opencode

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

Updated Aug 21, 2026
One-click install
npx skills add https://github.com/TylerSimons1127/vibe --skill opencode-tylersimons1127
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: opencode
Source: https://github.com/TylerSimons1127/vibe/tree/main/skills/autonomous-ai-agents/opencode
Command: npx skills add https://github.com/TylerSimons1127/vibe --skill opencode-tylersimons1127

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Delegating bounded or long-running coding work to an external agent requires managing sessions, binaries, and interactive terminals manually. This Skill orchestrates the OpenCode CLI through terminal and process tools so features, refactors, and PR reviews run autonomously with progress monitoring. ## Core Features & Use Cases - One-Shot Automation: Run bounded tasks with opencode run, attaching context files, forcing models, and showing reasoning with flags like -f, --model, and --thinking. - Interactive Background Sessions: Launch the OpenCode TUI with pty=true, submit prompts, poll logs, resume sessions, and exit cleanly with Ctrl+C. - PR Review & Parallel Work: Review pull requests via opencode pr or isolated clones, and run parallel tasks in separate workdirs or worktrees to avoid collisions. - Use Case: Ask the agent to fix issue #101 in one worktree while adding parser regression tests in another, then monitor both sessions and summarize files changed and test results. ## Quick Start Use the opencode skill to run 'Add retry logic to API calls and update tests' in my project directory.

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 target repository. 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 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 via `-f`.

How do I exit an interactive OpenCode TUI session?▼

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

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

Shell environments can resolve different OpenCode binaries. Check with `which -a opencode` and `opencode --version`, then pin an explicit binary path such as `$HOME/.opencode/bin/opencode` if the configs diverge.

Can I run multiple OpenCode sessions in parallel?▼

Yes, launch separate background sessions scoped to different workdirs or git worktrees so they do not collide. Track them with process list and poll each session's logs for progress updates.

What are the prerequisites for using OpenCode CLI?▼

Install via `npm i -g opencode-ai@latest` or Homebrew, then configure a provider with `opencode auth login` or environment variables like OPENROUTER_API_KEY. Verify with `opencode auth list` and use a git repository for code tasks.