godot-agent-loop CLAUDE.md

godot-agent-loop CLAUDE.md is an instructions file for coding agents from beremaran/godot-agent-loop. It costs 1,380 tokens per session, scanned A, original, MIT.

A project guide for Godot Agent Loop, a TypeScript server that lets AI agents work with Godot 4 games. It documents the project’s structure, commands, architecture, tool pipeline, and tests.

In plain words
What is it for?
Use it to build, test, lint, and verify the TypeScript MCP server and its Godot 4 integrations.
Why use it?
It gives the agent the context and checks needed to change the server without breaking its Godot game workflow.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/beremaran/godot-agent-loop/claude-md
Clone the repo
git clone --depth 1 https://github.com/beremaran/godot-agent-loop

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.

agentmods badge for godot-agent-loop CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/beremaran/godot-agent-loop/claude-md.svg)](https://agentmods.dev/instructions/beremaran/godot-agent-loop/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/beremaran/godot-agent-loop/claude-md"><img src="https://agentmods.dev/badge/instructions/beremaran/godot-agent-loop/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,380 This file is loaded in full into every session.
When invoked 1,380 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01380 $0.01380
Opus 5 $0.00690 $0.00690
Sonnet 5 $0.00276 $0.00276
Haiku 4.5 $0.00138 $0.00138

Measured 5d ago against content hash 01b270cb784a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

godot-agent-loop CLAUDE.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 5d 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.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

Godot Agent Loop (@beremaran/godot-agent-loop): a TypeScript MCP server (stdio transport) that lets agents author, run, observe, and verify Godot 4 games. Entry point src/index.ts, compiled to build/index.js. Godot 4.7 is both the compatibility floor and primary target.

Commands

npm run build          # tsc + metadata/adapter sync + scripts/build.js (copies GDScript into build/)
npm test               # unit tests (vitest)
npx vitest run tests/tool-registry.test.ts            # single unit test file
npx vitest run tests/tool-registry.test.ts -t "name"  # single test by name
npm run test:e2e       # retained full-path MCP E2E (builds first, needs Godot)
npm run build && npx vitest run --config vitest.e2e.config.ts tests/e2e/representative-path.test.ts  # single E2E file
npm run lint           # eslint + markdownlint; npm run lint:md:fix auto-fixes markdown
npm run check          # lint + build + retained unit suite; used by CI and release validation
npm run check:built    # lint + retained unit suite, assuming a fresh build
npm run check:fast     # lint + tsc --noEmit — what the Husky pre-commit hook runs (~seconds)
npm run inspector      # MCP Inspector against build/index.js

Godot binary resolution for E2E tests: GODOT_BIN (executable path) → godot4/godot on PATH → first godot* executable inside GODOT_PATH (a directory). Note: the MCP server itself treats GODOT_PATH as an executable path, not a directory — the E2E harness passes the binary explicitly.

Architecture

Tool pipeline (TypeScript side)

Every MCP tool flows through this chain:

  • src/tool-definitions.ts — name + JSON schema for all tools.
  • src/tool-manifest.ts — one entry per tool: domain, handler method, backend, action list, privilege flag. Typed as Record<ToolName, ...> so completeness is a compile-time fact.
  • src/domain-tool-registries.ts — dispatches to the three handler classes in src/tool-handlers/: lifecycle (processes/editor), project (validation, imports, integrity, .NET, add-ons, exports), game (runtime interaction).
  • src/tool-surface.ts — the advertised surface. Default is a lean 20-tool core set covering the author → validate → run → observe → interact → assert loop; GODOT_MCP_TOOL_SURFACE=full advertises the complete 64-tool catalog. The godot_catalog tool searches/describes the full catalog and godot_call dispatches a hidden tool by name either way. Size budgets (bytes/token/count) are constants here.

Read the full file on GitHub · 60 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.

  1. 5d ago First seen · 60 lines · 1,380 tokens per session scan A 01b270cb784a

Subscribe to this mod's changes

godot-agent-loop CLAUDE.md is an instructions file published in the GitHub repository beremaran/godot-agent-loop (5 stars, last pushed yesterday), licensed MIT. It adds 1,380 tokens to every session, about $0.0069 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 2026-08-31.

Related

Other instructions, from other repositories

claudemon CLAUDE.md

Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.

zamarrowski/claudemon · 7,681 tokens

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.

krogh-jacobsen/unity-code-style-guide · 4,528 tokens

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.

oliverearl/nes-php-glfw · 2,719 tokens

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.

sylverb/game-and-watch-retro-go-sd · 2,946 tokens

base-building-trap-defense-design-agent-skill CLAUDE.md

Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.

dungnotnull/base-building-trap-defense-design-agent-skill · 1,910 tokens

trident-mcp AGENTS.md

Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.

mordor-forge/trident-mcp · 1,465 tokens