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 tanstack-startgit 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/tanstack-start)<a href="https://agentmods.dev/skills/vercel-labs/json-render/tanstack-start"><img src="https://agentmods.dev/badge/skills/vercel-labs/json-render/tanstack-start/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/tanstack-start"><img src="https://agentmods.dev/badge/skills/vercel-labs/json-render/tanstack-start.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 | $0.00058 | $0.01385 |
| Opus 5.5 | $0.00023 | $0.00554 |
| Sonnet 5.5 | $0.00012 | $0.00277 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
tanstack-start 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@json-render/tanstack-start
Use this integration when a TanStack Start app needs complete pages or routes described by json-render specs.
Install
npm install @json-render/core @json-render/react @json-render/tanstack-start
Application Spec
Include the server-safe built-in definitions in the generation catalog. The renderer supplies their component implementations.
import { defineCatalog } from "@json-render/core";
import {
schema,
startComponentDefinitions,
} from "@json-render/tanstack-start/server";
const catalog = defineCatalog(schema, {
components: {
...startComponentDefinitions,
Card: cardDefinition,
Shell: shellDefinition,
Navigation: navigationDefinition,
Home: homeDefinition,
Post: postDefinition,
},
actions: {},
});
Then use StartAppSpec and TanStack Router route patterns:
import type { StartAppSpec } from "@json-render/tanstack-start";
export const spec: StartAppSpec = {
metadata: {
title: { default: "Site", template: "%s | Site" },
},
layouts: {
main: {
root: "shell",
elements: {
shell: { type: "Shell", props: {}, children: ["nav", "slot"] },
nav: { type: "Navigation", props: {}, children: [] },
slot: { type: "Slot", props: {}, children: [] },
},
},
},
routes: {
"/": {
layout: "main",
metadata: { title: "Home" },
page: {
root: "home",
elements: {
home: { type: "Home", props: {}, children: [] },
},
},
},
"/posts/$slug": {
layout: "main",
loader: "post",
staticParams: [{ slug: "hello" }],
page: {
root: "post",
elements: {
post: {
type: "Post",
props: { value: { $state: "/post" } },
children: [],
},
},
},
},
},
};
Routes use /posts/$slug for named parameters and /docs/$ for a splat.
Splat loader parameters are slash-delimited strings under _splat. Escape
route-key slashes as ~1 when generating RFC 6902 patches.
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 · 200 lines · 58 tokens per session scan A ca31a5a557a1
tanstack-start 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 58 tokens to every session and 1,385 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 2026-09-08.
tanstack-start compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tanstack-startvercel-labs/json-render | Skill | 19k | 2d ago | Apache-2.0 | A | 58 | 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 |