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 bearlike/Assistant --skill generative-uigit clone --depth 1 https://github.com/bearlike/AssistantWrote 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/bearlike/assistant/generative-ui)<a href="https://agentmods.dev/skills/bearlike/assistant/generative-ui"><img src="https://agentmods.dev/badge/skills/bearlike/assistant/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.
<a href="https://agentmods.dev/skills/bearlike/assistant/generative-ui"><img src="https://agentmods.dev/badge/skills/bearlike/assistant/generative-ui.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 | $0.00048 | $0.01117 |
| Opus 5.5 | $0.00019 | $0.00447 |
| Sonnet 5.5 | $0.00010 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00112 |
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 1mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generative UI panels
present_ui displays a static, allowlisted, no-code panel. Call it directly; it
is not a widget or an app.
Choose the smallest surface
| Need | Use |
|---|---|
| An explanation, conclusion, or short list | Plain prose |
| A small comparison that reads well as text and needs no visual grouping | A markdown table |
| Information already in hand that benefits from status, cards, grouped fields, or a compact visual summary | present_ui |
| A chart, interactive controls, or a custom interactive display | Delegate to st-widget-builder; its Streamlit widget runs code in a browser sandbox |
| A durable surface with its own data and pipelines | Delegate to app-builder |
A panel lays out known information with fixed components. It does not fetch data, run code, accept input, or become a durable application.
The call
Three arguments, all top level. root is a list; there is no wrapper object
around it.
{
"summary": "Release checks for main",
"root": [
{"component": "Heading", "value": "Release checks", "level": 2},
{
"component": "Card",
"title": "Current status",
"children": [
{"component": "Badge", "label": "Ready", "status": "success"},
{
"component": "KeyValue",
"items": [
{"label": "Tests", "value": "Passed"},
{"label": "Review", "value": "Complete"}
]
},
{"component": "Alert", "body": "No remaining blockers.", "variant": "info"}
]
}
]
}
Every node is flat: component names the type, and that type's fields sit
beside it on the same object. Only Card and Stack accept children.
Component vocabulary
The present_ui description carries it, flat, and that copy is the only one.
It is derived from the same models that validate your call, so it lists every
component with its required and optional fields and cannot be out of date. Read
it there rather than expecting a list here — a second copy in this file could
only ever be older.
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.
- 1mo ago First seen · 112 lines · 48 tokens per session scan A 629d36c06995
generative-ui is a skill published in the GitHub repository bearlike/Assistant (44 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 1,117 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 2026-08-30.
Other skills, from other repositories
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
pr-screenshot-comparison
Create clear, polished before-and-after screenshots from the actual running product for a GitHub pull request. Use when a UI change needs visual proof: capture matching product states, crop to the relevant UI, stitch and caption one comparison image, attach it natively to the PR, and keep the image out of the…
typography
Apply professional typography principles to create readable, hierarchical, and aesthetically refined interfaces. Use when setting type scales, choosing fonts, adjusting spacing, designing text-heavy layouts, implementing dark mode typography, or when asked about readability, font pairing, line height, measure…
clean-copy
Cut interface copy that should not exist. Captions that restate a label, hints that pre-empt a worry the user never had, warnings that are scar tissue from a fixed bug. Use when writing or reviewing any user-facing string (labels, hints, empty states, toasts, confirmations, button text), or when asked to clean up or…
design-ui-style-guide
Create a visual system for a new or redesigned user interface. Generate exactly three image concepts and stop for user approval. After approval, create an HTML and CSS style guide with a representative demo. Do not use when the user supplies an approved design, requests a small edit, or skips visual exploration.
skill-icon-workflow
Create, update, or validate Codex skill icons. Use this skill for the small SVG, the 100x100 PNG, and the icon fields in agents/openai.yaml. Do not use it for app icons, favicons, badges, unrelated artwork, or skill work that does not include an icon.