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/imagenpx skills add vercel-labs/json-render --skill imagegit 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 | $0.00046 | $0.00685 |
| Opus 5 | $0.00023 | $0.00342 |
| Sonnet 5 | $0.00009 | $0.00137 |
| Haiku 4.5 | $0.00005 | $0.00068 |
Grade A, and why
image 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 2d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@json-render/image
Image renderer that converts JSON specs into SVG and PNG images using Satori.
Quick Start
import { renderToPng } from "@json-render/image/render";
import type { Spec } from "@json-render/core";
const spec: Spec = {
root: "frame",
elements: {
frame: {
type: "Frame",
props: { width: 1200, height: 630, backgroundColor: "#1a1a2e" },
children: ["heading"],
},
heading: {
type: "Heading",
props: { text: "Hello World", level: "h1", color: "#ffffff" },
children: [],
},
},
};
const png = await renderToPng(spec, {
fonts: [{ name: "Inter", data: fontData, weight: 400, style: "normal" }],
});
Using Standard Components
import { defineCatalog } from "@json-render/core";
import { schema, standardComponentDefinitions } from "@json-render/image";
export const imageCatalog = defineCatalog(schema, {
components: standardComponentDefinitions,
});
Adding Custom Components
import { z } from "zod";
const catalog = defineCatalog(schema, {
components: {
...standardComponentDefinitions,
Badge: {
props: z.object({ label: z.string(), color: z.string().nullable() }),
slots: [],
description: "A colored badge label",
},
},
});
Standard Components
| Component | Category | Description |
|---|---|---|
Frame |
Root | Root container. Defines width, height, background. Must be root. |
Box |
Layout | Container with padding, margin, border, absolute positioning |
Row |
Layout | Horizontal flex layout |
Column |
Layout | Vertical flex layout |
Heading |
Content | h1-h4 heading text |
Text |
Content | Body text with full styling |
Image |
Content | Image from URL |
Divider |
Decorative | Horizontal line separator |
Spacer |
Decorative | Empty vertical space |
Key Exports
| Export | Purpose |
|---|---|
renderToSvg |
Render spec to SVG string |
renderToPng |
Render spec to PNG buffer (requires @resvg/resvg-js) |
schema |
Image element schema |
standardComponents |
Pre-built component registry |
standardComponentDefinitions |
Catalog definitions for AI prompts |
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.
- 2d ago First seen · 97 lines · 46 tokens per session scan A 117929c3ffbf
image is a skill published in the GitHub repository vercel-labs/json-render (16,056 stars, last pushed 4d ago), licensed Apache-2.0. It adds 46 tokens to every session and 685 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
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
resolve-rough-cut
Assembling a short-form social rough cut from raw behind-the-scenes or vlog footage in the DaVinci Resolve MCP. Apply when asked for a rough cut, first cut, assembly, or "make me a timeline" from a folder of footage — day-in-the-life, BTS, process, or product-shoot material destined for Reels, TikTok, or Shorts.…