json-render is a framework where AI produces user interfaces as structured JSON constrained by a developer-defined component catalogue. It is for building dynamic interfaces from natural-language prompts across web and mobile frameworks.
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 vercel-labs/json-render --skill sveltegit clone --depth 1 https://github.com/vercel-labs/json-renderWrote 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/vercel-labs/json-render/svelte)<a href="https://agentmods.dev/skills/vercel-labs/json-render/svelte"><img src="https://agentmods.dev/badge/skills/vercel-labs/json-render/svelte/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/vercel-labs/json-render/svelte"><img src="https://agentmods.dev/badge/skills/vercel-labs/json-render/svelte.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 71 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00049 | $0.01814 |
| Opus 5.5 | $0.00020 | $0.00726 |
| Sonnet 5.5 | $0.00010 | $0.00363 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade A, and why
svelte 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 2mo 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@json-render/svelte
Svelte 5 renderer that converts json-render specs into Svelte component trees.
Quick Start
<script lang="ts">
import { Renderer, JsonUIProvider } from "@json-render/svelte";
import type { Spec } from "@json-render/svelte";
import Card from "./components/Card.svelte";
import Button from "./components/Button.svelte";
interface Props {
spec: Spec | null;
}
let { spec }: Props = $props();
const registry = { Card, Button };
</script>
<JsonUIProvider>
<Renderer {spec} {registry} />
</JsonUIProvider>
Creating a Catalog
import { defineCatalog } from "@json-render/core";
import { schema } from "@json-render/svelte";
import { z } from "zod";
export const catalog = defineCatalog(schema, {
components: {
Button: {
props: z.object({
label: z.string(),
variant: z.enum(["primary", "secondary"]).nullable(),
}),
description: "Clickable button",
},
Card: {
props: z.object({ title: z.string() }),
description: "Card container with title",
},
},
});
Defining Components
Components should accept BaseComponentProps<TProps>:
interface BaseComponentProps<TProps> {
props: TProps; // Resolved props for this component
children?: Snippet; // Child elements (use {@render children()})
emit: (event: string) => void; // Fire a named event
bindings?: Record<string, string>; // Map of prop names to state paths (for $bindState)
loading?: boolean; // True while spec is streaming
}
<!-- Button.svelte -->
<script lang="ts">
import type { BaseComponentProps } from "@json-render/svelte";
interface Props extends BaseComponentProps<{ label: string; variant?: string }> {}
let { props, emit }: Props = $props();
</script>
<button class={props.variant} onclick={() => emit("press")}>
{props.label}
</button>
<!-- Card.svelte -->
<script lang="ts">
import type { Snippet } from "svelte";
import type { BaseComponentProps } from "@json-render/svelte";
interface Props extends BaseComponentProps<{ title: string }> {
children?: Snippet;
}
let { props, children }: Props = $props();
</script>
<div class="card">
<h2>{props.title}</h2>
{#if children}
{@render children()}
{/if}
</div>
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.
- 2mo ago First seen · 287 lines · 49 tokens per session scan A 03e6e301b519
svelte is a skill published in the GitHub repository vercel-labs/json-render (19,433 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 1,814 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.
svelte compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sveltevercel-labs/json-render | Skill | 19k | yesterday | Apache-2.0 | A | 49 | Claude Code, Codex |
| add-localizationmicrosoft/power-platform-skills | Skill | 1.1k | today | MIT | A | 69 | Claude Code |
| vue-router-best-practicesvuejs-ai/skills | Skill | 3.3k | 16d ago | MIT | A | 25 | Claude Code, Codex |
| moai-domain-uiuxmodu-ai/moai-adk | Skill | 1.3k | today | Apache-2.0 | A | 49 | Claude Code |
| frontend-conventionsfpindej/netrock | Skill | 235 | 5d ago | MIT | A | 27 | Claude Code |
| native-to-weapp-vite-wevu-migrationweapp-vite/weapp-vite | Skill | 519 | today | MIT | A | 106 | Codex |
| weapp-vite-vue-sfc-best-practicesweapp-vite/weapp-vite | Skill | 519 | today | MIT | A | 107 | Codex |