opencode

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

16|Updated Sep 22, 2026
One-click install
npx skills add https://github.com/igniteenow/robo --skill opencode-igniteenow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: opencode
Source: https://github.com/igniteenow/robo/tree/main/skills/autonomous-ai-agents/opencode
Command: npx skills add https://github.com/igniteenow/robo --skill opencode-igniteenow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires opencode-ai.

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 drive the OpenCode CLI from Robo's terminal and process tools, so features, refactors, and PR reviews run in one-shot or interactive sessions with progress monitoring. ## Core Features & Use Cases - One-Shot Task Execution: Run bounded coding tasks with opencode run, attaching context files, forcing specific models, and showing model thinking. - Interactive Background Sessions: Launch the OpenCode TUI with pty support, submit 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 workdirs or worktrees. - Use Case: Ask Robo to have OpenCode implement an OAuth refresh flow with tests in your repo, monitor its progress in the background, then summarize the files changed and test results. ## Quick Start Ask Robo to use OpenCode to implement a feature or review a pull request in your project directory, for example: "Use OpenCode to add retry logic to the API calls and update 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'` in the project directory for bounded, non-interactive tasks. Attach context files with `-f`, force a model with `--model provider/model`, and show reasoning with `--thinking`.

How do I review a pull request with OpenCode?▼

Run `opencode pr 42` inside the repository for the built-in PR review command. For isolation, clone the repo into a temporary directory and run `opencode run` with a review prompt and the changed files attached.

Does OpenCode interactive mode need a pseudo-terminal?▼

Yes, the interactive OpenCode TUI requires `pty=true` when started in the background. The `opencode run` one-shot command does not need pty and can run as a plain terminal command.

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

PATH mismatches can resolve different OpenCode binaries or model configs. Check with `which -a opencode` and `opencode --version`, then pin an explicit binary path such as `$HOME/.opencode/bin/opencode` if needed.

How do I exit an OpenCode TUI session cleanly?▼

Send Ctrl+C (`\x03`) to the session or kill the process directly. Do not use `/exit` — it is not a valid OpenCode command and opens an agent selector dialog instead.

Can I run multiple OpenCode sessions in parallel?▼

Yes, launch separate background sessions scoped to different workdirs or git worktrees to avoid file collisions. Track them with the process list action and monitor each session's logs independently.