What is godot-agent-loop AGENTS.md?

A set of project instructions for a Godot game-development repository. Godot is a tool for making games, and these instructions explain its code layout, commands, style, and tests.

Use it when working on the repository's TypeScript server, Godot add-on, agent skills, examples, documentation, or automated tests.

It gives coding agents a shared understanding of where files belong and how to build and test the project. This helps avoid incorrect edits and skipped checks.

How beremaran/godot-agent-loop configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to beremaran/godot-agent-loop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/beremaran/godot-agent-loop/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/beremaran/godot-agent-loop

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/beremaran/godot-agent-loop/agents-md/github.svg)](https://agentmods.dev/instructions/beremaran/godot-agent-loop/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/beremaran/godot-agent-loop/agents-md"><img src="https://agentmods.dev/badge/instructions/beremaran/godot-agent-loop/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/beremaran/godot-agent-loop/agents-md"><img src="https://agentmods.dev/badge/instructions/beremaran/godot-agent-loop/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 760 This file is loaded in full into every session.

When invoked 760 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00760	$0.00760
Opus 5.5	$0.00304	$0.00304
Sonnet 5.5	$0.00152	$0.00152
Haiku 4.5	$0.00076	$0.00076

Measured 2mo ago against content hash 8cf9f7efc5db, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

godot-agent-loop 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 2mo 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.

AGENTS.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

Core MCP server code lives in src/; tool handlers are grouped under src/tool-handlers/, while the Godot runtime bridge is in src/scripts/. The retained unit and contract smoke tests are tests/*.test.ts; real-engine smoke tests live in tests/e2e/. The distributable editor add-on is in addons/godot_agent_loop/, reusable agent skills in agent-plugin/, and the playable reference project in examples/. Documentation lives in docs/. Treat build/, coverage/, and dist/ as generated output.

Build, Test, and Development Commands

npm install installs Node 18+ dependencies and Husky hooks.
npm run build compiles TypeScript and synchronizes product and adapter metadata.
npm run watch recompiles TypeScript while developing.
npm test runs the Vitest unit and contract suite.
npm run check runs lint, one build, and the retained unit suite exactly once. Release validation reuses its own build via npm run check:built.
npm run check:fast runs ESLint, Markdown linting, and a no-emit TypeScript check; this is the Husky pre-commit gate.
npm run test:e2e builds and runs the retained MCP-to-Godot smoke tests serially. It requires GODOT_BIN, GODOT_PATH, or godot4/godot on PATH.
npm run inspector opens the MCP Inspector against the built server.

Coding Style & Naming Conventions

Use strict TypeScript, two-space indentation, single quotes, semicolons, and descriptive camelCase identifiers; use PascalCase for types and classes. Keep imports ESM-compatible, including .js suffixes for local TypeScript imports. GDScript uses tabs, static type annotations, and snake_case names. Prefer Node path utilities over hard-coded separators. Run npm run lint; documentation must also pass npm run lint:md.

Testing Guidelines

Name tests *.test.ts and place E2E coverage in tests/e2e/. Keep additions focused on representative validation and failure paths. The Husky pre-commit gate runs npm run check:fast (lint plus no-emit typecheck); run the retained E2E suite when engine behavior changes. Godot 4.7 is both the compatibility floor and primary target.

Read the full file on GitHub · 69 lines

Changes

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.

2mo ago Changed · +14 lines · +118 tokens per session 8cf9f7efc5db
2mo ago First seen · 55 lines · 642 tokens per session scan A 9b383261d175

Subscribe to this mod's changes

godot-agent-loop AGENTS.md is an instructions file published in the GitHub repository beremaran/godot-agent-loop (10 stars, last pushed 22d ago), licensed MIT. It adds 760 tokens to every session, about $0.0030 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 2026-08-31.

Game development

godot-agent-loop AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
godot-agent-loop AGENTS.mdberemaran/godot-agent-loop	Instructions file	10	22d ago	MIT	A	760	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	1,907	GitHub Copilot

godot-agent-loop: Instructions file for Codex