Usage

Learn how to use MyCoder effectively for your development tasks.

Basic Usage

Running with a Prompt

The simplest way to use MyCoder is to provide a natural language prompt:

mycoder "Fix all TypeScript build errors and ensure tests pass"

Interactive Mode

You can run MyCoder in interactive mode for ongoing conversation:

mycoder -i

Reading Prompts from Files

For complex tasks, you can prepare your prompt in a file:

mycoder --file=my-task-description.txt

Command Line Options

Option	Description
[prompt]	Main prompt text (positional argument)
-i, --interactive	Run in interactive mode, asking for prompts
-f, --file	Read prompt from a specified file
-l, --logLevel	Set minimum logging level (debug, verbose, info, warn, error)
--tokenUsage	Output token usage at info log level
--headless	Use browser in headless mode with no UI showing (default: true)
--userSession	Use user's existing browser session instead of sandboxed session (default: false)
--pageFilter	Method to process webpage content (simple, none, readability)
--profile	Enable performance profiling of CLI startup
--provider	Specify the AI model provider to use (anthropic, openai, mistral, xai, ollama)
--model	Specify the model name to use with the selected provider
-h, --help	Show help
-V, --version	Show version number

Configuration

MyCoder provides a configuration system that allows you to set default values for various options. This saves you from having to specify the same options repeatedly on the command line.

Configuration is managed through a mycoder.config.js file in your project root:

// mycoder.config.js
export default {
  // GitHub integration
  githubMode: true,

  // Browser settings
  headless: false,
  userSession: false,
  pageFilter: 'readability',

  // Model settings
  provider: 'anthropic',
  model: 'claude-3-7-sonnet-20250219',

  // Custom settings
  customPrompt: 'Always use TypeScript when writing code. Prefer functional programming patterns when possible.',
};

Available Configuration Options

Option	Description	Example in mycoder.config.js
logLevel	Default logging level	logLevel: 'verbose'
tokenUsage	Show token usage by default	tokenUsage: true
headless	Use browser in headless mode	headless: false
userSession	Use existing browser session	userSession: true
pageFilter	Default webpage content processing method	pageFilter: 'readability'
provider	Default AI model provider	provider: 'openai'
model	Default model name	model: 'gpt-4o'
customPrompt	Custom instructions to append to the system prompt	customPrompt: "Always use TypeScript"
githubMode	Enable GitHub integration mode	githubMode: true
profile	Enable performance profiling	profile: true

Custom Prompt

The customPrompt configuration option allows you to append custom instructions to the system prompt used by MyCoder. This can be useful for guiding the AI's behavior for your specific use cases:

// mycoder.config.js
export default {
  // Example: Set a custom prompt to prefer TypeScript
  customPrompt: "Always use TypeScript when writing code. Prefer functional programming patterns when possible.",
};

The custom prompt will be included in both the main agent and any sub-agents that are created.

GitHub Mode

MyCoder supports GitHub integration through the githubMode configuration option. When enabled, MyCoder will:

• Work with GitHub issues and PRs as part of its workflow
• Create branches for issues it's working on
• Make commits with descriptive messages
• Create PRs when work is complete

To enable GitHub mode:

// mycoder.config.js
export default {
  githubMode: true,
};

You can also enable it for a single session:

mycoder --githubMode true "Fix the bug in issue #42"

This requires the GitHub CLI (gh) to be installed and authenticated. For more details, see the GitHub Mode documentation.

Available Tools

MyCoder has access to a variety of tools that enable it to perform complex tasks:

Tool	Description	Use Case
textEditor	Views, creates, and edits files with persistence	Reading and modifying project files with advanced capabilities
shellStart	Executes shell commands	Running builds, tests, installations, git operations
shellMessage	Interacts with running shell processes	Working with interactive CLIs, monitoring long-running processes
fetch	Makes HTTP requests	Accessing APIs, downloading resources
browseStart	Starts a browser session	Researching documentation, exploring solutions
browseMessage	Performs actions in an active browser	Navigating websites, extracting information
agentStart	Starts a sub-agent and returns immediately	Creating asynchronous specialized agents for parallel tasks
agentMessage	Interacts with a running sub-agent	Checking status, providing guidance, or terminating sub-agents

For more detailed information about specific features, check the following pages:

• Configuration Options
• GitHub Mode
• Performance Profiling