Skip to main content

Recipe Reference Guide

Recipes are reusable goose configurations that package up a specific setup so it can be easily shared and launched by others.

Recipe File Format​

Recipes can be defined in either:

  • .yaml files (recommended)
  • .json files

See Shareable Recipes to learn how to create, use, and manage recipes.

CLI and Desktop Formats​

goose recipes use two formats:

  • CLI Format: Recipe fields (like title, description, instructions) are at the root level of the YAML/JSON file. This format is used when recipes are created via the CLI /recipe command and Recipe Generator YAML option.
  • Desktop Format: Recipe fields are nested inside a recipe object, with additional metadata fields at the root level. This format is used when recipes are created from goose Desktop.

The CLI automatically detects and handles both formats for .yaml and .json recipe files when running goose run --recipe <file> and goose recipe commands. The Desktop can import .yaml, .yml, and .json recipe files (or deeplinks) in either CLI or Desktop format.

Format Examples

Recipes can be written in either YAML or JSON format. Both formats follow the same schema structure.

CLI Format​

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: []

Desktop Format​

name: "Code Review Assistant"
recipe:
  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: []
isGlobal: true
lastModified: 2025-07-02T03:46:46.778Z
isArchived: false
note

goose automatically adds metadata fields to recipes saved from the Desktop app.

Recipe Structure​

Required Fields​

FieldTypeDescription
versionStringThe recipe format version (e.g., "1.0.0")
titleStringA short title describing the recipe
descriptionStringA detailed description of what the recipe does

Optional Fields​

FieldTypeDescription
instructionsStringTemplate instructions that can include parameter substitutions
promptStringA template prompt that can include parameter substitutions; required in headless (non-interactive) mode
parametersArrayList of parameter definitions
activitiesArrayList of example prompts that appear as clickable bubbles in goose Desktop
extensionsArrayList of extension configurations
settingsObjectConfiguration for model provider, model name, and other settings
sub_recipesArrayList of subrecipes
responseObjectStructured output schema for automation workflows
retryObjectConfiguration for automated retry logic with success validation

Desktop Format Metadata Fields​

When recipes are saved from goose Desktop, additional metadata fields are included at the top level (outside the recipe key). These fields are used by the Desktop app for organization and management but are ignored by CLI operations.

FieldTypeDescription
nameStringDisplay name used in Desktop Recipe Library
isGlobalBooleanWhether the recipe is available globally or locally to a project
lastModifiedStringISO timestamp of when the recipe was last modified
isArchivedBooleanWhether the recipe is archived in the Desktop interface

Parameters​

The parameters field allows you to create dynamic, reusable recipes that can be customized for different contexts. Parameters define placeholders that users fill in when running the recipe, making the recipe more flexible and adaptable.

Parameter substitution uses Jinja-style template syntax with {{ parameter_name }} placeholders. Each parameter in the parameters array has the following structure:

Required Parameter Fields​

FieldTypeDescription
keyStringUnique identifier for the parameter
input_typeStringType of input: "string" (default) or "file" (reads file contents)
requirementStringOne of: "required", "optional", or "user_prompt"
descriptionStringHuman-readable description of the parameter

Optional Parameter Fields​

FieldTypeDescription
defaultStringDefault value for optional parameters

Parameter Requirements​

  • required: Parameter must be provided when using the recipe
  • optional: Can be omitted if a default value is specified
  • user_prompt: Will interactively prompt the user for input if not provided

The required and optional parameters work best for recipes opened in goose Desktop. If a value isn't provided for a user_prompt parameter, the parameter won't be substituted and may appear as literal {{ parameter_name }} text in the recipe output.

Input Types​

  • string: Default type. The parameter value is used as-is in template substitution
  • file: The parameter value should be a file path. goose reads the file contents and substitutes the actual content (not the path) into the template

When using input_type: file, this is useful for including file contents directly in your prompts or instructions.

Example:

parameters:
  - key: source_code
    input_type: file
    requirement: required
    description: "Path to the source code file to analyze"

prompt: "Please review this code:\n\n{{ source_code }}"

When you run this recipe with source_code: /path/to/app.py, goose will read the contents of app.py and substitute the actual code into the {{ source_code }} placeholder.

important
  • Optional parameters MUST have a default value specified
  • Required parameters cannot have default values
  • File parameters cannot have default values regardless of requirement type to prevent unintended importing of sensitive files
  • Parameter keys must match any template variables used in instructions, prompt, or activities

Parameter Substitution in Desktop​

When a recipe with parameters is opened in goose Desktop, users are presented with a Recipe Parameters dialog where they can:

  • Provide values for required parameters
  • Modify or accept default values for optional parameters
  • Enter values for user_prompt parameters

Once parameter values are submitted, they are substituted into the recipe's instructions, prompt, and activities fields before the recipe starts.

Activities​

The activities field defines an optional message and clickable activity bubbles (buttons) that appears when a recipe is opened in goose Desktop.

Desktop only

Activities are a Desktop-only feature. When recipes with activities are run via the CLI or as a scheduled job, the activities field is ignored and has no effect on recipe execution.

Activity Types​

Activities can be defined in two ways:

  1. Message Activity: Displays the markdown-formatted activity text in an info box above the activity bubbles. For example:

    activities:
      - "message: **Welcome!** Here's what I can help with:\n\n• 📊 Data analysis\n• 🔍 Code review\n• 📝 Documentation\n\nSelect an option below to begin."

    Only include one message: prefixed activity. Additional message: prefixed activities become regular clickable bubbles (and display the literal "message:" text).

  2. Button Activities: Text to display in activity bubbles, which send the activity text as a prompt when clicked

Parameter Substitution​

Activities support parameter substitution, allowing you to create dynamic, personalized activity bubbles. After users provide parameter values in the Recipe Parameters dialog, the values are substituted into the activity text before the bubbles are displayed.

Example Configuration​

version: "1.0.0"
title: "Code Review Assistant"
description: "Review code with customizable focus areas"
parameters:
  - key: language
    input_type: string
    requirement: required
    description: "Programming language to review"
  - key: focus
    input_type: string
    requirement: optional
    default: "best practices"
    description: "Review focus area"

activities:
  - "message: Click an option below to start reviewing {{ language }} code with a focus on {{ focus }}."
  - "Review the current file for {{ focus }}"
  - "Suggest improvements for {{ language }} code quality"
  - "Check for security vulnerabilities"
  - "Generate unit tests"

In this example:

  • The message activity displays instructions with substituted parameter values, for example: "Click an option below to start reviewing rust code with a focus on best practices."
  • The first two activity bubbles use parameter substitution, for example: "Review the current file for best practices"
  • The last two activity bubbles are static prompts that work regardless of parameters

Extensions​

The extensions field allows you to specify which Model Context Protocol (MCP) servers and other extensions the recipe needs to function. Each extension in the array has the following structure:

Extension Fields​

FieldTypeDescription
typeStringType of extension (e.g., "stdio")
nameStringUnique name for the extension
cmdStringCommand to run the extension
argsArrayList of arguments for the command
env_keysArray(Optional) Names of environment variables required by the extension
timeoutNumberTimeout in seconds
bundledBoolean(Optional) Whether the extension is bundled with goose
descriptionStringDescription of what the extension does
available_toolsArrayList of tool names within the extension that will be available. When not specified all will be available

Example Extension Configuration​

extensions:
  - type: stdio
    name: codesearch
    cmd: uvx
    args:
      - mcp_codesearch@latest
    timeout: 300
    bundled: true
    description: "Query https://codesearch.sqprod.co/ directly from goose"
  
  - type: stdio
    name: presidio
    timeout: 300
    cmd: uvx
    args:
      - 'mcp_presidio@latest'
    available_tools:
      - query_logs

  - type: stdio
    name: github-mcp
    cmd: github-mcp-server
    args: []
    env_keys:
      - GITHUB_PERSONAL_ACCESS_TOKEN
    timeout: 60
    description: "GitHub MCP extension for repository operations"

Extension Secrets​

This feature is only available through the CLI.

If a recipe uses an extension that requires a secret, goose can prompt users to provide the secret when running the recipe:

  1. When a recipe is loaded, goose scans all extensions (including those in subrecipes) for env_keys fields
  2. If any required environment variables are missing from the secure keyring, goose prompts the user to enter them
  3. Values are stored securely in the system keyring and reused for subsequent runs

To update a stored secret, remove it from the system keyring and run the recipe again to be re-prompted.

info

This feature is designed to prompt for and securely store secrets (such as API keys), but env_keys can include any environment variable needed by the extension (such as API endpoints, configuration values, etc.).

Users can press ESC to skip entering a variable if it's optional for the extension.

Settings​

The settings field allows you to configure the AI model and provider settings for the recipe. This overrides the default configuration when the recipe is executed.

Settings Fields​

FieldTypeDescription
goose_providerString(Optional) The AI provider to use (e.g., "anthropic", "openai")
goose_modelString(Optional) The specific model name to use
temperatureNumber(Optional) The temperature setting for the model (typically 0.0-1.0)

Example Settings Configuration​

settings:
  goose_provider: "anthropic"
  goose_model: "claude-sonnet-4-20250514"
  temperature: 0.7
settings:
  goose_provider: "openai"
  goose_model: "gpt-4o"
  temperature: 0.3
note

Settings specified in a recipe will override your default goose configuration when that recipe is executed. If no settings are specified, goose will use your configured defaults.

Subrecipes​

The sub_recipes field specifies the subrecipes that the main recipe calls to perform specific tasks. Each subrecipe in the array has the following structure:

Subrecipe Fields​

FieldTypeDescription
nameStringUnique identifier for the subrecipe
pathStringRelative or absolute path to the subrecipe file
valuesObject(Optional) Pre-configured parameter values that are passed to the subrecipe
sequential_when_repeatedBoolean(Optional) Forces sequential execution of multiple subrecipe instances. See Running Subrecipes In Parallel for details

Example Subrecipe Configuration​

sub_recipes:
  - name: "security_scan"
    path: "./subrecipes/security-analysis.yaml"
    values:  # in key-value format: {parameter_name}: {parameter_value}
      scan_level: "comprehensive"
      include_dependencies: "true"
  
  - name: "quality_check"
    path: "./subrecipes/quality-analysis.yaml"

Automated Retry with Success Validation​

The retry field enables recipes to automatically retry execution if success criteria are not met. This is useful for recipes that might need multiple attempts to achieve their goal, or for implementing automated validation and recovery workflows.

Retry Configuration Fields​

FieldTypeDescription
max_retriesNumberMaximum number of retry attempts (required)
timeout_secondsNumber(Optional) Timeout for success check commands (default: 300 seconds)
on_failure_timeout_secondsNumber(Optional) Timeout for on_failure commands (default: 600 seconds)
checksArrayList of success check configurations (required)
on_failureString(Optional) Shell command to run when a retry attempt fails

Success Check Configuration​

Each success check in the checks array has the following structure:

FieldTypeDescription
typeStringType of check - currently only "shell" is supported
commandStringShell command to execute for validation (must exit with code 0 for success)

How Retry Logic Works​

  1. Recipe Execution: The recipe runs normally with the provided instructions
  2. Success Validation: After completion, all success checks are executed in order
  3. Retry Decision: If any success check fails and retry attempts remain:
    • Execute the on_failure command (if configured)
    • Reset the agent's message history to initial state
    • Increment retry counter and restart execution
  4. Completion: Process stops when either:
    • All success checks pass (success)
    • Maximum retry attempts are reached (failure)

Basic Retry Example​

version: "1.0.0"
title: "Counter Increment Task"
description: "Increment a counter until it reaches target value"
prompt: "Increment the counter value in /tmp/counter.txt by 1."

retry:
  max_retries: 5
  timeout_seconds: 10
  checks:
    - type: shell
      command: "test $(cat /tmp/counter.txt 2>/dev/null || echo 0) -ge 3"
  on_failure: "echo 'Counter is at:' $(cat /tmp/counter.txt 2>/dev/null || echo 0) '(need 3 to succeed)'"

Advanced Retry Example​

version: "1.0.0"
title: "Service Health Check"
description: "Start service and verify it's running properly"
prompt: "Start the web service and verify it responds to health checks"

retry:
  max_retries: 3
  timeout_seconds: 30
  on_failure_timeout_seconds: 60
  checks:
    - type: shell
      command: "curl -f http://localhost:8080/health"
    - type: shell  
      command: "pgrep -f 'web-service' > /dev/null"
  on_failure: "systemctl stop web-service || killall web-service"

Environment Variables​

You can configure retry behavior globally using environment variables:

  • GOOSE_RECIPE_RETRY_TIMEOUT_SECONDS: Global timeout for success check commands
  • GOOSE_RECIPE_ON_FAILURE_TIMEOUT_SECONDS: Global timeout for on_failure commands

These environment variables are overridden by recipe-specific timeout configurations.

Structured Output with response​

The response field enables recipes to enforce a final structured JSON output from goose. When you specify a json_schema, goose will:

  1. Validate the output: Validates the output JSON against your JSON schema with basic JSON schema validations
  2. Final structured output: Ensure the final output of the agent is a response matching your JSON structure

This feature is designed for non-interactive automation to ensure consistent, parseable output. Recipes can produce structured output when run from either the goose CLI or goose Desktop. See use cases and ideas for automation workflows.

Basic Structure​

response:
  json_schema:
    type: object
    properties:
      # Define your fields here, with their type and description
    required:
      # List required field names

Simple Example​

version: "1.0.0"
title: "Task Summary"
description: "Summarize completed tasks"
prompt: "Summarize the tasks you completed"
response:
  json_schema:
    type: object
    properties:
      summary:
        type: string
        description: "Brief summary of work done"
      tasks_completed:
        type: number
        description: "Number of tasks finished"
      next_steps:
        type: array
        items:
          type: string
        description: "Recommended next actions"
    required:
      - summary
      - tasks_completed

Template Support​

Recipes support Jinja-style template syntax in instructions, prompt, and activities fields:

instructions: "Follow these steps with {{ parameter_name }}"
prompt: "Your task is to {{ action }}"
activities:
  - "Process {{ parameter_name }} with {{ action }}"

Advanced template features include:

  • Template inheritance using {% extends "parent.yaml" %}
  • Blocks that can be defined and overridden: 
    {% block content %}
    Default content
    {% endblock %}
  • indent() template filter

indent() Filter For Multi-Line Values​

Use the indent() filter to ensure multi-line parameter values are properly indented and can be resolved as valid JSON or YAML format. This example uses {{ raw_data | indent(2) }} to specify an indentation of two spaces when passing data to a subrecipe:

sub_recipes:
  - name: "analyze"
    path: "./analyze.yaml"
    values:
      content: |
        {{ raw_data | indent(2) }}

Built-in Parameters​

ParameterDescription
recipe_dirAutomatically set to the directory containing the recipe file

Complete Recipe Example​

version: "1.0.0"
title: "Example Recipe"
description: "A sample recipe demonstrating the format"
instructions: "Follow these steps with {{ required_param }} and {{ optional_param }}"
prompt: "Your task is to use {{ required_param }} with {{ interactive_param }}"
parameters:
  - key: required_param
    input_type: string
    requirement: required
    description: "A required parameter example"
  
  - key: optional_param
    input_type: string
    requirement: optional
    default: "default value"
    description: "An optional parameter example"
  
  - key: interactive_param
    input_type: string
    requirement: user_prompt
    description: "Will prompt user if not provided"

extensions:
  - type: stdio
    name: codesearch
    cmd: uvx
    args:
      - mcp_codesearch@latest
    timeout: 300
    bundled: true
    description: "Query codesearch directly from goose"

settings:
  goose_provider: "anthropic"
  goose_model: "claude-sonnet-4-20250514"
  temperature: 0.7

retry:
  max_retries: 3
  timeout_seconds: 30
  checks:
    - type: shell
      command: "echo 'Task validation check passed'"
  on_failure: "echo 'Retry attempt failed, cleaning up...'"

response:
  json_schema:
    type: object
    properties:
      result:
        type: string
        description: "The main result of the task"
      details:
        type: array
        items:
          type: string
        description: "Additional details of steps taken"
    required:
      - result
      - details

Template Inheritance​

Parent recipe (parent.yaml):

version: "1.0.0"
title: "Parent Recipe"
description: "Base recipe template"
prompt: |
  {% block prompt %}
  Default prompt text
  {% endblock %}

Child recipe:

{% extends "parent.yaml" %}
{% block prompt %}
Modified prompt text
{% endblock %}

Recipe Location​

Recipes can be loaded from:

  1. Local filesystem:
  2. GitHub repositories:

Validation Rules​

Recipe files must be valid YAML or JSON. In addition, the following validation rules are enforced when loading recipes and are also checked by the goose recipe validate subcommand:

  • Required title and description fields must be present
  • At least one of instructions or prompt must be present
  • All template variables must have corresponding parameter definitions
  • Parameter keys must be unique (not enforced, but required for proper functionality)
  • All defined parameters must be used in template variables (no unused parameters)
  • Optional parameters must have default values
  • File parameters cannot have default values (prevents importing sensitive files)
  • response.json_schema must be a valid JSON schema if specified

Error Handling​

Common errors to watch for:

  • Missing required parameters
  • Optional parameters without default values
  • Template variables without parameter definitions
  • Invalid YAML/JSON syntax
  • Missing required fields
  • Invalid extension configurations
  • Invalid retry configuration (missing required fields, invalid shell commands)

When these occur, goose will provide helpful error messages indicating what needs to be fixed.

Retry-Specific Errors​

  • Invalid success checks: Shell commands that cannot be executed or have syntax errors
  • Timeout errors: Success checks or on_failure commands that exceed their timeout limits
  • Max retries exceeded: When all retry attempts are exhausted without success
  • Missing required retry fields: When max_retries or checks are not specified

Learn More​

Check out the Recipes guide for more docs, tools, and resources to help you master goose recipes.