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.
Borrowing it
Nothing to install: this file belongs to vercel-labs/json-render. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vercel-labs/json-render/main/AGENTS.mdgit 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/instructions/vercel-labs/json-render/agents-md)<a href="https://agentmods.dev/instructions/vercel-labs/json-render/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/json-render/agents-md/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/instructions/vercel-labs/json-render/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/json-render/agents-md.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 | $0.01530 | $0.01530 |
| Opus 5.5 | $0.00612 | $0.00612 |
| Sonnet 5.5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
json-render AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working with this codebase.
Package Management
Always check the latest version before installing a package.
Before adding or updating any dependency, verify the current latest version on npm:
npm view <package-name> version
Or check multiple packages at once:
npm view ai version
npm view @ai-sdk/provider-utils version
npm view zod version
This ensures we don't install outdated versions that may have incompatible types or missing features.
Code Style
- Do not use emojis in code or UI
- Use shadcn CLI to add shadcn/ui components:
pnpm dlx shadcn@latest add <component> - Web app docs (
apps/web/): Never use Markdown table syntax (| col | col |). Always use HTML<table>with<thead>,<tbody>,<tr>,<th>,<td>. Markdown tables do not render correctly in the web app. Inside HTML table cells, curly braces must be escaped as JSX expressions (e.g.<code>{'{ "$state": "/path" }'}</code>) because MDX parses{as a JSX expression boundary.
AI SDK / AI Gateway
When using the Vercel AI SDK (ai package) with AI Gateway, pass the model as a plain string identifier -- do not import a provider constructor:
import { streamText } from "ai";
const result = streamText({
model: "anthropic/claude-haiku-4.5",
prompt: "...",
});
This requires AI_GATEWAY_API_KEY to be set in the environment. See tests/e2e/ for examples.
Dev Servers
All apps and examples with dev servers use portless to avoid hardcoded ports. Portless assigns random ports and exposes each app via .localhost URLs.
Naming convention:
- Main web app:
json-render→json-render.localhost:1355 - Examples:
[name]-demo.json-render→[name]-demo.json-render.localhost:1355
When adding a new example that runs a dev server, wrap its dev script with portless <name>:
{
"scripts": {
"dev": "portless my-example-demo.json-render next dev --turbopack"
}
}
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.
- 8d ago Changed · +1 lines · +54 tokens per session ce13e23bf042
- 1mo ago Changed · +2 lines · +119 tokens per session 114601433815
- 2mo ago First seen · 131 lines · 1,357 tokens per session scan A 420d7eb36edb
json-render AGENTS.md is an instructions file published in the GitHub repository vercel-labs/json-render (18,930 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,530 tokens to every session, about $0.0061 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.
json-render AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| json-render AGENTS.mdvercel-labs/json-render | Instructions file | 19k | yesterday | Apache-2.0 | A | 1,530 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |