chatgpt-apps
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply A
- License
- Not stated
- SKILL.md tokens
- 4,903
- Bundled files
- 10
- Bundled tokens (estimated)
- 14,264
Cost per 1,000 loads
Estimated input cost per 1,000 loads of SKILL.md only (characters ÷ 4). Bundled files, output tokens and execution are excluded.
| Model | Input / 1M tokens | 1,000 loads |
|---|---|---|
| Claude Opus 5 | $5.00 | $24.52 |
| Claude Sonnet 5 | $2.00 | $9.81 |
| Claude Haiku 4.5 | $1.00 | $4.90 |
Safety flags
Detected automatically from files; not a security audit.
- Runs scripts
- Yes
- Network access
- Yes
- Shell commands
- No
Works with
Open SKILL.md format
- Claude Code
- Codex
- Cursor
- GitHub Copilot
- Gemini CLI
- OpenCode
- Goose
Install
npx skills add openai/skills --skill chatgpt-appsLast verified:
chatgpt-apps FAQ
What does the chatgpt-apps skill do?
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply A Source: https://github.com/openai/skills/blob/main/skills/.curated/chatgpt-apps/SKILL.md
What does the chatgpt-apps skill cost to load?
SKILL.md is about 4,903 tokens. Estimated input cost per 1,000 loads: Claude Opus 5 $24.52; Claude Sonnet 5 $9.81; Claude Haiku 4.5 $4.90. Estimated input cost per 1,000 loads of SKILL.md only (characters ÷ 4). Bundled files, output tokens and execution are excluded. Prices: https://docs.anthropic.com/en/docs/about-claude/pricing
How do I install the chatgpt-apps skill?
Skills CLI: npx skills add openai/skills --skill chatgpt-apps. Download the chatgpt-apps skill folder as a ZIP and upload it in Claude.ai skills settings.
Is the chatgpt-apps skill safe?
Automatically detected flags: runs scripts, network access. Flags are detected automatically from the skill's files and are not a security audit; review the SKILL.md before installing.