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/bearlike/assistant/generative-uinpx skills add bearlike/Assistant --skill generative-uigit clone --depth 1 https://github.com/bearlike/AssistantWhat 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 | $0.00048 | $0.01117 |
| Opus 5 | $0.00024 | $0.00558 |
| Sonnet 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 2d 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.
- 2d ago First seen · 112 lines · 48 tokens per session scan A 629d36c06995
generative-ui is a skill published in the GitHub repository bearlike/Assistant (41 stars, last pushed 8d ago), licensed MIT. It adds 48 tokens to every session and 1,117 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
largest-files-finder
List the top 3 largest files in a given directory.
extract-action-items
Extract a list of action items with owners and deadlines from a meeting transcript.
skill-structure-advisor
Helps you choose the right design pattern and structure for a new skill.
cross-border-customer-service-brief
Cluster refund, return, complaint, and bad-review notes into a daily support brief with response guidance and escalation hints.
cross-border-listing-image-layout-audit
Audit listing image and layout notes — first-impression hero, info hierarchy, lifestyle vs studio, copy density, trust signals, compliance — into a follow-up checklist.
cross-border-price-match-review
Cluster competitor price, coupon, shipping, and bundle observations into a price-gap review with explicit human-approval guidance.