Bookmark this page. Use Ctrl+F (or Cmd+F on Mac) to find what you need. This cheat sheet compares AI coding tools, their features, pricing, and best use cases.
Last updated: March 2026
Tool Comparison
| Tool | Type | Best For | Pricing (Mar 2026) |
|---|---|---|---|
| Claude Code | CLI agent | Multi-file edits, refactoring, debugging | $20/mo Pro, $100/$200 Max |
| Cursor | IDE (VS Code fork) | Day-to-day coding with AI inline | $20/mo (Pro) |
| GitHub Copilot | IDE extension | Autocomplete, inline suggestions | Free (limited), $10/mo Pro, $39/mo Pro+ |
| Windsurf | IDE (VS Code fork) | Chat + agent workflows | $15/mo (Pro) |
| ChatGPT | Chat | Explaining code, brainstorming | $20/mo (Plus) |
| Gemini CLI | CLI | Quick questions, code review | Free (1K req/day), Pro/Ultra plans |
| Codex CLI | CLI | Code review, autonomous tasks | OpenAI API pricing |
Feature Matrix
| Feature | Claude Code | Cursor | Copilot | Windsurf |
|---|---|---|---|---|
| Autocomplete | — | Yes | Yes | Yes |
| Chat | Yes | Yes | Yes | Yes |
| Multi-file editing | Yes | Yes | Limited | Yes |
| Terminal commands | Yes | Yes (Cmd+K in terminal) | — | — |
| Agent mode | Yes | Yes | Yes | Yes |
| Git integration | Yes | Yes | Yes | Yes |
| MCP support | Yes | Yes | Yes | Yes |
| Custom rules | CLAUDE.md | .cursorrules | .github/copilot-instructions.md | .windsurfrules |
| Context window | 200K (up to 1M on Max) | 128K | 128K | 128K |
Claude Code Shortcuts
| Command | Description |
|---|---|
/help | Show available commands |
/clear | Clear conversation |
/compact | Compress context to save tokens |
/cost | Show token usage and cost |
/init | Create CLAUDE.md project file |
Esc | Cancel current generation |
Shift+Tab | Accept file edit |
Ctrl+C | Exit |
Claude Code Tips
# Run Claude Code
claude
# Start with a prompt
claude "fix the failing tests"
# Non-interactive mode
claude -p "explain this function" < file.py
# Use a specific model
claude --model sonnet # or opus, haiku
# Continue last conversation
claude --continue
CLAUDE.md — Project Instructions
# CLAUDE.md
- Use TypeScript strict mode
- Tests: Jest with React Testing Library
- Style: Tailwind CSS, no inline styles
- Always run tests before committing
Place CLAUDE.md in your project root. Claude reads it automatically.
Cursor Shortcuts
| Shortcut | Action |
|---|---|
Cmd+K / Ctrl+K | Inline edit (AI rewrites selected code) |
Cmd+L / Ctrl+L | Open AI chat panel |
Cmd+I / Ctrl+I | Composer (multi-file agent) |
Tab | Accept autocomplete suggestion |
Esc | Dismiss suggestion |
Cmd+Shift+P | Command palette |
@file | Reference a file in chat |
@codebase | Search entire codebase for context |
@web | Search the web |
@docs | Reference documentation |
.cursorrules — Project Instructions
You are a senior TypeScript developer.
- Use functional components with hooks
- Prefer Tailwind CSS utility classes
- Write tests for every new function
GitHub Copilot Shortcuts
| Shortcut | Action |
|---|---|
Tab | Accept suggestion |
Esc | Dismiss suggestion |
Alt+] / Option+] | Next suggestion |
Alt+[ / Option+[ | Previous suggestion |
Ctrl+Enter | Open Copilot completions panel |
Cmd+I / Ctrl+I | Inline chat (Copilot Chat) |
Effective Prompting Tips
| Tip | Example |
|---|---|
| Be specific | “Add error handling to the fetchUsers function in api.ts” not “fix the code” |
| Give context | “This is a Next.js 14 app using App Router and Prisma ORM” |
| Specify output | “Return only the modified function, not the full file” |
| Reference files | “Look at src/types.ts for the User interface” |
| Ask for alternatives | “Show me 3 different ways to implement this” |
| Iterate | “Good, but use async/await instead of .then()” |
When to Use Which Tool
| Scenario | Best Tool |
|---|---|
| Quick inline autocomplete while typing | Copilot or Cursor |
| Large refactoring across many files | Claude Code |
| Explaining unfamiliar code | ChatGPT or Claude Code |
| Building a new feature from scratch | Cursor Composer or Claude Code |
| Code review | Codex CLI or Claude Code |
| Debugging a tricky bug | Claude Code (terminal access) |
| Writing documentation | ChatGPT or Claude Code |
| Learning a new framework | ChatGPT (conversational) |
MCP (Model Context Protocol)
MCP lets AI tools connect to external services (databases, APIs, Figma):
// .mcp.json in project root
{
"mcpServers": {
"postgres": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-postgres"],
"env": { "DATABASE_URL": "postgresql://..." }
}
}
}
Supported by: Claude Code, Cursor, Copilot, Windsurf. Lets the AI query your database, read Figma designs, or interact with any MCP-compatible service. See our MCP Protocol Explained article for details.
Common Mistakes
Accepting code without reviewing — AI suggestions can contain bugs, security issues, or outdated patterns. Always read the diff before accepting. Treat AI output as a junior developer’s first draft.
Not providing enough context — “Fix the bug” gives bad results. “Fix the null pointer in handleSubmit at line 42 of LoginForm.tsx — the user object can be undefined when the session expires” gives great results.
Using AI for everything — Simple tasks (renaming a variable, adding an import) are faster to do manually. Use AI for complex tasks where it saves significant time.
Related Resources
- Claude Code Setup Guide — get started with Claude Code
- Cursor vs Claude Code vs Copilot — detailed comparison
- What Are AI Coding Agents? — how agent mode works
- All Cheat Sheets