Godogen is a generator that lets coding agents create complete games for Godot, Bevy, or Babylon.js from a short description. It is for people who want an agent to build, generate assets for, run, and demonstrate a game project. The catalogue add-ons are instructions and skills used by Claude Code and Codex during that game-building workflow.
Borrowing it
Nothing to install: this file belongs to htdt/godogen. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/htdt/godogen/master/AGENTS.mdgit clone --depth 1 https://github.com/htdt/godogenWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/htdt/godogen/agents-md)<a href="https://agentmods.dev/instructions/htdt/godogen/agents-md"><img src="https://agentmods.dev/badge/instructions/htdt/godogen/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/htdt/godogen/agents-md"><img src="https://agentmods.dev/badge/instructions/htdt/godogen/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00432 | $0.00432 |
| Opus 5.5 | $0.00173 | $0.00173 |
| Sonnet 5.5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
godogen AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Godogen Source Repo
This repository is not a published game repo. It is the source that publish.sh renders into a runtime game repo for a chosen engine and host agent.
Source Layout
prompts/runtime.md— the engine-agnostic runtime manifest textasset-gen/— the asset-generation skill, the one skill every published repo carries: local generation through godogen_assets by default (SKILL.md), paid APIs inapi.mdengines/godot.md(C#),engines/godot-gdscript.md,engines/bevy.md,engines/babylon.md,engines/threejs.md— per-engine guides (stack, project sketch, capture recipe, silent-failure traps)publish.sh— renders a runtime repo with--engine {godot,godot-gdscript,bevy,babylon,threejs},--agent {claude,codex}; the asset-gen skill gets the local godogen_assets path from.godogen_assets(git-ignored)scripts/— render helpers:render_dir.py(token substitution),generate_codex_metadata.py(Codexopenai.yaml)
Editing Rules
- Do not create or maintain
.claude/skills/or.agents/skills/in this source repo. - Local generation is documented and coded in godogen_assets.
asset-genlinks to its docs with a short TL;DR and adds only what the game side needs; never copy its instructions or tools here. - Don't give obvious guidance. The agent is a highly capable LLM, and the deliverable (a recorded video, or a live URL the user watches) surfaces its own mistakes — so keep the guides to what the model can't infer or discover fast.
- When you change or remove a feature, describe the new state on its own terms. Name the new thing as if it were always the design.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago Changed · +1 lines · +128 tokens per session 3bae1fde2b4a
- 1mo ago First seen · 18 lines · 304 tokens per session scan A 68a99d75b8ac
godogen AGENTS.md is an instructions file published in the GitHub repository htdt/godogen (7,221 stars, last pushed 11d ago), licensed MIT. It adds 432 tokens to every session, about $0.0017 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.