opencode

Delegate software engineering tasks to autonomous AI coding agent via CLI/TUI interfaces.

Updated Jul 6, 2026
One-click install
npx skills add https://github.com/ghufronbagaskara/agent-im --skill opencode-ghufronbagaskara
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: opencode
Source: https://github.com/ghufronbagaskara/agent-im/tree/main/hermes-home/skills/autonomous-ai-agents/opencode
Command: npx skills add https://github.com/ghufronbagaskara/agent-im --skill opencode-ghufronbagaskara

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the challenge of managing complex, multi-step coding tasks by delegating them to an autonomous agent that can handle refactoring, PR reviews, and iterative development directly within your terminal.

Core Features & Use Cases

  • Autonomous Coding: Execute one-shot tasks like refactoring or bug fixing without manual intervention.
  • Interactive TUI Sessions: Manage long-running, iterative coding sessions with persistent state and model switching.
  • PR Review Workflow: Automate the analysis of pull requests to identify bugs, security risks, and test gaps.

Quick Start

Use the opencode skill to run a task that adds retry logic to the API calls in the current project directory.

Frequently Asked Questions about opencode

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

FAQPage Schema
How do I automate code refactoring directly from the terminal?

You can automate code refactoring from the terminal by delegating one-shot tasks to an autonomous coding agent, which handles the modifications without manual intervention in your project directory.

Can I review pull requests for bugs and security risks automatically?

Yes, you can automatically review pull requests by running an analysis workflow that identifies bugs, security risks, and test gaps without manual code inspection.

How do I manage long-running iterative coding sessions with model switching?

You can manage long-running iterative coding sessions with model switching using an interactive TUI interface, which maintains persistent state throughout the development cycle.

Do I need provider authentication to run an autonomous coding agent in the terminal?

Yes, you need provider authentication and the OpenCode CLI tool installed to execute terminal-based autonomous coding operations within isolated work environments.

What is the best way to handle multi-step coding tasks without manual intervention?

The best way to handle multi-step coding tasks without manual intervention is to delegate them to an autonomous agent capable of executing iterative development cycles in isolated work environments.