Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/godot-fun/godot-framework/agents-mdgit clone --depth 1 https://github.com/godot-fun/godot-frameworkWrote 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/godot-fun/godot-framework/agents-md)<a href="https://agentmods.dev/instructions/godot-fun/godot-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/godot-fun/godot-framework/agents-md.svg" alt="Measured on agentmods" 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 | $0.02480 | $0.02480 |
| Opus 5 | $0.01240 | $0.01240 |
| Sonnet 5 | $0.00496 | $0.00496 |
| Haiku 4.5 | $0.00248 | $0.00248 |
Grade A, and why
godot-framework 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Directory Structure
Separate framework, resources (by type), and game code. Do not mix them.
project-root/
├── zfoo/ # Framework only — sync/upgrade; no game business logic
├── assets/ # Extra assets (video, fonts, 3D, …)
├── audio/ # Audio assets
├── image/ # Image assets
├── config/ # CSV/JSON tables (optional)
├── shader/ # Custom shaders (optional)
├── scene/ # Runnable and instanced .tscn scenes
├── script/ # Game scripts (.gd), systems, data models
├── test/ # Unit tests (UnitTest.gd scenes)
└── project.godot
Resource directories (no .gd logic)
image/ — textures and sprites:
image/
├── ui/ # Buttons, panels, icons
├── characters/ # Character sprites and portraits
├── backgrounds/ # Scene backgrounds
├── tiles/ # Tilemap tiles
└── effects/ # VFX and particle textures
audio/ — use with zfoo Audio API:
audio/
├── bgm/ # Looping background music
├── sfx/ # Short one-shot sound effects
└── voice/ # Voice-over and narration
assets/ — video, fonts, 3D, and other extra binary assets:
assets/
├── video/ # Cutscenes, trailers, background video
├── font/ # Font files (.ttf, .otf, …)
├── 3d/ # Models, meshes, materials, animations
└── … # Other misc assets as needed
Other resource roots (add when needed): config/, shader/.
Game code — scene/ and script/
scene/
├── boot/
├── main/
├── gameplay/
└── ui/
script/
├── autoload/ # Game Autoloads (after GodotFramework)
├── core/ # Constants, ResPath, shared base classes
├── data/ # Resource classes and .tres instances
├── systems/ # Pure logic (inventory, save, quest, …)
└── network/ # Packets and codec (zfoo Router)
GDScript (this project)
- Types: Use explicit types on function signatures and return values (
-> void, etc.). Use theclass_nametype when a class has one. Prefer:=for locals to lock in the inferred type at declaration; usevar x = ...only when you need Variant or mixed types. - Docs: Use
##comments for scene entry points or complex logic. Match the tone of nearby files. - Nodes: Prefer
@onready var name: Type = $Path. - Trailing pass: If a function has no
returnstatement, end the body withpass.
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.
- 4d ago First seen · 322 lines · 2,480 tokens per session scan A 4f4dd526ff8f
godot-framework AGENTS.md is an instructions file published in the GitHub repository godot-fun/godot-framework (116 stars, last pushed 4d ago), licensed MIT. It adds 2,480 tokens to every session, about $0.0124 per session on Opus 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
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
Cities2-MCP AGENTS.md
Instructions for mayor-modder/Cities2-MCP, covering agent rules, workspace safety, commit and pr safety, public-facing writing and merge and release gates.