Skip to main content
The todo tool gives agents structured task management. The agent calls write_todos to create and update a task list, and the TaskPlanner injects the current status into the system prompt before each LLM call.

Setup

write_todos

The agent calls write_todos with a JSON array of task objects. Each call replaces the entire list.

Task fields

Auto-generated fields

TaskPlanner

TaskPlanner reads from the shared TodoList and injects the current status into the system prompt before each LLM call:

Initial task seeding

You can pre-seed tasks via the planner:
Tasks are seeded on the first LLM call if the todo list is empty.

Checking completion

TodoList API

Verification nudge

When all tasks are marked as completed, the tool automatically appends a reminder for the agent to verify its work before responding — unless a task already contains “verify”, “test”, or “check” in its content.