omnimodal
v3.1.0Omnimodal plugin for Codex and Claude Code: recognize and generate images, video, and audio through Qwen, Z.AI, or OpenAI-compatible APIs.
By good-boy4069License: MIT1.1k GitHub starsUpdated 2 days ago
Directory evidence
- Runtimes
- Codex
- Parsed components
- 5 skill or MCP entries
- Source updated
- Sep 22, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install omnimodal for Codex
codex plugin marketplace add hashgraph-online/awesome-codex-plugins
codex plugin marketplace upgrade awesome-codex-plugins
codex plugin add omnimodal@awesome-codex-pluginsPaste and run these commands in a terminal with Codex. They add and refresh the awesome-codex-plugins catalog, then install this plugin.
Compatibility: the page URL and API slug “omnimodal” remain stable.
- Codex:
omnimodal@agent-plugin-marketplace→omnimodal@awesome-codex-plugins
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/hashgraph-online/awesome-codex-pluginsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/ZXY1240/read-image/.
Plugin files
├── .codex-plugin/plugin.json├── skills/omnimodal/SKILL.md└── .mcp.json
Included Skills1
为纯文本主模型提供多模态能力:识别图片、视频、音频,并生成图片、视频、音频。遇到图片路径、截图、UI/网页截图、图表、错误弹窗、OCR、音频/视频理解、文生图/文生视频/TTS 或任何需要多模态能力的任务时自动启用。
MCP servers4
- command
- uv
- args
- run --project . omnimodal-capture-page
- cwd
- .
- command
- uv
- args
- run --project . omnimodal-generation
- cwd
- .
- command
- uv
- args
- run --project . omnimodal-recognize
- cwd
- .
- command
- uv
- args
- run --project . omnimodal-windows-capture
- cwd
- .
Plugin manifests1
{
"name": "omnimodal",
"version": "3.1.0",
"description": "Omnimodal plugin for Codex and Claude Code: recognize and generate images, video, and audio through Qwen, Z.AI, or OpenAI-compatible APIs.",
"homepage": "https://github.com/good-boy4069/Deepseek-omnimodal",
"repository": "https://github.com/good-boy4069/Deepseek-omnimodal",
"license": "MIT",
"keywords": [
"vision",
"audio",
"generation",
"wanx",
"tts",
"omnimodal",
"mcp",
"read-video",
"screenshot",
"qwen",
"zai",
"glm",
"deepseek",
"agent-harness"
],
"author": {
"name": "good-boy4069",
"url": "https://github.com/good-boy4069"
},
"skills": "./skills/",
"mcpServers": "./.mcp.json",
"interface": {
"displayName": "Omnimodal",
"shortDescription": "Recognize and generate images, video, and audio with Qwen, Z.AI, or OpenAI-compatible APIs",
"longDescription": "Adds omnimodal_recognize_*, omnimodal_generate_*, omnimodal_capture_page, and native Windows omnimodal_capture_windows/omnimodal_list_windows MCP tools.",
"developerName": "good-boy4069",
"composerIcon": "./assets/icon.svg",
"websiteURL": "https://github.com/good-boy4069/Deepseek-omnimodal",
"privacyPolicyURL": "https://github.com/good-boy4069/Deepseek-omnimodal/blob/main/PRIVACY.md",
"termsOfServiceURL": "https://github.com/good-boy4069/Deepseek-omnimodal/blob/main/LICENSE",
"category": "Productivity",
"capabilities": [
"Read",
"Write"
],
"defaultPrompt": [
"Read this local image and extract the requested content."
]
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[omnimodal on Agent Plugins Marketplace](https://pluginsmp.com/plugins/omnimodal)