📄️ AI Coding Tools Overview
A quick look at the most popular AI coding assistants available.
📄️ Subagents
Subagents are specialized AI assistants that run in isolated contexts with their own conversation history and restricted tool access. Instead of handling everything in a single conversation, the main agent delegates focused tasks to subagents that work independently and return results.
📄️ Worktrees
Git worktrees let you have multiple working directories sharing the same repository. Each worktree has its own files, branch, and working state while sharing commit history and remotes. This enables parallel, isolated sessions.
📄️ Skills (Commands)
Skills are reusable instruction sets that extend what an AI assistant can do. You invoke them with /skill-name (in Claude Code), $skill-name (in Codex) or the assistant loads them automatically when they match the current task.
📄️ MCP (Model Context Protocol)
The Model Context Protocol (MCP) is an open standard for connecting language models to external tools and data sources. Think of it like USB for AI tools, a standardized way to plug in new capabilities without building custom integrations for each one.
📄️ Hooks
Hooks are shell commands that execute automatically at specific points in Claude Code's lifecycle. Unlike model decisions (which can vary), hooks are deterministic: they run when their trigger condition is met. Well-designed hooks can save context and reduce repeated manual steps.