Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models. From arXiv:2601.08955
Scanned 9/9/2026
Install to Claude Code
npx -y skills add ADu2021/skillXiv --skill imagine-then-plan-world-model --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Imagine Then Plan World Model?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/adu2021-imagine-then-plan-world-model)More formats (shields.io, HTML) on the badges page.
---
name: imagine-then-plan-world-model
title: "Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models"
version: 0.0.2
engine: skillxiv-v0.0.2-claude-opus-4.6
license: MIT
url: "https://arxiv.org/abs/2601.08955"
keywords: ['Imagine-then-Plan']
description: "Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models. From arXiv:2601.08955"
---
## Overview
This skill implements the approach from the paper: Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models
## Purpose
Implements advanced techniques for agent reasoning, search, and learning described in arXiv:2601.08955.
## Method
[To be populated from full paper analysis]
## When NOT to use
- Oversimplified reasoning tasks
- Time-critical applications requiring minimal overhead
- Scenarios not matching the paper's problem formulation
## References
- Paper: https://arxiv.org/abs/2601.08955
- HTML: https://arxiv.org/html/2601.08955
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.