opencode

Delegates coding tasks to the OpenCode CLI agent for implementation, refactoring, and PR review.

1|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/kaminocorp/hermes-alpha-hunter --skill opencode-kaminocorp
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: opencode
Source: https://github.com/kaminocorp/hermes-alpha-hunter/tree/main/skills/autonomous-ai-agents/opencode
Command: npx skills add https://github.com/kaminocorp/hermes-alpha-hunter --skill opencode-kaminocorp

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Offloading bounded or long-running coding work to an external autonomous agent is hard to orchestrate manually. This Skill lets you delegate feature implementation, refactoring, debugging, and PR review to the OpenCode CLI while monitoring progress and collecting concrete results. ## Core Features & Use Cases - One-Shot Task Execution: Run bounded coding tasks with opencode run, attaching context files and forcing specific models when needed. - Interactive Background Sessions: Drive the OpenCode TUI in background mode, submit follow-up prompts, poll logs, and resume past sessions by ID. - PR Review & Parallel Work: Review pull requests in isolated clones and run multiple OpenCode sessions in separate worktrees to avoid collisions. - Use Case: Ask the agent to fix issue #101 in one worktree while adding regression tests in another, then poll both sessions and summarize files changed and test results. ## Quick Start Use the opencode skill to run a one-shot task that adds retry logic to the API calls in my project and updates the tests.

Frequently Asked Questions about opencode

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

FAQPage Schema
How do I run a one-shot coding task with OpenCode CLI?▼

Use `opencode run 'your task description'` from the project directory. Attach context files with `-f`, force a model with `--model provider/model`, and show reasoning with `--thinking`. One-shot runs do not require a pty.

How do I run OpenCode interactively in the background?▼

Start `opencode` with background=true and pty=true, then send prompts with process submit and monitor with poll or log. Exit with Ctrl+C (\x03) or kill; `/exit` is not a valid OpenCode command.

Can OpenCode review pull requests automatically?▼

Yes, OpenCode has a built-in `opencode pr <number>` command. For isolation, you can clone the repo into a temporary directory and run a review prompt against the diff versus the main branch.

Why does OpenCode behave differently in my terminal versus the agent?▼

Shell environments may resolve different OpenCode binaries via PATH. Check with `which -a opencode` and `opencode --version`, and pin an explicit binary path such as $HOME/.opencode/bin/opencode if needed.

Can I run multiple OpenCode sessions in parallel?▼

Yes, run separate sessions in distinct workdirs or git worktrees to avoid file collisions. Track all sessions with process list and poll each one independently for progress.