Skip to content
AgentAtlas

goose Recipes: recipe.yaml Format, Parameters and goose run --recipe

How do I write and run a goose recipe?

A recipe is a YAML or JSON file with a title, a description, and instructions or a prompt. Run it with goose run --recipe recipe.yaml and pass values with --params key=value. goose finds recipes in the current folder, in GOOSE_RECIPE_PATH folders, or in a GitHub repo set by GOOSE_RECIPE_GITHUB_REPO.

Minimal recipe

recipe.yaml

version: "1.0.0"
title: "Code Review Assistant"
description: "Automated code review with best practices"
instructions: "You are a code reviewer..."
prompt: "Review the code in this repository"
extensions: []
  • Required: title, description, and at least one of instructions or prompt.
  • prompt is required for headless runs.
  • version defaults to 1.0.0.
  • Optional: activities, extensions, parameters, response, retry, settings, sub_recipes.
  • Use .yaml or .json. The CLI does not support .yml files.

Parameters

Parameter block

parameters:
  - key: language
    input_type: string
    requirement: required
    description: "Language to review"
  • Each parameter needs key, input_type, requirement and description.
  • input_type: string (default), number, boolean, date, file or select. select also needs options.
  • requirement: required, optional or user_prompt.
  • optional parameters need a default. required and file parameters cannot have one.

Run a recipe

Shell

goose run --recipe recipe.yaml
goose run --recipe ./recipes/my-recipe.yaml
goose run --recipe recipe.yaml --interactive
goose run --recipe recipe.yaml --params language=Python

For a recipe in your GitHub recipe repo, use its folder name, for example goose run --recipe code-review.

Where goose finds recipes

  • The current folder.
  • Folders listed in the GOOSE_RECIPE_PATH environment variable.
  • A GitHub repo set with GOOSE_RECIPE_GITHUB_REPO in owner/repo format, used when a recipe is not found locally.
  • Keep each recipe in its own folder as recipe.yaml or recipe.json.

Settings, response and sharing

  • settings can set goose_provider, goose_model, temperature and max_turns.
  • response.json_schema validates the final output.
  • Make a share link with goose recipe deeplink <FILE> --param key1=value1.

Shell

goose recipe deeplink recipe.yaml --param language=Python

Sources

More goose guides

Reviewed Oct 23, 2026. Settings change often; the linked vendor docs are the source of truth.

Built an MCP server? Get it listed everywhere →

Shipping an Android app? Google Play needs 12 testers for 14 days first. Get them with Tester Exchange →