Pixel Orchard
An idle game about growing a tiny orchard, one tap a day
About
Plant a tree, come back tomorrow, watch it grow. Trade fruit with friends. Pixel Orchard is deliberately slow: one meaningful tap a day, no ads, no timers designed to annoy you.
8,000 people check their orchard every morning.
How it was made
Shared by the maker. Numbers are their own estimate.
- Build time
- 6 weeks
- AI spend
- $52
- Prompts
- ~260
- Written by AI
- 70%
Agents
Bolt
70% of the workGame loop and save system
Claude
30% of the workGame economy tuning
Midjourney · inside the product
Concept art for the seasons
MCP servers
No MCP servers. Built with the agents alone.
Build recipe
The code isn’t public. This is the whole project as one prompt: paste it into your own agent to build the same thing.
Written by Claude
From the project’s code and history · 321 words
Build a game called Pixel Orchard: an idle game about growing a tiny orchard, one tap a day.
What it does
Plant a tree, come back tomorrow, watch it grow. Trade fruit with friends. Pixel Orchard is deliberately slow: one meaningful tap a day, no ads, no timers designed to annoy you.
Stack
Use Phaser, TypeScript, Cloudflare. The original was built with Bolt and Claude in 6 weeks, for about $52 in AI usage.
How it fits together
- A small game loop with one core mechanic
- Local saves, plus a simple backend for sharing or leaderboards
- A daily or slow rhythm that brings people back
Build it in this order
- Build the core mechanic with placeholder art and make it fun
- Add saving and the daily rhythm
- Add art, sound and the share feature
- Tune the economy or difficulty with a quick simulation
- Test it with five people and watch where they stop
A prompt that worked: Tune a slow economy
Here's the growth and trading table for Pixel Orchard. Simulate 60 days for three players: one who plays every day, one who plays every third day, one who only trades. Show where the casual player falls too far behind to enjoy it, and suggest the smallest change to fix that without making daily play pointless.
Watch out for
- Prototype the mechanic before any art
- Respect the player's time: no timers designed to annoy
Done when
- Someone new gets the mechanic in thirty seconds
- Progress is never lost
- It runs well on a mid-range phone
Before writing code, ask me up to five questions about who this just for fun game is for and what the first version must do. Then work in small steps: after each one, tell me how to try it and wait for my feedback.
Discussion
3 comments · 1 member tried it
Ran it locally in under five minutes. README is great. Would you take a PR that adds a Docker set-up?
- Amara Okafor2 days ago
Copied the main prompt and adapted it for a project at work. Saved me an afternoon.
More like this
Paste a README, get honest notes on what a stranger won't understand