# Game Dev bundle: build a small game with coding agents from one runbook a script can check

> Game Jam Kit, Unreal from Codex, Game Assets as Code and Engine Agent Kits in full, tied into one build loop by a new Game Build Runbook: a pinned engine, milestones that start with a test, playtests by an agent and a person, an asset ledger with licenses, seeds and sha256, builds with size budgets, and action gates. game.py answers every action with go, ask the owner or never, and a fifteen-check script names every gap. Uploads, store page changes, engine upgrades and asset promotions wait for the owner's yes typed at their terminal and tied to that request's sha256.

- URL: https://paperchasewebb.ai/bots/marketplace/items/game-dev-bundle-build-a-small-game-with-coding-agents-from-one-runbook/
- Type: Bundle
- Category: Games
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Grok Bot, Hermes (named in the listing); A skill file for Claude Code, Codex and Hermes, an AGENTS.md snippet and a Grok Bot rules block; the runbook scripts were tested on Linux with Python 3.13, the agent files were not loaded inside each harness
- Price: $69 USD
- Difficulty: Intermediate
- Setup time: 1 hr
- Time to result: A checked, ratified runbook in one afternoon once the packs you need are installed
- Format: Markdown (.md) file, game-dev-bundle-build-a-small-game-with-coding-agents-from-one-runbook.md
- Version: 1.0, updated 2026-10-29
- License: Use on your own machines and on games you make for yourself, clients and teams, including commercial games. Do not resell or republish the bundle itself.

## What you end up with

A small game your agents build one tested milestone at a time on a pinned engine, where every asset has a license on file, every build has a hash, a size and a passing test, and nothing goes up to a jam or store page without your typed yes.

## What you get

- Four packs in full: Game Jam Kit, Unreal from Codex, Game Assets as Code and Engine Agent Kits ($111 bought separately)
- The Game Build Runbook (only in this bundle): one folder of plain files for the pinned engine, milestones, playtests, assets, builds and actions, with templates
- A build loop: what happens when, which runbook file it lands in and which pack it comes from
- game.py: a gate for every action (0 go, 11 ask the owner, 12 never), requests, owner approval at a terminal tied to the request sha256, verify with expiry, one use per yes
- game_check.py: fifteen read-only checks, with a seeded test runbook (15 findings, then 0)
- A skill file for Claude Code, Codex and Hermes, an AGENTS.md snippet and a Grok Bot rules block
- Ten prompts, a failure table and a worked example
- A look at game dev prompt packs, agent skill packs and jam templates, with sources

## Who it is for

Developers and small teams making a small game with coding agents who want one place that says what agents do alone and what waits for a person.

## Tools needed

- Grok Bot, Claude Code, Codex or Hermes: the agents that write the code, make the assets and export the builds; each reads the skill file, AGENTS.md snippet or rules block and checks game.py gate before acting
- Python 3: runs game.py (init, hash, gate, request, owner approval, verify, done) and the fifteen-check checker; standard library only, no network
- Your engine: Godot, Unity, Unreal or a web engine at one pinned version; the included packs cover Godot 4, Unity 6 and Unreal 5
- The game's owner: pins the engine, agrees the milestones, plays each milestone, approves assets and types each yes at their own terminal
- You need: Any of Grok Bot, Claude Code, Codex or Hermes
- You need: Python 3.9 or newer
- You need: A game project in git, in one engine at one version, and a terminal you control

Cost to run: The bundle is the only purchase. The checker and game.py use no model tokens. Engines and your agents' own plans are separate.

## What is in the bundle (4 packs)

| Pack | Format | Separate price |
|---|---|---|
| [Game Jam Kit: a 48-hour Godot 4 plan and a two-day Unity PRD that a coding agent can follow](https://paperchasewebb.ai/bots/marketplace/items/game-jam-kit-godot-48-hour-plan-and-unity-two-day-prd.md) | Bot template | $29 |
| [Unreal from Codex: Unreal MCP setup, a session contract and a tested asset pipeline for coding agents](https://paperchasewebb.ai/bots/marketplace/items/unreal-from-codex-mcp-session-contract-and-asset-pipeline.md) | Bot template | $24 |
| [Game Assets as Code: one spec file, seeded generators and a fifteen-check checker for agent-made game art and sound](https://paperchasewebb.ai/bots/marketplace/items/game-assets-as-code-spec-seeded-generators-and-checker.md) | Bot template | $29 |
| [Engine Agent Kits: Godot 4, Unity 6 and Unreal 5 rules files, editor bridges and build loops for coding agents](https://paperchasewebb.ai/bots/marketplace/items/engine-agent-kits-godot-unity-unreal-rules-and-build-loops.md) | Prompt pack | $29 |
| Bought separately | | $111 |
| The bundle | | $69 |

## How it works

1. **Run the tests.** Copy the game-dev-bundle folder and run sh test_all.sh. Expected: 15 findings on the seeded runbook and 0 on the fixed one, 15 of 15 single faults caught alone, checker tests 30 passed, game tests 37 passed, exit 2 on a missing folder.
2. **Install the packs you need.** Set up Engine Agent Kits for your engine, the Game Jam Kit plan, Game Assets as Code, and Unreal from Codex if you use Unreal, each passing its own checks. Expected: Rules for one pinned engine, a milestone plan, assets from specs and seeds, and Unreal sessions inside a contract.
3. **Start the runbook.** Run game.py init build/<game>, fill game.json, copy the trap table into ENGINE.md and let your agent draft milestones.csv. Expected: One engine version in game.json, ENGINE.md and the project, and three to seven milestones, each with a first test and a leave-out list.
4. **Gate the risky actions.** Add your safe daily actions as agent-ok, keep the ten risky ones owner-yes, and write the AI disclosure. Expected: game_check.py shows only G15.
5. **Ratify and build.** Run game.py approve --runbook at your own terminal. From then on agents check game.py gate before every action, and each milestone closes when an agent replay and a person both play it. Expected: Safe work goes ahead, uploads and store page changes arrive as requests you approve by hash, and any edit to the runbook stops every gate until you ratify again.

## Sample prompt: Pin the engine (Grok Bot, Claude Code, Codex, Hermes)

```
Read the project file and tell me the engine version it says. Compare it with ENGINE.md and game.json.
If they differ, stop and show me all three.
```

Prompt 2 of 10.

## Sample prompt: Done means played (Grok Bot, Claude Code, Codex, Hermes)

```
Play milestone <M> with the input replay and log the result in playtests.csv as played_by agent.
Tell me what to try when I play it. Do not write my row.
```

Prompt 7 of 10.

## Free preview of game-dev-bundle-build-a-small-game-with-coding-agents-from-one-runbook.md

````markdown
# Game Dev bundle: build a small game with coding agents from one runbook a script can check

Version 1.0, 2026-10-29. By PaperChaseWebb. A bundle of four paid packs (Game Jam Kit, Unreal from Codex, Game Assets as Code, Engine Agent Kits) plus a new Game Build Runbook that ties them into one build loop for one game. The runbook comes with a gate and approval script, a read-only checker with fifteen checks, templates, a seeded test runbook, ten prompts and the tests, all Python 3 standard library. Works with Claude Code, Codex and Hermes through a skill file and an AGENTS.md snippet, and with Grok Bot through a rules block. Tested as described in section 10: the runbook scripts ran on Linux with Python 3.13, including owner approvals typed at a pseudo-terminal. The skill file, snippet and rules block were not loaded inside the harnesses for this release, and the runbook itself does not start an engine. Each limit is marked where it matters.

Game dev packs for agents usually sell one of two things: a pile of prompts, or a pile of skills with a router on top. Both help with the first hour. What goes wrong comes later. The agent writes code for an engine version you are not on. A milestone is called done because the code compiled, and nobody played it. A sound file from a forum thread ends up in the build with no license on file. The web build is 60 MB and nobody noticed until the upload. An agent with MCP write access to the editor deletes a scene. A build goes up to the jam p
````

## Test record

- Date: Oct 29, 2026
- What was run: game_check.py on a seeded runbook and a fixed copy, each planted fault alone, a missing input, and the unit tests. Linux, Python 3.13.
- Result: 15 findings on the seeded runbook, 0 on the fixed one; 15 of 15 planted faults caught alone; exit 2 on missing input; nothing written. 30 checker and 37 game.py tests passed, 0 failed.
- Not run: The agent files inside Claude Code, Codex, Hermes or Grok Bot. A real Godot, Unity or Unreal project. Windows and macOS.

Copied from this item's dated test notes. What was not run stays in.

## Worth knowing

- The checker checks that each build decision was made and written down. It cannot tell whether a test really covers a feature, a playtest was careful or a license is genuine; you and the included packs' own checks do that.
- The skill file, AGENTS.md snippet and Grok Bot rules block were not loaded inside Claude Code, Codex, Hermes or Grok Bot for this release. The runbook reads files and starts no engine, so it was not run next to a real Godot, Unity or Unreal project. The test runbook is a made-up game. Linux only; Windows and macOS were not tested.
- The gate makes the rules plain and testable; it does not sandbox an agent. Pair it with each harness's own permission settings and read-only MCP tools.
- The approval script refuses piped input and the environment variables Claude Code, Codex, Hermes and Grok Bot set. That stops an agent approving by mistake; it is not a lock against someone with the same account.
- On 2026-10-29, on Linux with Python 3.13: game_check.py gave 15 findings on the seeded runbook (each check once) and 0 on the fixed one, caught 15 of 15 single faults with only its own check, wrote nothing, and exited 2 on a missing folder, any missing file or broken game.json; checker tests 30 passed, 0 failed; game.py tests at a pseudo-terminal 37 passed, 0 failed.
- Game Dev with AI Agents is not included; it is a separate planning playbook.
- The bundle contains the versions listed on this page on the day you buy. Each included pack keeps its own notes and limits.

## Questions

**Why not buy the four packs on their own?** You can, for $111. The bundle is $69 and adds the Game Build Runbook, which is only here: the gate every agent checks before acting, approvals tied to one request, and one checker across the engine, milestones, assets and builds.

**Which engines does it cover?** The runbook works with any engine you can pin to a version. The included packs give rules, trap tables and build loops for Godot 4, Unity 6 and Unreal 5, and the asset generators were tested with Blender and Godot headless.

**Can an agent upload a build on its own?** No. upload-build and store-page-publish are owner-yes. game.py approve refuses piped input and the agent environments it recognizes, and the owner types their name and part of the request hash at their own terminal.

**Does it replace a jam template or a game engine skill pack?** No. Use a good template or your engine's own skills. The runbook records what the agents did with them and what waits for you.

**What if I want it set up with me?** Book a call on the paperchasewebb.ai homepage about the $5,000 Install sprint, or Manage at $5,000 a month to keep the runbook and engine rules current.

## How to buy

$69 one time at https://paperchasewebb.ai/bots/marketplace/items/game-dev-bundle-build-a-small-game-with-coding-agents-from-one-runbook/. Stripe checkout, then an instant download page; the download link is also in your emailed receipt.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com