🖥️ PC2016ConcernedApeVERY HARDStardew Valley rebuild deck
VERY HARD
The systems are a fortnight and they will all work, at which point you are staring at a very good farming engine with fifty characters' worth of dialogue missing from it.
You will get a good prototype. The product is what comes after.
The systems are a two-week build and they will work. The reason this is NOT REALLY is content: Stardew is one person doing everything for four years, and what you feel playing it is authored volume, not mechanics. A prompt gives you a very good farming engine with nothing to do in it. Which is still a fine thing to have built.
- Difficulty
- VERY HARD · 4 of 5
- First playable
- A project
- The original
- 4 team-years
- Released
- 2016 · PC
- Genre
- Farming Sim
Build a farming and life-sim prototype in the Stardew Valley mould. Top-down 2D, tile-based, Canvas or Phaser. Requirements: - Time system: 10 minutes per in-game hour, 6am to 2am, then forced sleep. Four seasons of 28 days, each changing which crops grow and what the tileset looks like. Save on sleep. - Farm plot: hoe tills soil, seeds planted, watering can with a capacity, crops advancing one growth stage per watered day. Unwatered crops pause; out-of-season crops die at the season boundary. - Energy budget: every tool swing costs energy, running out forces collapse and a penalty. This is the core constraint that makes the day feel scarce — tune it so a full day is genuinely not enough. - Inventory grid with stacking, a shipping bin that pays out overnight, and a shop with a daily stock. - Four NPCs with a schedule (different location per hour, per day, per season), a friendship value, gift preferences, and 3 dialogue lines per friendship tier. Store schedules and dialogue as JSON data files, not code. - Mine: procedurally generated floors with rocks, ore, ladders down, and simple slime enemies. A tool-upgrade loop gates depth. - Fishing minigame: a bar you hold to raise and release to lower, keeping a moving fish inside it against a progress meter. Definition of done: a full in-game week passes, crops mature, an NPC greets me differently on day 7 than on day 1.
- Roughly 50 characters with hand-written dialogue that changes across seasons, events and relationships
- Content volume — hundreds of items, recipes, fish, and a decade of update cadence
- The pixel art and the soundtrack, which are half of why anyone plays it
- The sense that the town remembers you
NPC daily schedules as queryable data
A town feeling alive is not writing, it is the fact that someone is at the bakery at eleven because they are always at the bakery at eleven. Author it once as data and every other system — quests, gossip, locked doors — can ask it questions instead of hard-coding answers.
ScopeA weekend— build just this, not the game
Build a schedule-driven town toy as a single self-contained HTML file, Canvas 2D, no build step.
A small top-down map with six named locations and a path graph between them. Four characters, each with a schedule held in a JSON block: entries keyed by season and day of week, each a list of {hour, location}. Every tick the sim asks the schedule where a character should be and walks them there along the graph rather than teleporting them.
Two rules that carry it. Lookup falls back from most specific (season plus day) to a default, so you only author the exceptions. And a character's current location and destination are queryable by any other system, including while they are in transit on a path.
Give me a clock I can scrub from 6am to midnight, plus day and season selectors.
Definition of done: I scrub to Tuesday 2pm in autumn and all four are somewhere deliberate, and one of them has a different Tuesday from their Monday.Not a clone — Stardew Valley re-themed and cut down to something you can finish. The angle is the important reel: it is what turns a project into a weekend. 5,880 ways to land.
Ironworks From Above
Stardew Valley, but a management sim of the same world, set in a dieselpunk war. Rendered in claymation with baked light.
Build a browser game called "Ironworks From Above". The pitch in one line: a farming sim in the spirit of Stardew Valley, but a management sim of the same world, set in a dieselpunk war. WHAT THIS IS Take the SHAPE of Stardew Valley — its core loop, and whatever makes that loop good — and rebuild it as your own game in a different world at a smaller scope. Use your own names, art and audio, which you want anyway: a reskin of somebody else's game is less interesting than a new one that works the same way. THE ANGLE — this is the important constraint, honour it above everything else A management sim of the same world. The player never controls a character — they set policy and watch agents with visible needs succeed or fail at it. This is what makes the project finishable. If a decision would push the scope back towards the original's, take the smaller option every time. THE THEME A dieselpunk war. Heavy machinery that takes time to start, riveted plate, and logistics as the real front line. The theme is not a coat of paint. Let it change what the mechanics mean — a reload, a health pack and a locked door should all be things that make sense in this world and nowhere else. LOOK Claymation with baked light. Soft rounded geometry, a fingerprint-style normal texture, stop-motion timing at 12fps for characters while the camera stays at 60. REQUIREMENTS - Runs in a browser with no build step. Canvas 2D unless the angle genuinely requires 3D, in which case three.js. - Fixed-timestep update loop with interpolated rendering, so it behaves the same at 60Hz and 144Hz. - Every tuning constant in one CONFIG object at the top, exposed as live sliders in a debug panel. You will find the feel by dragging those, not by prompting. - All content — levels, entities, balance numbers — in JSON or plain data files, never inline in the logic. - Audio generated with the Web Audio API rather than asset files. - Respect prefers-reduced-motion: keep the fades, drop the shake and the parallax. BUILD ORDER 1. The core loop with placeholder rectangles, at the reduced scope the angle demands. No theme, no art, no audio. Make it fun as rectangles first. 2. The angle's consequences. Cutting to bots, or to turn-based, or to one level changes the design rather than just shrinking it — find out how and rewrite step 1. 3. The theme, as content and data. 4. The look, applied last as a rendering layer over a game that already works. Start by writing a one-page plan: the core loop, what the angle removes and what that frees you to do properly, and what you are deliberately leaving out. Wait for me to approve it before writing code.
Half the time one of these already does what you wanted, and the other half it saves you a week of solving a problem someone documented in 1997.
One count per game. No account — it is tied to a salted hash of your IP, which is not stored in a form anyone can reverse. Every build adds 4 team-years to the counter on the homepage.
Then try these
Questions
How hard is Stardew Valley to rebuild with an AI agent?
Yes — every game is buildable at some scope. The question is how hard, and Stardew Valley is VERY HARD (4 of 5). You will get a good prototype. The product is what comes after. The systems are a fortnight and they will all work, at which point you are staring at a very good farming engine with fifty characters' worth of dialogue missing from it. Reckon on a project to something you can actually play — not to something that matches the 4 team-years ConcernedApe spent.
What makes Stardew Valley hard to rebuild?
The systems are a fortnight and they will all work, at which point you are staring at a very good farming engine with fifty characters' worth of dialogue missing from it. That is why it sits at VERY HARD rather than a tier either side of it. If you want the idea without the project, the transferable part is npc daily schedules as queryable data — a weekend of work.
How long does it take to build a Stardew Valley clone?
Wrong question, and it is worth saying why. Nobody rebuilds Stardew Valley — the original took ConcernedApe on the order of 4 team-years, released in 2016 on PC. What you can do is reach something playable and genuinely yours in about a project, and then keep going for as long as it stays interesting. Any figure that claims otherwise is measuring a prototype and calling it a game.
What do I lose by building my own Stardew Valley?
Roughly 50 characters with hand-written dialogue that changes across seasons, events and relationships. Content volume — hundreds of items, recipes, fish, and a decade of update cadence. The pixel art and the soundtrack, which are half of why anyone plays it. Those are the parts a prompt will not hand you.
Which AI coding agent should I use to build it?
Any of Claude Code, Codex or Cursor will handle this prompt. Paste it as your first message, let the agent scaffold the project, then iterate on feel — the second, third and tenth prompts are where a game actually gets good. Work in an empty folder or a fresh git branch so you can throw it away cheaply.
One email when new games go on the list. No other reason to email you, ever.