agent-planners

Inject structured planning instructions and maintain planning state across LLM calls.

19|6|Updated Mar 12, 2026

Search Tags:#task management #agent orchestration #Python #agent planning #llm prompts #react planning

Ready to run

npx skills add https://github.com/NicolaiLassen/orxhestra --skill agent-planners

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-planners
Source: https://github.com/NicolaiLassen/orxhestra/tree/main/docs/skills/agent-planners
Command: npx skills add https://github.com/NicolaiLassen/orxhestra --skill agent-planners

SYSTEM DOCUMENTATION & REQUIREMENTS

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.

Frequently Asked Questions about agent-planners

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I add structured planning to my Python agents before LLM calls?▼

Add structured planning to Python agents by injecting deterministic planning instructions and maintaining planning state across LLM calls using BasePlanner methods. This enforces predictable output structure and consistent reasoning before execution.

What is ReAct-style planning and how does it enforce agent output structure?▼

ReAct-style planning enforces agent output structure by requiring explicit /*PLANNING*/ and /*FINAL_ANSWER*/ blocks. This separation ensures clearer intermediate reasoning and safer final responses during LLM-driven task execution.

How do I maintain a task board for agent orchestration across multiple steps?▼

Maintain a task board for agent orchestration by storing task status in ctx.state and injecting it into the system prompt. This approach pairs with ManageTasksTool actions to drive tool-based task execution.

Can I use custom planning instructions for each agent request?▼

Yes, you can generate custom planning instructions per request by implementing BasePlanner. It allows you to inject optional planning instructions dynamically, adapting the agent reasoning structure to specific workflow needs.

When should I use task board planning instead of ReAct-style planning blocks?▼

Use task board planning when you need maintainable, tool-driven task status updates across steps, and choose ReAct-style planning blocks when you need explicit intermediate reasoning and safer final responses without external task management.

Do I need external dependencies to manage task state in agent workflows?▼

No external dependencies are required to manage task state. The Skill handles task state injection natively through ctx.state with ManageTasksTool actions, maintaining task status directly within the agent workflow.