A set of instructions for building, testing, debugging, and visually checking Godot projects. Godot is a game engine, and the set covers code checks, runtime inspection, input, scenes, gameplay tests, screenshots, and related systems.

Use it when working on Godot project structure, GDScript or C# code, controls, scenes, gameplay, UI, animation, audio, navigation, particles, physics, shaders, or visual verification.

It gives coding agents a defined way to check both the project's code and what happens while the game runs.

godot — Skill for Claude Code and Codex by valkor-ai

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.

Any agent

npx skills add valkor-ai/loom --skill godot

Clone the repo

git clone --depth 1 https://github.com/valkor-ai/loom

Made for: Claude Code, Codex.

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/skills/valkor-ai/loom/godot.svg)](https://agentmods.dev/skills/valkor-ai/loom/godot)

Your own site

<a href="https://agentmods.dev/skills/valkor-ai/loom/godot"><img src="https://agentmods.dev/badge/skills/valkor-ai/loom/godot.svg" alt="Measured on agentmods" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 733 The whole file, excluding the scripts and references it only reads on demand.

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

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00062	$0.00733
Opus 5	$0.00031	$0.00367
Sonnet 5	$0.00012	$0.00147
Haiku 4.5	$0.00006	$0.00073

Measured 8d ago against content hash 10f6e69e91e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

godot 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 8d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (godot-api/tools/class_list.py, godot-api/tools/ensure_doc_api.sh, godot-api/tools/godot_api_converter.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/shared/loom/skills/godot/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Godot Skills for Loom

Loom provides the delivery workflow. These references provide Godot-specific working knowledge; they do not replace the Godot editor, the Godot runtime, or the project's own addons.

Choose the smallest skill

Task	Skill
Godot API or GDScript/C# syntax	`godot-api`
Parse or compile check	`headless-build`
gdUnit4 tests	`gdunit-driver`
Live runtime, scene tree, console, or input debugging	`mcp-driver`
Project layout or `project.godot` settings	`project-scaffold`
Input actions	`input-mapper`
End-to-end gameplay or UI tests	`godot-e2e`
Capture a gameplay frame	`screenshot`
Inspect a capture for acceptance issues	`visual-qa`
GDScript linting and formatting	`gdtoolkit`
Animation, audio, navigation, particles, physics, shaders, TileMap, or UI review	`reviewer/*`

Do not load every reference for every task. Start with mcp-driver only when the problem is runtime-specific; use headless-build for syntax and import failures first.

Loom delivery loop

For a non-trivial Godot change, route the work through Loom before editing:

@loom plan Add a third-person dog that walks beside the house in the Godot project
@loom continue

Keep the Godot project root as the active workspace, with project.godot at the root. Let Loom own the delivery state in .loom/; keep screenshots, logs, and other evidence at the task paths returned by Loom or in the project's existing evidence directory.

The normal verification order is:

Check the Godot version and project structure.
Run a headless parse/import check after script or scene edits.
Run unit or end-to-end tests when the project has them.
Use godot-mcp for live behavior and visual inspection.
Capture the result and record the evidence in the Loom task handoff.

Specialist reviewers under reviewer/ run after implementation. Use only the reviewer that matches the changed Godot subsystem; they supplement Loom review with engine-specific gotchas and do not replace the Loom review or repair loop.

Read the full file on GitHub · 78 lines

Files

What ships with it

47 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

8d ago First seen · 78 lines · 62 tokens per session scan A 10f6e69e91e7

Subscribe to this mod's changes

godot is a skill published in the GitHub repository valkor-ai/loom (977 stars, last pushed 21d ago), licensed Apache-2.0. It adds 62 tokens to every session and 733 once invoked, about $0.0003 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.

Game development Testing

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens

tests-run

Execute Unity tests (EditMode or PlayMode) and return per-test results. Supports filtering by test assembly, namespace, class, and method. Refreshes the AssetDatabase first; defers execution across domain reloads if scripts changed. Precondition: every open scene must be saved — dirty scenes abort the run.

IvanMurzak/Unity-MCP · 68 tokens

unity-agent-workflows

Use for AI-assisted Unity work that needs live repo discovery, project-derived routing, runtime-owner proof, runtime-visible output hard stops, runtime numeric proof for repeated visible-output failures, state-step guards, multi-agent scope ownership, modular C#/asmdef safety, UI/scene/visual asset gates, data-first…

hashgraph-online/awesome-codex-plugins · 146 tokens

testing-bgs-modpack

A checklist and decision guide for checking a newly installed batch of Bethesda Game Studios game modifications before accepting it as ready.

hashgraph-online/awesome-codex-plugins · 101 tokens

sprite-gen

Generate clean 2D game sprites and animation atlases with a component-row pipeline: base identity, numeric sprite-request SSoT, per-state layout guides, image-gen row strips, chroma-key alpha cleanup, connected-component frame extraction, cell-based atlas composition, QA reports, and runtime manifest framelayout. Its…

aldegad/sprite-gen · 291 tokens

prototype

Concept prototype — validate the core idea is worth designing before writing GDDs. Run right after /brainstorm and /setup-engine. Routes to HTML, Engine, or Paper path based on game type. Produces a throwaway build and a PROCEED/PIVOT/KILL verdict.

Donchitos/Claude-Code-Game-Studios · 61 tokens