prompt-canvas
v0.3.0A local infinite canvas for Codex, powered by tldraw and built for visual thinking, image generation, and annotation-driven edits.
By LunarAITalkLicense: MIT41 GitHub starsUpdated 4 months ago
Directory evidence
- Runtimes
- Codex
- Parsed components
- 2 skill or MCP entries
- Source updated
- Jun 23, 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 prompt-canvas for Codex
codex plugin marketplace add lqshow/prompt-canvas
codex plugin marketplace upgrade prompt-canvas-marketplace
codex plugin add prompt-canvas@prompt-canvas-marketplacePaste and run these commands in a terminal with Codex. They add and refresh the prompt-canvas-marketplace catalog, then install this plugin.
Compatibility: the page URL and API slug “prompt-canvas” remain stable.
- Codex:
prompt-canvas@agent-plugin-marketplace→prompt-canvas@prompt-canvas-marketplace
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/lqshow/prompt-canvasClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .codex-plugin/plugin.json├── skills/prompt-canvas/SKILL.md└── .mcp.json
Included Skills1
Drive the local Prompt Canvas from Codex for visual AI image iteration. Use when the user wants to open a local infinite canvas, generate images, place them on the canvas, and refine them by drawing annotations (arrows, scribbles, text) directly on the image. The canvas exposes MCP tools prefixed with `prompt_canvas_` (prompt_canvas_open, prompt_canvas_create_ai_image_holder, prompt_canvas_fill_ai_image_holder, prompt_canvas_read_annotations, prompt_canvas_insert_image, ...).
MCP servers1
- command
- bash
- args
- ./scripts/start-mcp.sh
- cwd
- .
Plugin manifests1
{
"name": "prompt-canvas",
"version": "0.3.0",
"description": "A local infinite canvas for Codex, powered by tldraw and built for visual thinking, image generation, and annotation-driven edits.",
"author": {
"name": "LunarAITalk",
"email": "[email protected]",
"url": "https://github.com/lqshow"
},
"homepage": "https://github.com/lqshow/prompt-canvas",
"repository": "https://github.com/lqshow/prompt-canvas.git",
"license": "MIT",
"keywords": [
"canvas",
"tldraw",
"whiteboard",
"image-generation",
"visual-collaboration"
],
"skills": "./skills/",
"mcpServers": "./.mcp.json",
"interface": {
"displayName": "Prompt Canvas",
"shortDescription": "Create, annotate, and generate on a local infinite canvas in Codex.",
"longDescription": "Prompt Canvas brings a tldraw-powered infinite canvas into Codex for visual planning and creative iteration. Open a local canvas for the active project, sketch ideas, place AI image holders, generate images into selected slots, and turn annotated screenshots into revised image outputs while keeping canvas data in the user's project workspace.",
"developerName": "LunarAITalk",
"category": "Productivity",
"websiteURL": "https://github.com/lqshow/prompt-canvas",
"brandColor": "#1a73e8",
"logo": "./assets/app-icon.png",
"composerIcon": "./assets/app-icon.png",
"capabilities": [
"Interactive canvas",
"Local web service",
"AI image generation",
"Annotation-driven editing",
"Project-local persistence"
],
"defaultPrompt": [
"Open the Prompt Canvas for this project.",
"Use my Prompt Canvas annotation screenshot to generate a clean revised image beside the original.",
"Generate a new image into the selected Prompt Canvas AI image holder."
]
}
}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.
[prompt-canvas on Agent Plugins Marketplace](https://pluginsmp.com/plugins/prompt-canvas)