agent-planners

What problem does it solve?

This Skill solves the problem of unstructured agent thinking by providing planner components that add consistent planning instructions and enforce predictable output structure before each LLM call.

Core Features & Use Cases

• Custom planning injection: Use BasePlanner to generate optional planning instructions per request.
• PlanReAct enforced structure: Require /*PLANNING*/ and /*FINAL_ANSWER*/ blocks for clearer intermediate reasoning and safer final responses.
• Task board planning: Use TaskPlanner to maintain a task board in ctx.state and inject task status into the system prompt, designed to pair with ManageTasksTool.

Quick Start

Add a planner to your LlmAgent configuration, using PlanReActPlanner for tagged planning blocks or TaskPlanner for maintainable, tool-driven task status.