🖥️ PC2008Turtle Rock Studios (Valve)VERY HARD

Left 4 Dead rebuild deck

VERY HARD

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

The director is the most stolen idea in this category and it is one prompt away — a stress metric and a four-state machine is an afternoon's work. The KINDA is because Left 4 Dead is a game about three other people panicking, and the solo version with bots is a demonstration rather than an experience. The part nobody talks about is that Valve's survivor bots are the harder AI problem: an agent will hand you followers who walk into your line of fire and stand in doorways, and fixing that is where the forty hours go.

Difficulty: VERY HARD · 4 of 5
First playable: A project
The original: 50 team-years
Released: 2008 · PC
Genre: Co-op Survival Shooter

The one-shot build prompt

Build a co-operative survival shooter for one player and three AI teammates, moving through a linear level from one safe room to the next. three.js, no networking.

Requirements:
- The director is the project, not the shooting. Maintain a per-survivor stress value that rises with damage taken, enemies inside a short radius, and sustained firing, and decays exponentially when none of that is happening. Take the team maximum and run a four-state machine over it: build up, peak, relax, and a quiet period with an enforced minimum duration. Spawning is permitted only in build up and peak, and quiet must be empty. If your director only ever escalates you have built a difficulty curve, not a director, and the horde stops landing.
- Enemies spawn out of view, ahead along the route, from a population budget the director owns. Never spawn inside a visible volume.
- Four special enemy types, each of which removes exactly one survivor from the fight in a different way, and each with a distinct audio cue audible before it is visible.
- Item placement is director-controlled too: health and ammunition are placed at run time against the team's current condition, not authored into the map.
- Teammate bots that follow, revive, hand over health items and call out specials by name.
- One linear level: an obvious route, a horde-triggering event partway, a safe room at each end.

Definition of done: I get a full thirty seconds of nothing, start to relax, and the horde arrives exactly then.

Before you start🧰 The toolkit — models, MCP servers, art and 3D

What you lose

Three friends on voice chat, which is the product and cannot be coded
Survivor bots good enough to carry a campaign, a hard AI problem most co-op games still have not solved
Four campaigns of hand-built geometry, each a corridor that reads as a route without ever showing you a map
The audio mix: knowing which special is nearby before you can see it is doing most of the tension work

What to steal

A director that enforces silence

Everyone remembers the part where the game watches your stress and throws a horde at you. The part that works is the state that refuses to spawn anything for a mandatory minimum — tension is a rhythm, and without a guaranteed empty stretch you have built a difficulty slider with a fancy name.

ScopeA weekend— build just this, not the game

Single self-contained HTML file, Canvas 2D, no build step. Top-down corridor the player walks along, with simple enemies. Build the pacing controller, not the game. Each frame, compute a stress value from damage taken recently, enemies within a radius, and shots fired, with exponential decay. Run four states over it. BUILD_UP spawns at an increasing rate. PEAK holds a large population until stress crosses a threshold or a timer expires. RELAX stops spawning and lets stress fall. QUIET spawns nothing at all for a mandatory minimum of thirty seconds no matter what the player does. Spawn only outside the player's view and ahead of them. Draw the stress value, the current state and its timer as a live graph across the bottom of the screen: the graph is the toy. Definition of done: I watch the line go flat, feel myself relax, and get caught by the first BUILD_UP spawn every time.

Make it different

Not a clone — Left 4 Dead 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.

Gaslight Deck

Left 4 Dead, but a deckbuilder version of its combat, set in Victorian gothic. Rendered in hand-drawn ink on paper.

ThemeVictorian gothic

Anglea deckbuilder version of its combat

Lookhand-drawn ink on paper

Build a browser game called "Gaslight Deck".

The pitch in one line: a co-op survival shooter in the spirit of Left 4 Dead, but a deckbuilder version of its combat, set in Victorian gothic.

WHAT THIS IS
Take the SHAPE of Left 4 Dead — 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 deckbuilder version of its combat. Every action becomes a card with a cost. Cards, relics and enemy intents are pure data, and the whole balance surface becomes a spreadsheet you can tune.
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
Victorian gothic. Fog, gaslight and etiquette. Social rules that constrain movement as hard as walls do.
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
Hand-drawn ink on paper. Rough stroked outlines with per-frame jitter so lines boil, a paper-grain texture over everything, and ink-bleed on impacts.

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 50 team-years to the counter on the homepage.

Then try these

Or roll something nobody has built yet →

Questions

How hard is Left 4 Dead to rebuild with an AI agent?

Yes — every game is buildable at some scope. The question is how hard, and Left 4 Dead is VERY HARD (4 of 5). You will get a good prototype. The product is what comes after. The Director is a stress value and a four-state machine, an afternoon's work; the panic only reads because each special infected has a distinct audio tell and each campaign is a hand-built funnel of choke points, which is sound design and level design rather than code. Reckon on a project to something you can actually play — not to something that matches the 50 team-years Turtle Rock Studios (Valve) spent.

What makes Left 4 Dead hard to rebuild?

The Director is a stress value and a four-state machine, an afternoon's work; the panic only reads because each special infected has a distinct audio tell and each campaign is a hand-built funnel of choke points, which is sound design and level design rather than code. 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 a director that enforces silence — a weekend of work.

How long does it take to build a Left 4 Dead clone?

Wrong question, and it is worth saying why. Nobody rebuilds Left 4 Dead — the original took Turtle Rock Studios (Valve) on the order of 50 team-years, released in 2008 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 Left 4 Dead?

Three friends on voice chat, which is the product and cannot be coded. Survivor bots good enough to carry a campaign, a hard AI problem most co-op games still have not solved. Four campaigns of hand-built geometry, each a corridor that reads as a route without ever showing you a map. 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.