A toolkit for inspecting and changing Godot game projects, including scenes, settings, tiles, user interfaces, animation, audio, and some 3D features. Godot is a game engine used to build 2D and 3D games.

Use it to inspect a Godot project, edit its scenes and resources, create tilemaps and interfaces, set up animation and audio routing, or adjust selected 3D game elements.

It gives a coding agent defined workflows for working with Godot project files and checking which Godot automation tools are available. This reduces the need to make manual edits without understanding the project structure.

godot — Skill for Codex by haxqer/godot-skill

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 haxqer/godot-skill --skill godot

Clone the repo

git clone --depth 1 https://github.com/haxqer/godot-skill

Made for: 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/haxqer/godot-skill/godot/github.svg)](https://agentmods.dev/skills/haxqer/godot-skill/godot)

Your own site

<a href="https://agentmods.dev/skills/haxqer/godot-skill/godot"><img src="https://agentmods.dev/badge/skills/haxqer/godot-skill/godot/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/skills/haxqer/godot-skill/godot"><img src="https://agentmods.dev/badge/skills/haxqer/godot-skill/godot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 245 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 19,824 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 warn 7 Sept 2026

SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Anti-Refusal · line 80
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
medium Memory Poisoning · line 97
Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.

Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.

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	$0.00245	$0.19824
Opus 5.5	$0.00098	$0.07930
Sonnet 5.5	$0.00049	$0.03965
Haiku 4.5	$0.00024	$0.01982

Measured 1mo ago against content hash 1a15711ab1d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo ago.

The scan reads SKILL.md. This mod also ships 14 executable files (scripts/assets/chroma_key_cutout.py, scripts/assets/make_music.py, scripts/assets/make_sfx.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.

skill/godot/SKILL.md · 502 lines

How it starts

The opening of the file, as written. The whole thing — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Godot

Use this skill to inspect and modify Godot projects with the bundled workflows, scripts, and any available host-native Godot automation tooling, including gameplay presentation work such as art generation, frame animation integration, and project-native integration of provided or separately generated music and story content.

Start

Route By Task

Task	Read / run	Verify
New project from nothing	`scripts/project/scaffold_project.py DEST --preset pixel2d\|hd2d\|3d\|ui` (hand-run version: `references/playbooks.md` §1)	its `validate.counts` → `errors` and `warnings` both 0
Any engine class, method, signal or constant you are about to type	`scripts/docs/api_lookup.py CharacterBody2D.move_and_slide` (`references/api_lookup.md`)	exit 0 prints the exact 4.7 signature; a wrong name exits 1 with the nearest real ones
Player controller (2D/3D)	`templates/gdscript/player_*.gd`, playbooks §2, §3, §12, §21	`run_scenario.py` → `"ok": true`
Enemy, damage, health, projectiles, waves	`templates/gdscript/{enemy_patrol_2d,enemy_chase_nav_2d,health,hitbox,hurtbox,projectile,shooter,wave_spawner}.gd`, playbooks §4, §19	`run_scenario.py` → `"ok": true`
State machine	`templates/gdscript/{state,state_machine}.gd`, playbook §4	`run_project.py` → `counts.errors == 0`
Tile level	`build_tileset` + `paint_tilemap` `ascii_map`, playbook §5	`inspect_tilemap` `"format":"text"` rows match
Menu / theme	`references/game_ui.md`, playbook §6	`run_scenario.py` `ui_report` → `findings=0`
HUD, pause, dialog, branching dialogue, settings	`templates/gdscript/{hud,pause_menu,dialog_box,dialogue_runner,choice_list,settings,settings_menu,input_remap}.gd`, playbooks §7–§9, §16, §17	`run_scenario.py` `ui_report` → `findings=0`
Items, inventory, loot, save / load	`templates/gdscript/{item_data,inventory,loot_table,inventory_ui,save_manager}.gd`, playbooks §10, §15	`run_tests.py` → `"ok": true`
A whole small game (collectathon, wave shooter, sokoban, 3D third-person)	`references/playbooks.md` §18–§21, finishing checklist §22	the scripted scenario wins the level; §22's five commands exit 0
Art with no image generator; cleaning generated art	`references/pixel_art.md`, `draw_image`, `process_image`, playbook §14	payload `frame_reports[*].rows` reads back what you drew; `inspect_image` `expect`
Sound effects and music	`references/audio.md`, `scripts/assets/make_sfx.py`, `scripts/assets/make_music.py`, playbook §13	`inspect_audio` `expect` → exit 0
Shader effect (flash, outline, dissolve, CRT, toon, water…)	`templates/shaders/*.gdshader`, `references/shaders.md`	`check_project` → `failed_count == 0`; screenshot `expect`
Scene fades, music, SFX wiring	`templates/gdscript/{scene_transition,audio_manager}.gd`, playbook §11	`validate_project.py` → `counts.warnings == 0`
Writing or editing any `.gd`	`references/gdscript_conventions.md`, then `lint_project.py`	`lint_project.py` → `counts.errors == 0`
Project written for Godot 3	`references/godot3_to_4.md`	`lint_project.py --only godot3_api,godot3_shader` → `counts.errors == 0`
Custom data (`class_name X extends Resource`)	`resource_batch` with `script`, typed JSON `__script`	`inspect_resource` → `script_class`
Hand-writing `.tscn`/`.tres` text	`references/tscn_format.md`	`inspect_scene` nesting matches intent
Moving, renaming or reorganising files	never `mv` — `scripts/project/move_resource.py PROJECT SRC DST` (`--map` for many, `--dry-run` to preview)	its `verify.new_missing == []`, then `validate_project.py` → `"ok": true`
Forgot an op's parameters, or what tools exist	dispatcher `help '{}'` / `help '{"op":"add_node"}'`	the printed `command` runs as-is
No op fits, or a quick logic check	`run_gdscript '{"code":"return …"}'` (`references/api_lookup.md`)	`"ok": true`; a parse or runtime error exits 1 with `code:<line>`
Player falls through the floor, sprite or particles silently do nothing, collisions never fire	`references/node_config.md`, `validate_project.py`	`check_project` → `config_warning_count == 0`, `physics_layers.findings == []`
Runtime errors or a project that will not boot	`references/debugging.md`	`run_project.py` → `"ok": true`
Errors in scenes and input paths a boot never reaches; leaks, hangs	`scripts/debug/smoke_scenes.py PROJECT --seconds 2 --jobs 4 --fuzz`	exit 0, every `scenes[]` entry `ok`
Unit-testing game logic (no addon, no download)	`references/testing.md`, `scripts/test/run_tests.py PROJECT --init-mini`	`"ok": true`, `counts.tests > 0`
Verifying anything without vision or hearing	`references/automation_api.md` "Verification Without Vision"	`dump_tree` / `ui_report` / `spatial_report` / `inspect_image` / `inspect_tilemap` / `inspect_audio`
Is it on screen, in the floor, lit, in front of the camera (2D/3D)	`references/spatial_verification.md`	`run_scenario.py` `spatial_report` `fail_on` → `findings=0`
Packaging a build, from no preset at all	`references/export_targets.md`, `add_export_preset`, `scripts/export/export_project.py`	artifact exists; `scripts/export/serve_web.py DIR --check` → `"ok": true`

Read the full file on GitHub · 502 lines

Files

What ships with it

60 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.

1mo ago Changed · +119 lines · -41 tokens per session 1a15711ab1d8
1mo ago Changed · +51 lines · -60 tokens per session 92ab8065833e
2mo ago First seen · 332 lines · 346 tokens per session scan A 41f1c144b7a8

Subscribe to this mod's changes

godot is a skill published in the GitHub repository haxqer/godot-skill (254 stars, last pushed 1mo ago), licensed MIT. It adds 245 tokens to every session and 19,824 once invoked, about $0.0010 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 2026-08-30.

Game development

godot next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
godothaxqer/godot-skill	Skill	254	1mo ago	MIT	A	245	Codex
playtest-reportDonchitos/Claude-Code-Game-Studios	Skill	36k	18d ago	MIT	A	20	Claude Code
godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills	Skill	6.9k	9d ago	Apache-2.0	A	95	Claude Code
scenario-unreal-gameplayscenario-labs/skills	Skill	3.2k	yesterday	MIT	A	121	Claude Code
motionOpenDCAI/GameFactory-3A	Skill	1.0k	8d ago	Apache-2.0	A	0	Claude Code, Codex
unity-addressablesBesty0728/Unity-Skills	Skill	1.9k	yesterday	MIT	A	25	Claude Code, Codex
unity-manual-componentBesty0728/Unity-Skills	Skill	1.9k	yesterday	MIT	A	36	Claude Code, Codex