npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@sami7786/opencode-image-proxy

v1.0.6

Published

OpenCode plugin that proxies images through a vision-capable model, enabling image-incapable models to "see"

Readme

opencode-image-proxy

OpenCode plugin that proxies images through a vision-capable model, enabling image-incapable models to "see" pasted images.

Installation

From npm

Add this to opencode config (typically in: ~/.config/opencode/opencode.json)

{
  "$schema": "https://opencode.ai/config.json",
    "plugin": [
      "@sami7786/opencode-image-proxy@latest"
    ]
}

How It Works

  1. Checks if the current model is in the "imageIncapableModels" list as configured
  2. If image-incapable: Automatically sends images to a vision-capable model for analysis, then replaces the image with a text description
  3. If image-capable: Images pass through natively with no transformation

All model calls use OpenCode's existing authentication - no separate API keys needed.

Configuration

Create ~/.config/opencode/opencode-image-proxy.json (or $XDG_CONFIG_HOME/opencode/opencode-image-proxy.json)

To see available models, run: opencode models

default config:

{
  "imageIncapableModels": [
    "zai-coding-plan/glm-4.5",
    "zai-coding-plan/glm-4.5-air",
    "zai-coding-plan/glm-4.5-flash",
    "zai-coding-plan/glm-4.6",
    "zai-coding-plan/glm-4.7",
    "zai-coding-plan/glm-4.7-flash",
    "zai-coding-plan/glm-5"
  ],
  "imageReaderModel": {
    "providerID": "opencode",
    "modelID": "kimi-k2.5-free"
  },
  "analysisPrompt": "The user has pasted an image into their chat. Describe what you see as if you are directly observing the image. Be thorough but concise. Include:\n- All visible elements (objects, text, UI elements, people, etc.)\n- Exact transcription of any text\n- The context and purpose of the image\n- Any relevant technical details\n\nDescribe it naturally, as if explaining to someone what you're looking at right now."
}
  • imageIncapableModels — Models that you want to enable the proxy for.
  • imageReaderModel — Any vision-capable model in your OpenCode setup.
  • analysisPrompt — System prompt for image analysis.

Behavior

| Model | Result | |-------|--------| | In image-incapable list | Images proxied through vision model, replaced with descriptions | | NOT in list | Images pass through natively |

Example Output

[User pasted image: screenshot.png]
This is a terminal window showing a Node.js error. The error message reads:
"TypeError: Cannot read property 'map' of undefined" at line 42 in app.js.
The stack trace below shows the error originated in the UserList component...

Requirements

  • The configured imageReaderModel must be available and authenticated in OpenCode
  • The vision model must support image input

Building

npm install
npm run build

License

MIT