opencode

Delegate coding, refactoring, and PR review tasks to the OpenCode CLI.

19|4|Updated Apr 22, 2026
One-click install
npx skills add https://github.com/carterwayneskhizeine/hermes-agent-windows-R --skill opencode-carterwayneskhizeine
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: opencode
Source: https://github.com/carterwayneskhizeine/hermes-agent-windows-R/tree/main/skills/autonomous-ai-agents/opencode
Command: npx skills add https://github.com/carterwayneskhizeine/hermes-agent-windows-R --skill opencode-carterwayneskhizeine

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you offload coding and refactoring work to an autonomous agent so you can move faster without manually driving every implementation and review step.

Core Features & Use Cases

  • Autonomous coding for bounded tasks and projects: Use one-shot runs for specific changes or keep an interactive TUI session running for iterative development.
  • Context-aware execution: Attach files to the agent, specify models, and scope work to a dedicated workdir/worktree to reduce conflicts.
  • Built-in PR review workflow: Use PR-focused commands (optionally with isolated clones) to surface bugs, security risks, test gaps, and style issues.

Quick Start

Start an autonomous coding run in your repo by asking the agent to implement your requested change while it can read and modify the attached workdir files.

Frequently Asked Questions about opencode

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

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

You can delegate coding tasks to an autonomous agent by sending specific change requests to the OpenCode CLI. The agent reads and modifies attached workdir files to implement the requested changes autonomously.

Can I use an interactive TUI session for iterative development?

Yes, you can use an interactive TUI session for iterative development. The OpenCode CLI supports multi-turn sessions using terminal or process orchestration with optional PTY to maintain context across development steps.

How do I run a PR review to surface bugs and security risks?

To run a PR review, use the PR-focused commands provided by the OpenCode CLI, optionally with isolated clones. This workflow surfaces bugs, security risks, test gaps, and style issues within your code changes.

Does autonomous coding require workspace isolation?

Autonomous coding supports workspace isolation by scoping work to a dedicated workdir or worktree. This reduces conflicts during execution but requires OpenCode availability and authenticated provider access to function correctly.

What is the best way to execute one-shot feature changes?

The best way to execute one-shot feature changes is through the OpenCode CLI. You provide a bounded task request and attach relevant files, allowing the autonomous agent to implement the specific changes in a single run.

Can I specify models for autonomous refactoring tasks?

Yes, you can specify models for autonomous refactoring tasks. The OpenCode CLI allows model selection during execution, ensuring the agent uses your preferred authenticated provider for code modifications.