opencode-zen

Invoke the opencode CLI headlessly for automated code analysis and reviews.

7|Updated Dec 25, 2025
One-click install
npx skills add https://github.com/osoleve/the-fold --skill opencode-zen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: opencode-zen
Source: https://github.com/osoleve/the-fold/tree/main/.claude/skills/opencode-zen
Command: npx skills add https://github.com/osoleve/the-fold --skill opencode-zen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables headless invocation of the opencode CLI to perform automated code analysis, reviews, and provide alternative AI perspectives without launching a UI.

Core Features & Use Cases

  • Headless analysis: Run opencode in the background to analyze codebases and generate insights without user interaction.
  • Batch and multi-file reviews: Analyze multiple files or projects in a single workflow for consistency.
  • Model variety and perspective: Compare results across providers/models to obtain diverse feedback and avoid single-model biases.
  • Use cases: Quick quality checks, architecture feedback, and security/maintainability reviews across large codebases.

Quick Start

Use opencode-zen to run a headless analysis on a file, for example: opencode run -m groq/qwen-qwq-32b "Review this module" -f src/main.rs

Frequently Asked Questions about opencode-zen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run headless AI code analysis from the command line?

Headless AI code analysis runs directly from the command line by invoking the opencode CLI without a UI. You execute it in the background to analyze codebases and generate insights without user interaction.

Can I perform batch code reviews on multiple files in a single workflow?

Batch code reviews support analyzing multiple files or projects in a single workflow. This enables consistency checks across large codebases and allows repeated feedback generation without launching a graphical interface.

How do I select specific AI models for automated code review?

Automated code review allows model selection using the -m flag in the opencode CLI. You can compare results across different providers and models to obtain diverse feedback and avoid single-model biases.

Does opencode work with Rust source files for architecture feedback?

Yes, opencode works with Rust source files by passing the file path with the -f flag. It provides architecture feedback and security reviews across large codebases regardless of the programming language.

What is the best way to compare AI perspectives across different models for codebase analysis?

Cross-model evaluation compares AI perspectives by running headless analysis with different model providers. This approach avoids single-model biases and delivers diverse feedback for quick quality checks and maintainability reviews.

How do I control output format when running headless code analysis?

Output format control uses the --format flag during headless code analysis invocation. This ensures results are structured consistently when integrating automated reviews into command-line workflows.