goose
$ brew install gooseCoding agent, terminal actions, and prompted automation from the terminal.
- goose fits local ai well, especially for coding agent, terminal actions, and prompted automation from the terminal.
- 776 homebrew installs (30d).
- Verify with `goose --help` first.
- Good fit for coding-agent workflows and repeatable scripts.
- Output is mostly text-first, so verify results before scripting around it.
Goose guide
Coding agent, terminal actions, and prompted automation from the terminal. Built by Block.
Open CLI packages the install path, verify step, and safe-start workflow so this tool can move from “interesting CLI” to something you can actually use. It also integrates with skills.sh so each CLI comes with the right companion skills, not just a binary and a docs link.
When to apply
- coding agent, terminal actions, and prompted automation from the terminal.
- You work with AI models and inference and want a fast terminal interface.
- You need coding agent.
- You need terminal actions.
- You need prompted automation.
Quick reference
brew install goosegoose --helpgooseOpen CLI × skills.sh
Open CLI integrates goose with the right skills.sh companions so you get the tool and the workflow together.
Prompt Engineering
Recommended pairingOpen CLI recommends this skills.sh skill because it fits ai workflows. Use sharper prompts so AI CLIs and agents produce more reliable results.
$ npx skills add https://github.com/inferen-sh/skills --skill prompt-engineeringUse goose together with the Prompt Engineering skills.sh skill. Start with a small prompt or read-only action, show the result, and propose the next loop before escalating scope.
Why this tool
- goose fits local ai well, especially for coding agent, terminal actions, and prompted automation from the terminal.
- 776 homebrew installs (30d).
- Verify with `goose --help` first.
Watch-outs
- Sign in before real work.
- Needs network access.
- Automation can be brittle.
Example workflow
1. gooseSafe start
Install goose.
Run `goose --help` first.
Start with `goose`.
Authenticate goose before asking the agent to do real work.