Skip to content
| Marketplace
Sign in
Visual Studio Code>Other>Agent TODOsNew to Visual Studio Code? Get it now.
Agent TODOs

Agent TODOs

Preview

Harald Kirschner

|
32 installs
| (2) | Free
Gives VS Code agent mode planning superpowers with dynamic todo lists
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

Agent TODOs

CI Release VS Code Marketplace Downloads

Your AI pair programmer's memory system. Seamlessly integrate persistent task tracking with GitHub Copilot and VS Code's native AI features—giving your coding assistant perfect memory across sessions.

"Finally, an AI assistant that remembers what we planned to do next."

Why Agent TODOs?

VS Code's agent mode is brilliant at writing code but lacks persistent memory between sessions. AI can spot TODO comments but can't maintain an actionable task list that evolves with your project.

Agent TODOs bridges this gap by giving VS Code's AI ecosystem a dedicated memory system for tracking tasks, context, and priorities across coding sessions.

Key Features

  • 🤖 Native VS Code Integration: Built-in todo_read and todo_write tools that work seamlessly with GitHub Copilot and VS Code's agent mode
  • 🧠 Persistent AI Memory: AI can read, update, and remember tasks between sessions—no more lost context
  • 📋 Visual Task Management: Interactive tree view in VS Code's Explorer with one-click status updates
  • 🔗 Auto-Sync with Copilot: Automatically inject todos into .github/copilot-instructions.md for enhanced AI context
  • ⚡ Instant AI Execution: Run todos directly in VS Code Chat with context-aware assistance
  • 🎯 Smart Organization: Subtasks, priorities, rich descriptions, and three-state workflow (pending → in-progress → completed)
  • 🔧 Flexible Integration: Works as VS Code extension or standalone MCP server for advanced integrations

How It Works

  1. Install → Extension adds todo tools to GitHub Copilot automatically
  2. Plan → Ask Copilot to create and organize your development tasks
  3. Track → Visual tree view shows progress; AI remembers everything
  4. Execute → Run todos directly in VS Code Chat with full context

🔄 Example Workflow

You: "Create a todo list for implementing user authentication"

GitHub Copilot: "I'll create a structured plan for user authentication. Let me organize this into actionable tasks..."

📝 Creating todos:
• Set up authentication routes (high priority)
• Configure auth library integration
• Create login/register endpoints
• Add JWT middleware for protected routes
• Write authentication tests

You: "Start with the first task"

GitHub Copilot: "I'll help you set up the authentication routes. First, let me mark this as in-progress..."

🔄 Updated todo: "Set up authentication routes" → in_progress

*Creates auth.routes.ts file*
*Implements basic route structure*

✅ Marking "Set up authentication routes" as completed

Now configuring the auth library integration...

🔄 Updated todo: "Configure auth library integration" → in_progress

*Installs passport and express-jwt packages*
*Sets up auth configuration*

✅ Completed "Configure auth library integration"

You: "What's left to do?"

GitHub Copilot: "Let me check your remaining todos..."

📋 Authentication TODOs (2/5 completed):
✅ Set up authentication routes
✅ Configure auth library integration
⏳ Create login/register endpoints (next up)
⏳ Add JWT middleware for protected routes
⏳ Write authentication tests

You: "Use the existing auth library we have"

GitHub Copilot: "I see you already have `express-jwt` and `passport` in your dependencies. Let me update our approach to leverage these existing libraries..."

🔄 Updated todo: "Create login/register endpoints" → in_progress

*Configures passport strategies*
*Integrates with existing user model*
*Creates streamlined auth endpoints using passport*

✅ Completed "Create login/register endpoints"

The existing auth library simplified our implementation significantly. Let me now add the JWT middleware...

🔄 Updated todo: "Add JWT middleware for protected routes" → in_progress

Quick Start

For AI Assistants (Recommended)

  1. Install the extension from VS Code Marketplace
  2. Chat with GitHub Copilot: Your AI now has todo_read and todo_write tools automatically
  3. Start planning: Ask Copilot to create todos, track progress, or suggest next steps
  4. Watch the magic: Todos appear in the Explorer tree view and sync with Copilot's memory

Try asking GitHub Copilot:

  • "Create a todo list for implementing user authentication"
  • "What should I work on next based on my current todos?"
  • "Mark the database setup task as completed and suggest the next step"

Get Started

Quick Setup

  1. Install from VS Code Marketplace
  2. Open VS Code Chat and start planning with GitHub Copilot
  3. Enable Auto-sync (optional): Settings > Extensions > Agent TODOs > Auto-inject

Try These Commands

Ask GitHub Copilot:

  • "Create a todo list for implementing user authentication"
  • "What should I work on next based on my current todos?"
  • "Mark the database setup task as completed and suggest the next step"

Requirements

  • VS Code 1.101.0 or higher
  • GitHub Copilot extension

Contributing

Found a bug or have a feature request? Open an issue or submit a pull request.

License

MIT License - see LICENSE for details.

  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
© 2025 Microsoft