ai-eng-system

AI Engineering System with context engineering, research orchestration, 19 commands, 28 specialized agents, and 7 skill files for Claude Code & OpenCode

Installation guide →

8 skills 19 commandshooksAI & Development ToolsMIT GitHub

Commands

clean

Remove AI-generated verbosity and slop patterns from content

compound

Document a solved problem to compound team knowledge

context

Manage session state, memories, and context engineering

create-agent

Create a new OpenCode agent with AI assistance. Uses agent-creator for intelligent agent generation.

create-command

Create a new OpenCode command with AI assistance. Uses command-creator for intelligent command generation.

create-plugin

Guided end-to-end plugin creation workflow for OpenCode extensions. Creates plugins, commands, agents, skills, and custom tools with AI assistance. Follows systematic 8-phase process from discovery to documentation.

create-skill

Create a new OpenCode skill with AI assistance. Uses skill-creator for intelligent skill generation.

create-tool

Create a new OpenCode custom tool with AI assistance. Uses tool-creator for intelligent TypeScript tool generation.

deploy

Pre-deployment verification and Coolify deployment

init

Initialize ai-eng-system configuration and project setup

optimize

Interactive optimization for prompts, code, queries, and more using research-backed techniques and web best practices

plan

Create detailed implementation plans from specifications

ralph-wiggum

Full-cycle feature development with continuous iteration through all spec-driven workflow phases (Research → Specify → Plan → Work → Review) until feature is complete.

recursive-init

Recursively initialize AGENTS.md in all important subdirectories with smart detection

research

Conduct comprehensive multi-phase research across codebase, documentation, and external sources

review

Run comprehensive code review with multiple perspectives

seo

Run SEO audit on a page or site

specify

Create a feature specification using structured requirements gathering

work

Execute a plan or task with systematic tracking, quality gates, and comprehensive validation.

Documentation

# ai-eng-system OpenCode Plugin

A minimal OpenCode plugin that logs version information when sessions are created.

## Purpose

This plugin provides a simple session start notification by:
- Listening for `session.created` events
- Reading the version from `package.json`
- Logging "ai-eng-system vX.X.X loaded" to the console

## Installation

Place this plugin in `.opencode/plugin/ai-eng-system/` directory:
```bash
mkdir -p .opencode/plugin/ai-eng-system
cp plugin.ts .opencode/plugin/ai-eng-system/
```

## Implementation Details

- **Event Hook**: Uses the generic `event` hook to monitor all events
- **Event Filter**: Checks for `event.type === "session.created"`
- **Version Reading**: Dynamically imports `package.json` to get version
- **Minimal Dependencies**: Only depends on `@opencode-ai/plugin` types

## Code Structure

```typescript
const plugin: Plugin = async ({ client, project, directory, worktree, $ }) => {
  const version = await getVersion()
  
  return {
    event: async ({ event }) => {
      if (event.type === "session.created") {
        console.log(`ai-eng-system v${version} loaded`)
      }
    }
  }
}
```

This plugin follows OpenCode's plugin architecture with proper TypeScript typing and async version loading.