chatgpt-app-builder

chatgpt-app-builder is a skill for Claude Code, Codex from Shubhamsaboo/awesome-llm-apps. It costs 129 tokens per session (752 once invoked), scanned A, original, Apache-2.0.

A deprecated guide for building ChatGPT apps with interactive widgets using the mcp-use framework and OpenAI Apps. It covers the server code, widget interface, shared state, and display modes.

In plain words
What is it for?
Use it only for older ChatGPT-app work; for new work, check whether mcp-app-builder is available instead.
Why use it?
It describes how a person and ChatGPT can work through the same interactive widget, but it has been replaced by mcp-app-builder.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it only for older ChatGPT-app work; for new work, check whether mcp-app-builder is available instead.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shubhamsaboo/awesome-llm-apps/chatgpt-app-builder
About the project

Awesome LLM Apps is a collection of open-source applications built around large language models, including AI agents and retrieval-augmented generation apps. It is intended for developers who want to study, run, or adapt these applications and related agent skills.

Shubhamsaboo/awesome-llm-apps · 143,248 stars · on GitHub · theunwindai.com

Install

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.

Any agent
npx skills add Shubhamsaboo/awesome-llm-apps --skill chatgpt-app-builder
Clone the repo
git clone --depth 1 https://github.com/Shubhamsaboo/awesome-llm-apps

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for chatgpt-app-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/shubhamsaboo/awesome-llm-apps/chatgpt-app-builder/github.svg)](https://agentmods.dev/skills/shubhamsaboo/awesome-llm-apps/chatgpt-app-builder)
Your own site
<a href="https://agentmods.dev/skills/shubhamsaboo/awesome-llm-apps/chatgpt-app-builder"><img src="https://agentmods.dev/badge/skills/shubhamsaboo/awesome-llm-apps/chatgpt-app-builder/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.

agentmods 80×15 button for chatgpt-app-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/shubhamsaboo/awesome-llm-apps/chatgpt-app-builder"><img src="https://agentmods.dev/badge/skills/shubhamsaboo/awesome-llm-apps/chatgpt-app-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 752 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 6
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00129 $0.00752
Opus 5.5 $0.00052 $0.00301
Sonnet 5.5 $0.00026 $0.00150
Haiku 4.5 $0.00013 $0.00075

Measured 1mo ago against content hash 7b8992f5fc17, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chatgpt-app-builder 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 1mo 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

generative_ui_agents/ai-mcp-app-builder/apps/mcp-use-server/.agent/skills/chatgpt-app-builder/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChatGPT App Builder

Build ChatGPT apps with interactive widgets using mcp-use. Zero-config widget development with automatic registration and built-in React hooks.

The app is consumed by two users at once: the human and the ChatGPT LLM. They collaborate through the widget -- the human interacts with it, the LLM sees its state. The widget is your shared surface.

Before You Code

  • Clarify what to build → discover.md: when starting a new app, validating an idea, or scoping features
  • Design tools and widgets → architecture.md: when deciding what needs UI vs tools-only, designing UX flows

Setup

  • Scaffold and run → setup.md: when creating a new project, starting dev server, connecting to ChatGPT/Claude

Implementation

  • Server handlers + widget creation → server-and-widgets.md: when writing server.tool() with widgets, widget() helper, React widget files
  • Widget state and LLM context → state-and-context.md: when persisting state, triggering LLM from widget, managing ephemeral vs persistent data
  • Display modes, theme, layout → ui-guidelines.md: when adapting to inline/fullscreen/PiP, handling theme, device, locale
  • Component API → components-api.md: when using McpUseProvider, Image, ErrorBoundary, useWidget
  • CSP and metadata → csp-and-metadata.md: when configuring external domains, dual-protocol metadata
  • Advanced patterns → widget-patterns.md: when building complex widgets with tool calls, state, theming

Quick Reference

// Server
import { MCPServer, widget, text, object } from "mcp-use/server";
server.tool({ name: "...", schema: z.object({...}), widget: { name: "widget-name" } },
  async (input) => widget({ props: {...}, output: text("...") })
);

// Widget (resources/widget-name.tsx)
import { McpUseProvider, useWidget, type WidgetMetadata } from "mcp-use/react";
export const widgetMetadata: WidgetMetadata = { description: "...", props: z.object({...}) };
export default function MyWidget() {
  const { props, isPending, callTool, sendFollowUpMessage, state, setState, theme } = useWidget();
  if (isPending) return <McpUseProvider autoSize><div>Loading...</div></McpUseProvider>;
  return <McpUseProvider autoSize><div>{/* UI */}</div></McpUseProvider>;
}

Read the full file on GitHub · 56 lines

Changes

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.

  1. 1mo ago First seen · 56 lines · 129 tokens per session scan A 7b8992f5fc17

Subscribe to this mod's changes

chatgpt-app-builder is a skill published in the GitHub repository Shubhamsaboo/awesome-llm-apps (143,248 stars, last pushed 5d ago), licensed Apache-2.0. It adds 129 tokens to every session and 752 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

daily-ai-news-digest

Fetches articles from 92 Karpathy-curated RSS feeds, scores them with an LLM, selects the top 3, and delivers a formatted digest to Telegram every morning.

Sumanth077/Hands-On-AI-Engineering · 42 tokens

hugging-face-model-trainer

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…

patchy631/ai-engineering-hub · 131 tokens

hugging-face-evaluation

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

patchy631/ai-engineering-hub · 55 tokens

hugging-face-datasets

Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.

patchy631/ai-engineering-hub · 49 tokens

hugging-face-paper-publisher

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

patchy631/ai-engineering-hub · 42 tokens

brightdata-web-mcp

Search the web, scrape websites, extract structured data from URLs, and automate browsers using Bright Data's Web MCP. Use when fetching live web content, bypassing blocks/CAPTCHAs, getting product data from Amazon/eBay, social media posts, or when standard requests fail.

patchy631/ai-engineering-hub · 62 tokens