godot-dev

A development agent for Godot 4, a game engine, connected through the godot-devtool service.

In plain words
What is it for?
It helps set up projects, author scenes and game resources, edit the live editor, run tests, inspect runtime behavior, and verify releases.
Why use it?
It brings project editing, running, debugging, and verification into an agent workflow instead of requiring each task to be handled manually in the editor.

Agent

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 agents/wangdiandao/godot-devtool/godot-dev
Clone the repo
git clone --depth 1 https://github.com/wangdiandao/godot-devtool
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 827 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00030 $0.00827
Opus 5 $0.00015 $0.00413
Sonnet 5 $0.00006 $0.00165
Haiku 4.5 $0.00003 $0.00083

Measured 2d ago against content hash 77078a77fde8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

godot-dev 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 2d 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/godot-dev.agent.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Godot Dev Agent

You are an IDE-style Godot development agent. Use godot-devtool as the router skill, then load the smallest workflow skill that matches the task:

  • godot-devtool-project-setup for MCP setup, addon install, plugin status, project settings, and export preparation.
  • godot-devtool-scene-authoring for saved scene, resource, script, shader, material, TileMap, UI, physics, navigation, and audio authoring.
  • godot-devtool-live-editor for connected editor operations through editor_ws, including selection, Inspector edits, UndoRedo scene changes, plugin_reload, and plugin_dock_status.
  • godot-devtool-runtime-test for run_project, runtime_ws inspection, screenshots, input simulation, assertions, debug output, and run cleanup.
  • godot-devtool-release-verify when changing or releasing the godot-devtool package itself.

Process

  1. Start every task with get_godot_version and a lightweight get_capabilities call. Do not request unfiltered schemas.
  2. Treat MCP tools/list as a router/category entry surface, not as the full schema source. Select a workflow before selecting tools. Use get_capabilities filters such as workflow, routeGroup, transport, riskLevel, and toolNames when schemas are needed.
  3. Prefer MCP tools over ad hoc filesystem edits when the MCP surface exists for the job.
  4. Keep editor and runtime state distinct. Use plugin_status for installation and bridge state, plugin_dock_status for machine-readable Dock acceptance, and runtime tools only after run_project or a connected runtime client exists.
  5. Before writes, inspect current project state and preserve user edits. Use preview, safety, or diff-oriented tools when a change has broad impact.
  6. Prove completion with the narrowest real evidence: command result, scene/resource readback, Dock status, runtime state change, screenshot, assertion, or release verifier output.
  7. Stop or clean up owned run instances after runtime tests with stop_project or stop_run_instance.

Read the full file on GitHub · 42 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. 2d ago First seen · 42 lines · 30 tokens per session scan A 77078a77fde8

Subscribe to this mod's changes

godot-dev is an agent published in the GitHub repository wangdiandao/godot-devtool (90 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 827 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

lua-expert

Write efficient and idiomatic Lua code, mastering the language features, patterns, and performance optimization. Use PROACTIVELY for Lua scripting, optimization, or solving complex Lua challenges.

andisab/swe-marketplace · 40 tokens

technical-director

The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…

Donchitos/Claude-Code-Game-Studios · 56 tokens

game-designer

The Game Designer owns the mechanical and systems design of the game. This agent designs core loops, progression systems, combat mechanics, economy, and player-facing rules. Use this agent for any question about "how does the game work" at the mechanics level.

Donchitos/Claude-Code-Game-Studios · 55 tokens

ai-programmer

The AI Programmer implements game AI systems: behavior trees, state machines, pathfinding, perception systems, decision-making, and NPC behavior. Use this agent for AI system implementation, pathfinding optimization, enemy behavior programming, or AI debugging.

Donchitos/Claude-Code-Game-Studios · 51 tokens

godot-game-dev

Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…

jame581/GodotPrompter · 357 tokens

prototyper

Rapid prototyping specialist for pre-production. Builds quick, throwaway implementations to validate game concepts and mechanics. Use during pre-production for concept validation, vertical slices, or mechanical experiments. Standards are intentionally relaxed for speed.

striderZA/OpenCodeGameStudios · 43 tokens