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/vercel-labs/json-render/codegennpx skills add vercel-labs/json-render --skill codegengit clone --depth 1 https://github.com/vercel-labs/json-renderWhat 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 | $0.00038 | $0.00602 |
| Opus 5 | $0.00019 | $0.00301 |
| Sonnet 5 | $0.00008 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
codegen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@json-render/codegen
Framework-agnostic utilities for generating code from json-render UI trees. Use these to build custom code exporters for Next.js, Remix, or other frameworks.
Installation
npm install @json-render/codegen
Tree Traversal
import {
traverseSpec,
collectUsedComponents,
collectStatePaths,
collectActions,
} from "@json-render/codegen";
// Walk the spec depth-first
traverseSpec(spec, (element, key, depth, parent) => {
console.log(`${" ".repeat(depth * 2)}${key}: ${element.type}`);
});
// Get all component types used
const components = collectUsedComponents(spec);
// Set { "Card", "Metric", "Button" }
// Get all state paths referenced
const statePaths = collectStatePaths(spec);
// Set { "analytics/revenue", "user/name" }
// Get all action names
const actions = collectActions(spec);
// Set { "submit_form", "refresh_data" }
Serialization
import {
serializePropValue,
serializeProps,
escapeString,
type SerializeOptions,
} from "@json-render/codegen";
// Serialize a single value
serializePropValue("hello");
// { value: '"hello"', needsBraces: false }
serializePropValue({ $state: "/user/name" });
// { value: '{ $state: "/user/name" }', needsBraces: true }
// Serialize props for JSX
serializeProps({ title: "Dashboard", columns: 3, disabled: true });
// 'title="Dashboard" columns={3} disabled'
// Escape strings for code
escapeString('hello "world"');
// 'hello \"world\"'
SerializeOptions
interface SerializeOptions {
quotes?: "single" | "double";
indent?: number;
}
Types
import type { GeneratedFile, CodeGenerator } from "@json-render/codegen";
const myGenerator: CodeGenerator = {
generate(spec) {
return [
{ path: "package.json", content: "..." },
{ path: "app/page.tsx", content: "..." },
];
},
};
Building a Custom Generator
import {
collectUsedComponents,
collectStatePaths,
traverseSpec,
serializeProps,
type GeneratedFile,
} from "@json-render/codegen";
import type { Spec } from "@json-render/core";
export function generateNextJSProject(spec: Spec): GeneratedFile[] {
const files: GeneratedFile[] = [];
const components = collectUsedComponents(spec);
// Generate package.json, component files, main page...
return files;
}
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.
- yesterday First seen · 113 lines · 38 tokens per session scan A f0773c775137
codegen is a skill published in the GitHub repository vercel-labs/json-render (16,056 stars, last pushed 3d ago), licensed Apache-2.0. It adds 38 tokens to every session and 602 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…