Goose Extensible AI Coding Agent by Block
Goose Extensible AI Coding Agent by Block
An open-source, extensible AI agent from Block (formerly Square) that goes beyond code suggestions to install packages, execute commands, edit files, and run tests. Supports any LLM and extends via MCP servers for tool integration.
Goose is an open-source AI coding agent developed by Block (the company behind Square, Cash App, and Bitkey). With over 33,000 GitHub stars, it has become one of the most popular terminal-based coding agents. Unlike simpler code completion tools, Goose can take autonomous actions: installing dependencies, running commands, editing multiple files, and executing test suites.
How It Works
Goose operates as both a CLI tool and a desktop application. You describe a task in natural language, and the agent plans and executes a series of steps to accomplish it. It can read and understand your entire codebase, make coordinated edits across multiple files, run shell commands to verify changes, and iterate based on test results or error output.
The agent supports any LLM as its reasoning backend, including Claude, GPT-4, Gemini, and local models. You configure your preferred provider and model, and Goose handles the tool-calling protocol to translate natural language into concrete actions.
Extension System
Goose extends through MCP (Model Context Protocol) servers, which are plugins that expose additional tools and data sources. This means you can connect Goose to your GitHub repositories, Jira boards, Slack channels, databases, or any other service with an MCP server. The extension system makes Goose customizable for specific team workflows and technology stacks.
Key Capabilities
File operations include reading, writing, searching, and patching across your project. Shell command execution runs builds, tests, linters, and any other CLI tools. Built-in web search and browsing let Goose look up documentation or API references. Structured planning breaks complex tasks into manageable steps before execution. Session memory maintains context across long interactions.
More from agentskillexchange/skills
your skill name
A clear description of what this skill does and when to use it. Reference specific APIs, tools, or techniques.
23playwright visual regression tester
Automates visual regression testing using the Playwright screenshot comparison API and pixelmatch diffing library. Captures baseline snapshots, detects pixel-level UI changes across viewport sizes, and generates HTML diff reports with threshold-based pass/fail results.
2playwright visual regression suite
Automated visual regression testing using Playwright’s screenshot comparison API (page.screenshot with maxDiffPixelRatio) and toMatchSnapshot assertions. Supports cross-browser testing on Chromium, Firefox, and WebKit.
2stripe payments connector
Full Stripe API integration using the stripe-node SDK. Creates PaymentIntents via stripe.paymentIntents.create(), manages Customers and Subscriptions, handles webhook events through stripe.webhooks.constructEvent(), and supports Stripe Connect for marketplace payouts.
2grafana loki log query agent
Queries Grafana Loki log aggregation system using LogQL via the Loki HTTP API. Filters log streams by labels, parses structured JSON logs, and correlates log entries with Grafana dashboard panels.
2great expectations data validation pipeline
Validate data quality using the Great Expectations Python library. Define expectations as unit tests for your data, run validation suites, and generate human-readable data quality reports.
1