skills.rest
Z43L
Z43LCOMMUNITY
Explore all skills by this author →
GitHub

opencode

Delegate coding tasks to OpenCode for implementation, refactoring, and PR review.

Updated May 5, 2026
Search Tags:#refactoring#cli#coding#workflows#tui#pull-request#autonomous-agents
One-click install
npx skills add https://github.com/Z43L/zeus-agent --skill opencode-z43l
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: opencode
Source: https://github.com/Z43L/zeus-agent/tree/main/skills/autonomous-ai-agents/opencode
Command: npx skills add https://github.com/Z43L/zeus-agent --skill opencode-z43l

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It reduces the time and effort required to implement, refactor, and review code by delegating those tasks to an external autonomous coding worker.

Core Features & Use Cases

  • One-shot coding jobs: Run bounded feature work, refactors, and fixes with a single prompt for predictable, non-interactive execution.
  • Interactive long-running sessions: Keep an OpenCode TUI session running for iterative development with progress monitoring and resumable work.
  • PR review support: Review a pull request (or a focused diff) for bugs, security risks, test gaps, and style issues, using isolated checkouts when needed.
  • Parallel work isolation: Safely run multiple coding tasks in separate workdirs/worktrees to avoid state collisions.

Quick Start

Ask an AI agent to use the OpenCode CLI to implement a specific feature by running a one-shot command against your repository, then report the files changed and any test results.

Frequently Asked Questions about opencode

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

FAQPage Schema
How do I delegate coding and refactoring tasks to an autonomous agent?▼

You can delegate coding and refactoring tasks to an autonomous agent by running one-shot commands against your Git repository, which executes bounded feature work predictably and returns concrete change summaries.

Can I run interactive long-running coding sessions for iterative development?▼

Yes, you can run interactive long-running coding sessions by keeping a TUI session active, enabling iterative development with progress monitoring and resumable work via background execution using pty=true.

How do I review a pull request for bugs and security risks automatically?▼

You can review a pull request for bugs, security risks, test gaps, and style issues by using autonomous PR review flows, which analyze focused diffs and operate within isolated checkouts.

What is the best way to run multiple coding tasks in parallel without state collisions?▼

The best way to run multiple coding tasks in parallel without state collisions is executing them in separate repo-scoped workdirs and worktrees, ensuring complete parallel work isolation.

Do I need to install OpenCode before using this coding workflow?▼

Yes, you need to install and authenticate OpenCode beforehand, ensuring correct binary resolution and interactive session support, to enable autonomous coding, refactoring, and PR review execution.

Related Skills

Explore More Software Engineering Skills→
afel6afel6

opencode

Delegate coding and review tasks to the OpenCode CLI agent.

Community
Intermediate
cookeyholdercookeyholder

squash-pr

Squash and merge a GitHub pull request into main after validating review feedback.

Community
Advanced
DarkArty07DarkArty07
3

codex

Delegate coding tasks to the OpenAI Codex CLI for autonomous execution.

Community
Intermediate
automatedigitalautomatedigital
1

claude-code

Delegate autonomous coding tasks to Anthropic's Claude Code CLI.

Official
Advanced