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/mindverse-ltd/macaron-artifacts/genui-buildernpx skills add mindverse-ltd/macaron-artifacts --skill genui-buildergit clone --depth 1 https://github.com/mindverse-ltd/macaron-artifactsWrote 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/mindverse-ltd/macaron-artifacts/genui-builder)<a href="https://agentmods.dev/skills/mindverse-ltd/macaron-artifacts/genui-builder"><img src="https://agentmods.dev/badge/skills/mindverse-ltd/macaron-artifacts/genui-builder.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 | $0.00091 | $0.02043 |
| Opus 5 | $0.00046 | $0.01022 |
| Sonnet 5 | $0.00018 | $0.00409 |
| Haiku 4.5 | $0.00009 | $0.00204 |
Grade A, and why
genui-builder scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If the `mcp__macaron.render_ui` tool is exposed to you, call it directly with the complete TSX module in its `code` field — the host mounts the component inline in the conversation. The tool's own description already car How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GenUI Builder
Use this skill to produce streaming GenUI App.tsx/HTML artifacts. Default to streaming model output and incremental preview refresh; do not build one-shot "wait for full TSX, then render" experiences unless the user explicitly asks for non-streaming output.
Preferred path: render_ui MCP tool
If the mcp__macaron.render_ui tool is exposed to you, call it directly with the complete TSX module in its code field — the host mounts the component inline in the conversation. The tool's own description already carries the authoring rules for $macaron/ui, streaming write order, and quality constraints. Do NOT curl anything or emit markdown TSX fences when this tool is available.
Local authoring rules (fallback)
If render_ui is not exposed (older host or a bare CLI), fall back to writing a self-contained TSX module and use the CLI below to validate or render it. Detailed constraints and common fixes are in references/tsx-output.md.
Optionally, if the runtime allows network egress, you MAY fetch the canonical live authoring prompt for cross-check — but only if you already have a specific ambiguity to resolve. Do NOT fetch it prophylactically before every render:
curl -fsSL https://genui.macaron.im/api/system-prompt
If that command errors (DNS blocked, no network, non-2xx), silently proceed with the local rules — do not surface the failure to the user.
CLI
The CLI is optional. Prefer direct streaming runtimes when the user wants an HTML harness or GenUI capability inside a page. Use the CLI for validation, standalone one-shot export, or when the user explicitly asks for the CLI.
Use this exact pinned command unless the user provides a newer one:
bunx genui@https://pkg.pr.new/MindLab-Research/macaron-genui-demo/@genui/cli@00b6767
The CLI supports:
bunx genui@https://pkg.pr.new/MindLab-Research/macaron-genui-demo/@genui/cli@00b6767 lint App.tsx
bunx genui@https://pkg.pr.new/MindLab-Research/macaron-genui-demo/@genui/cli@00b6767 check App.tsx
bunx genui@https://pkg.pr.new/MindLab-Research/macaron-genui-demo/@genui/cli@00b6767 build App.tsx -o index.html
bunx genui@https://pkg.pr.new/MindLab-Research/macaron-genui-demo/@genui/cli@00b6767 dev App.tsx -p 4173 --host 127.0.0.1
What ships with it
2 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.
- 4d ago First seen · 171 lines · 91 tokens per session scan A 0ca268d864f5
genui-builder is a skill published in the GitHub repository mindverse-ltd/macaron-artifacts (10 stars, last pushed 12d ago), licensed Apache-2.0. It adds 91 tokens to every session and 2,043 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
portaljs-add-chart
Add a chart (line, bar, area, pie, or scatter) to a dataset's showcase in a PortalJS portal. Installs recharts, writes a reusable Chart component, and renders it in the showcase Views section. Use when visualizing a dataset already registered in datasets.json.
re-review
Re-review a PR after the author has pushed updates in response to previous feedback.
reflect
Reflect on the conversation and persist learnings to project documentation.
panel
Best practices for developing tools, dashboards and interactive data apps with HoloViz Panel. Create reactive, component-based UIs with widgets, layouts, templates, and real-time updates. Use when developing interactive data exploration tools, dashboards, data apps, or any interactive Python web application. Supports…
panel-holoviews
Best practices for integrating HoloViews and hvPlot visualizations into Panel applications. Use when embedding HoloViews/hvPlot plots in Panel panes, preserving zoom/pan state across data refreshes with DynamicMap, composing DynamicMap overlays without type errors, using HoloViews streams (Selection1D, RangeXY, Tap…
hvplot
Best practices for doing quick exploratory data analysis with minimal code and a Pandas .plot like API using HoloViews hvPlot.