Game Dev bundle: build a small game with coding agents from one runbook a script can check
by PaperChaseWebb
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.
- Price
- $69
- Difficulty
- Intermediate
- Setup
- 1 hr
- Format
- .md file
game-dev-bundle-build-a-small-game-with-coding-agents-from-one-runbook.md · 329 KB · instant download after checkout · $111 if bought separately
Want this built for you instead? We can build it for you.
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.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: 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.
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 | Bot template | $29 |
| Unreal from Codex: Unreal MCP setup, a session contract and a tested asset pipeline for coding agents | Bot template | $24 |
| Game Assets as Code: one spec file, seeded generators and a fifteen-check checker for agent-made game art and sound | Bot template | $29 |
| Engine Agent Kits: Godot 4, Unity 6 and Unreal 5 rules files, editor bridges and build loops for coding agents | Prompt pack | $29 |
| Bought separately | $111 | |
| The bundle | $69 (you save $42) |
Tools needed
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.
Time to result: A checked, ratified runbook in one afternoon once the packs you need are installed
How it works
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.
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.
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.
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.
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 from the pack
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.
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 the file
# 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.
Details
Version 1.0 · Updated Oct 29, 2026 · Markdown version of this page
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. Download terms
Related
Game Dev: five rules for building a small game with coding agents, and a five-check script (free sample)
From the Game Dev bundle: five rules for a small game built with coding agents (pin the engine version in the project and the agent's rules, a first test before each milestone, done means played by an agent and a person, a license for every asset, uploads wait for the owner's yes), and a read-only script that checks one small file for them.
Game Jam Kit: a 48-hour Godot 4 plan and a two-day Unity PRD that a coding agent can follow
A tested jam method for working with a coding agent: seven milestones per engine, each with a first version, a first test and a written list of what to leave out, a JAM.md the agent cannot change without your new yes, three owner approvals (scope lock, art and audio licenses, upload), a scope-cut checklist and a fifteen-check read-only jam_check.py. Includes a playable Godot 4 starter that tests itself headless, and a tested proxy for games that call an LLM while people play.
Unreal from Codex: Unreal MCP setup, a session contract and a tested asset pipeline for coding agents
Connect Codex, Claude Code, Grok Bot or Hermes to the Unreal MCP server in Unreal Engine 5.8 and keep every session in bounds: a session file with a checkpoint commit and a leave-out list, five risk tiers, owner approvals tied to file hashes, an action log with a verify result for every call, and recovery steps for editor restarts, stale tool lists, compiles and timeouts. Adds a generator to Blender to Unreal asset path with a headless Blender prep script, an import script that refuses changed files, a connection probe and a fifteen-check read-only checker.
Game Assets as Code: one spec file, seeded generators and a fifteen-check checker for agent-made game art and sound
Let Grok Bot, Claude Code, Codex or Hermes make your placeholder and jam-ready game assets as code instead of prompts: pixel sprites from letter grids, seeded symmetric sprite variants, seamless tiles, SVG icons, retro sound effects and low-poly Blender props built headless, all from one spec file with a fixed palette and seeds. Every build writes a manifest with file and spec hashes and a review page; your approvals are tied to those hashes, a promote step copies only approved, unchanged files into the game, and a separate release yes covers anything that leaves your machine.
Engine Agent Kits: Godot 4, Unity 6 and Unreal 5 rules files, editor bridges and build loops for coding agents
One kit per engine for coding agents: a rules file, a trap table of version mistakes, terminal commands to check, test and build without clicking, ways to give the agent eyes, asset pipelines with a license ledger and a one-milestone work loop.
Game Dev with AI Agents: method, prompts, skills and check loops
A Markdown playbook for building games with Claude Code, Codex or Claude: a seven-stage method, a staged brief, 16 prompts, five agent skills, self-check loops, engine notes and 30 game concepts.