays.

It provides a defined way to present information that is difficult to understand as plain text or static Markdown.

generative_ui — Skill for Claude Code and Codex by asgeirtj

About the project

System Prompts Leaks is a collection of captured system instructions used to guide AI chatbots and coding agents before they receive user messages. It serves researchers and developers studying how different AI assistants are directed.

asgeirtj/system_prompts_leaks · 70,884 stars · on GitHub

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.

Any agent

npx skills add asgeirtj/system_prompts_leaks --skill generative_ui

Clone the repo

git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/generative_ui/github.svg)](https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/generative_ui)

Your own site

<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/generative_ui"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/generative_ui/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/generative_ui"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/generative_ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,393 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00054	$0.01393
Opus 5.5	$0.00022	$0.00557
Sonnet 5.5	$0.00011	$0.00279
Haiku 4.5	$0.00005	$0.00139

Measured 7d ago against content hash e68549d8cece, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

generative_ui 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 7d 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.

Google/antigravity/skills/generative_ui/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generative UI

You can render custom, rich, interactive user interfaces (inline widgets or larger artifacts) directly in the chat. This is a great way to communicate complex information to the user, generate rich visualizations, and even create small interactive experiences for the user.

Workflow

Create the HTML Artifact: Use write_to_file to save a self-contained .html file (using Tailwind CSS and inline JavaScript) to the artifact directory. Set UserFacing: true in ArtifactMetadata.
Embed Inline (optional): Include the <agent-embed> tag in your chat response, if you decide this html artifact should be rendered inline in the
conversation:
```
<agent-embed src="file:///<artifact_path>/widget.html"></agent-embed>
```

Constraints & Theming

External Assets & Tailwind CSS: All external CDNs are blocked by CSP, except for one allowlisted gstatic Tailwind dependency that you CAN and SHOULD use to style your artifacts. Include the following script tag in your <head> to enable Tailwind:
```
<script src="https://www.gstatic.com/antigravity/web/dev/tailwindcss.min.js"></script>
```
Use Provided Theme Variables: The iframe injects the app's semantic design-system tokens, so widgets automatically match the host theme and the user's custom colors. Surfaces (--background, --content, --card, --sidebar), borders (--border), text (--foreground, --muted-foreground, --placeholder), and accents (--primary/--primary-foreground, --secondary/--secondary-foreground, --accent) are all available. Typography is applied for you on the document body — you do not need to set a font, and never use sub-12px micro-text (text-[10px], text-[11px], or CSS font-size below 12px; keep text-xs / 12px as the minimum floor unless the user asks).
Text & Surface Colors: Use semantic variables (bg-[var(--card)], text-[var(--foreground)], text-[var(--muted-foreground)]) instead of hardcoded dark/light utility classes (e.g., bg-slate-900, text-white) to ensure high contrast across both light and dark themes.
Do Not Declare Local Fallbacks on :root: Never define local color fallbacks on :root in a <style> block; the host environment manages theme variables dynamically.
HTML Boilerplate Template: Recommended base template:

Read the full file on GitHub · 121 lines

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.

7d ago First seen · 121 lines · 54 tokens per session scan A e68549d8cece

Subscribe to this mod's changes

generative_ui is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (70,884 stars, last pushed 2d ago), licensed CC0-1.0. It adds 54 tokens to every session and 1,393 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-30.

CSS and styling Claude Code Design and UX Frontend ai anthropic chatbot chatgpt claude

generative_ui next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
generative_uiasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	54	Claude Code, Codex
claude-designNousResearch/hermes-agent	Skill	261k	today	MIT	A	16	Claude Code, Codex
scrollcraftNousResearch/hermes-agent	Skill	261k	today	MIT	A	13	Claude Code, Codex
sketchNousResearch/hermes-agent	Skill	261k	today	MIT	A	18	Claude Code, Codex
impeccableNousResearch/hermes-agent	Skill	261k	today	MIT	A	18	Claude Code, Codex
auteurNousResearch/hermes-agent	Skill	261k	today	MIT	A	13	Claude Code, Codex
motion-systemOneWave-AI/open-agent-stack	Skill	5	2mo ago	MIT	A	58	Claude Code