opencode-auto-reviewerOpenCode plugin that acts as a supervisor to detect conceptual loops
2
331
4 in 7 days
35.6
Multi-signal model
2 months ago
2026-06-07
Install and configure
opencode.jsonWrites to this project's opencode.json — applies to this repository only.
opencode.json
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["opencode-auto-reviewer@0.1.0"]
}Writes to ~/.config/opencode/opencode.json — applies to every project.
~/.config/opencode/opencode.json
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["opencode-auto-reviewer@0.1.0"]
}If you want to modify the plugin locally, install it into the project and reference the local path.
shell
pnpm add -D opencode-auto-revieweropencode loads npm dependencies through its embedded runtime on startup and caches them locally — no manual global install needed.
OpenCode plugin that acts as a supervisor to detect conceptual loops
Installation
npm install opencode-auto-reviewer
Features
- Acts as an LLM-powered supervisor observing the agent trajectory.
- Detects conceptual rabbit holes where the agent is stuck but technically not in an exact loop.
- Provides hints, warnings, and critical interventions to nudge the agent back on track.
- Forces strategy changes when approaches fail to converge.
Usage
This is a plugin for OpenCode.
You can easily enable this plugin globally by adding it to your opencode.json (or opencode.jsonc) configuration file under the plugins array.
{
"plugins": [
"opencode-auto-reviewer"
]
}
Once added to your configuration, OpenCode will automatically load and activate the plugin whenever it starts.
Alternatively, if you are configuring OpenCode programmatically via the SDK, you can register it like this:
import { configureAgent } from '@opencode-ai/sdk';
import plugin from 'opencode-auto-reviewer';
const agent = configureAgent({
plugins: [
plugin({
// Provide configuration options here
})
]
});