opencode

Delegate coding, refactoring, and code review tasks to OpenCode CLI.

Updated May 24, 2026
One-click install
npx skills add https://github.com/anxiety135790/hermes-skills --skill opencode-anxiety135790
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: opencode
Source: https://github.com/anxiety135790/hermes-skills/tree/main/autonomous-ai-agents/opencode
Command: npx skills add https://github.com/anxiety135790/hermes-skills --skill opencode-anxiety135790

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you offload coding, refactoring, and review work to OpenCode as an autonomous terminal-based agent, so you can move faster on implementation and validation tasks without micromanaging every step.

Core Features & Use Cases

  • One-shot coding tasks: Run bounded prompts for fixes, feature work, and test updates.
  • Interactive agent sessions: Use background TUI sessions for longer iterative work with progress checks and follow-up instructions.
  • PR review and parallel work: Review pull requests, inspect changes, and coordinate isolated workdirs or worktrees for concurrent tasks.
  • Use Case: Ask it to refactor an auth module, review a PR for security issues, or keep a long-running debugging session moving until the code is ready.

Quick Start

Ask OpenCode to implement your requested code change in the current repository and report back the files changed, tests run, and any remaining risks.

Frequently Asked Questions about opencode

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

FAQPage Schema
How do I delegate code review and refactoring tasks to a CLI coding agent?

You can delegate code review and refactoring by running bounded prompts through terminal orchestration to the OpenCode CLI, which autonomously handles feature implementation, debugging, and test updates before reporting changed files and risks.

Can I run parallel coding tasks in isolated workdirs for concurrent PR reviews?

Yes, you can coordinate parallel coding tasks by orchestrating isolated workdirs or worktrees, allowing the CLI agent to inspect changes and review pull requests concurrently without workspace conflicts.

How do I manage long-running interactive sessions for iterative debugging?

You can manage long-running interactive debugging by launching background pty-enabled TUI sessions, using session control to poll progress, log output, submit follow-up instructions, and ensure a clean exit when the code is ready.

Do I need authenticated provider access to use OpenCode for terminal automation?

Yes, you need OpenCode installed locally and authenticated provider access configured, as terminal and process orchestration requires valid API credentials to execute autonomous coding and refactoring tasks.

What's the best way to offload feature implementation to an autonomous terminal agent?

The best way is issuing a one-shot bounded prompt for the requested code change, letting the autonomous terminal agent execute the feature implementation, run tests, and report back remaining risks and modified files.

When should I avoid using a CLI coding agent for pull request reviews?

You should avoid using a CLI coding agent for pull request reviews when you lack a pty-enabled environment for interactive sessions or when tasks require continuous manual micromanagement rather than bounded autonomous execution.