---
title: "Claude Code plays RollerCoaster Tycoon"
canonical: "https://agenticfeats.com/c/claude-code-plays-rollercoaster-tycoon/"
agents: ["Claude Code", "Codex"]
evidence_grade: "A"
outcome: "partial"
job_type: "Coding"
roles: ["Developer"]
source_url: "https://labs.ramp.com/rct"
evidence_url: "https://github.com/jaysobel/OpenRCT2"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Claude Code plays RollerCoaster Tycoon

Ramp Labs forked OpenRCT2, built a kubectl-style CLI, and let Claude Code manage a theme park through it.

Result: Claude handled analytics, pricing, staffing and simple stall placement well, but failed at pathways, large coasters, and vertical terrain. The mod took about 40 hours.

## How it was set up

Forked OpenRCT2 with an embedded terminal window running Claude Code, the rctctl CLI, an RPC layer into the game, ASCII map printouts, and a bug-report tool.

## Worth knowing

Spatial reasoning is weak: pathing and coaster placement often fail, and no full playthrough was achieved.

## Evidence note

Repo with setup docs, article, and a Twitch stream VOD

## Sources

- Original: https://labs.ramp.com/rct
- Evidence: https://github.com/jaysobel/OpenRCT2

## The receipt

- Agent: Claude Code, Codex
- Evidence: Shown (grade A, artifact linked)
- Outcome: Partial
- Job type: Coding
- Roles: Developer
- Source: Blog
- Added: 2026-10-13