Skip to content
🍄 Nintendo2017Nintendo EPDVERY HARD

The Legend of Zelda: Breath of the Wild rebuild deck

VERY HARD

The elemental chemistry is a rules table you can write in a weekend; what you cannot write is a hand-sculpted landmass where every ridge you crest puts three things worth walking to on the horizon.

You will get a good prototype. The product is what comes after.

The chemistry table is where your review time goes. An agent will cheerfully write forty special cases for fire and ice, it will work, and then you will be unable to add a fifth element without rewriting the file — so demand the rules table in the first prompt and grep the diff for hardcoded pairs. What you cannot prompt is the ground itself. This is a landscape sculpted so that every climb pays out a view with reasons in it, and procedural generation gives you an empty map nobody wants to walk across.

Difficulty
VERY HARD · 4 of 5
First playable
A project
The original
600 team-years
Released
2017 · Nintendo
Genre
Open World Adventure
The one-shot build prompt
Build a traversal-and-chemistry sandbox: ONE hillside valley, three.js plus a physics library. Not the game — the movement and the elemental rules.

Requirements:
- Climb any surface below a slope threshold, sampling the surface normal with a short capsule sweep. Mantle when the top edge is within a body height. The mantle is where every clone falls over: script it as a fixed 0.4s arc ending exactly on the ledge, not a physics push.
- One stamina wheel shared by sprinting, climbing and gliding. It drains on climb per metre gained rather than per second, refills only when grounded and idle, and running out mid-cliff drops you. Do not give climbing its own bar.
- A glider with a fixed 3:1 glide ratio, so height is currency.
- The load-bearing part: elemental state as a rules table, not pairwise code. Every entity carries { material: wood | metal | grass | ice | stone, state: none | burning | wet | frozen | charged }. One table maps (state, contacting state) to a new state and a duration. Fire ignites grass, spreads to adjacent grass on a tick, and raises an updraft volume that lifts the glider. Rain wets everything and cancels burning. Metal in a storm draws lightning. Adding a sixth element must mean adding rows, never adding an if.
- Round wooden objects that roll downhill carrying fire.

Definition of done: I set a grass slope alight, ride the updraft it makes, and land somewhere I did not have the stamina to climb.
What you lose
  • 120 shrines, each a hand-authored puzzle with exactly one idea in it, plus four Divine Beasts on top
  • The terrain — a hand-sculpted landmass where every ridge you crest puts three things worth walking to on the horizon
  • A physics and chemistry sim that stays stable while you stack, freeze and launch objects, on Wii U hardware and a 2015 Tegra tablet chip
  • The reactive piano score and the ambient sound, which do most of the work of making an empty field feel occupied
What to steal

One stamina pool shared by every traversal verb — sprint, climb and glide all spend the same wheel.

It turns terrain into an economy. The moment the three ways of moving compete for one number, the player is doing arithmetic about the landscape instead of holding forward, and you bought that with a single float. Drops cleanly into a platformer, a stealth game, or a racer with a boost meter.

ScopeAn evening— build just this, not the game

Build a single-file HTML page, Canvas 2D, side-on, demonstrating one shared stamina pool.

Requirements:
- A blocky hill silhouette, a runner, and three verbs: sprint (hold Shift), climb (walk into a wall), glide (Space while airborne).
- One float, stamina 0..1, drawn as a ring beside the character. Sprint drains 0.15/s. Climb drains 0.30 per metre of height gained, not per second — climbing slowly must cost the same. Glide drains 0.05/s. Regeneration is 0.4/s, grounded and not sprinting only, after a 0.5s delay from the last spend.
- Running out while climbing drops you. Running out while gliding folds the wing. Both survivable from low height, fatal from high.
- Draw a faint ghost arc showing how far the current stamina could still carry you, updated live as it drains.

Definition of done: I stand at the foot of a cliff, see from the ring alone that I cannot reach the top, and go looking for a shorter route.
Make it different

Not a clone — The Legend of Zelda: Breath of the Wild 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. 24,360 ways to land.

Fallout Zone Teletype

The Legend of Zelda: Breath of the Wild, but text-only, in a terminal, set in a post-apocalyptic wasteland. Rendered in soft pastel indie.

Themea post-apocalyptic wasteland
Angletext-only, in a terminal
Looksoft pastel indie
Build a browser game called "Fallout Zone Teletype".

The pitch in one line: a open world adventure in the spirit of The Legend of Zelda: Breath of the Wild, but text-only, in a terminal, set in a post-apocalyptic wasteland.

WHAT THIS IS
Take the SHAPE of The Legend of Zelda: Breath of the Wild — 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
Text-only, in a terminal. A monospace grid and nothing else. Forces the writing and the systems to carry everything, and the entire art budget goes to zero.
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 post-apocalyptic wasteland. Scarcity in every system. Everything the player uses was built for a different purpose by people who are gone.
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
Soft pastel indie. Desaturated pastels, round characters, gentle bloom, and UI handwriting that stays legible at small sizes.

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.
Prior art — read before you build

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.

Did you build it?
0Share on X

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 600 team-years to the counter on the homepage.

Questions

How hard is The Legend of Zelda: Breath of the Wild to rebuild with an AI agent?

Yes — every game is buildable at some scope. The question is how hard, and The Legend of Zelda: Breath of the Wild is VERY HARD (4 of 5). You will get a good prototype. The product is what comes after. The elemental chemistry is a rules table you can write in a weekend; what you cannot write is a hand-sculpted landmass where every ridge you crest puts three things worth walking to on the horizon. Reckon on a project to something you can actually play — not to something that matches the 600 team-years Nintendo EPD spent.

What makes The Legend of Zelda: Breath of the Wild hard to rebuild?

The elemental chemistry is a rules table you can write in a weekend; what you cannot write is a hand-sculpted landmass where every ridge you crest puts three things worth walking to on the horizon. 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 one stamina pool shared by every traversal verb — sprint, climb and glide all spend the same wheel. — an evening of work.

How long does it take to build a The Legend of Zelda: Breath of the Wild clone?

Wrong question, and it is worth saying why. Nobody rebuilds The Legend of Zelda: Breath of the Wild — the original took Nintendo EPD on the order of 600 team-years, released in 2017 on Nintendo. 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 The Legend of Zelda: Breath of the Wild?

120 shrines, each a hand-authored puzzle with exactly one idea in it, plus four Divine Beasts on top. The terrain — a hand-sculpted landmass where every ridge you crest puts three things worth walking to on the horizon. A physics and chemistry sim that stays stable while you stack, freeze and launch objects, on Wii U hardware and a 2015 Tegra tablet chip. 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.

Get the next game

One email when new games go on the list. No other reason to email you, ever.