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 chatgit 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/chat)<a href="https://agentmods.dev/skills/vercel-labs/json-render/chat"><img src="https://agentmods.dev/badge/skills/vercel-labs/json-render/chat/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/chat"><img src="https://agentmods.dev/badge/skills/vercel-labs/json-render/chat.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00092 | $0.00978 |
| Opus 5.5 | $0.00037 | $0.00391 |
| Sonnet 5.5 | $0.00018 | $0.00196 |
| Haiku 4.5 | $0.00009 | $0.00098 |
Grade A, and why
chat 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@json-render/chat
Renders json-render specs as Chat SDK CardElement objects. Each Chat SDK adapter converts the card to its platform format.
Quick start
import { defineCatalog } from "@json-render/core";
import {
schema,
standardComponentDefinitions,
streamCard,
} from "@json-render/chat";
import { streamText } from "ai";
const catalog = defineCatalog(schema, {
components: standardComponentDefinitions,
});
chat.onNewMention(async (thread, message) => {
const result = streamText({
model: "anthropic/claude-haiku-4.5",
system: catalog.prompt(),
prompt: message.text,
});
await streamCard(thread, result.textStream);
});
streamCard(target, textStream, options) posts the card once the root exists, edits it every updateIntervalMs (default 500) as elements arrive, and finishes with a validated card. toCard(spec, options) converts a complete spec. toPartialCard(spec) returns a best-effort card for a streaming spec, or null before the root exists.
Spec structure
Same flat tree as other renderers: root plus elements, with optional state. The root must be a Card. An inner Card renders as a titled section, because chat cards cannot nest.
Standard components: Card, Section, Text (markdown), Fields with Field, Table, Chart (pie with segments, or bar, line, area with categories and series[].values), Divider, Image, and Actions with Button and LinkButton.
{
"root": "card",
"elements": {
"card": {
"type": "Card",
"props": { "title": "Weekly deploys" },
"children": ["kpis", "chart"]
},
"kpis": { "type": "Fields", "props": {}, "children": ["total"] },
"total": {
"type": "Field",
"props": { "label": "Deploys", "value": "985" },
"children": []
},
"chart": {
"type": "Chart",
"props": {
"title": "Deploys per day",
"chart": {
"type": "bar",
"categories": ["Mon", "Tue"],
"series": [{ "name": "Deploys", "values": [180, 210] }]
}
},
"children": []
}
}
}
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.
- 3d ago First seen · 87 lines · 92 tokens per session scan A 874d3ad7f0d2
chat is a skill published in the GitHub repository vercel-labs/json-render (19,433 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session and 978 once invoked, about $0.0004 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 2026-11-05.
chat compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| chatvercel-labs/json-render | Skill | 19k | 2d ago | Apache-2.0 | A | 92 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |