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.
npx skills add Simone-Tarantino/godot-superpowers --skill create-autoloadgit clone --depth 1 https://github.com/Simone-Tarantino/godot-superpowersWrote 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.
[](https://agentmods.dev/skills/simone-tarantino/godot-superpowers/create-autoload)<a href="https://agentmods.dev/skills/simone-tarantino/godot-superpowers/create-autoload"><img src="https://agentmods.dev/badge/skills/simone-tarantino/godot-superpowers/create-autoload.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00057 | $0.01361 |
| Opus 5 | $0.00028 | $0.00681 |
| Sonnet 5 | $0.00011 | $0.00272 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
create-autoload 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.
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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Autoload
Generate a single autoload singleton. For the canonical starter set (EventBus, GameState, SceneManager, AudioManager, SaveManager) use the bootstrap-godot-project skill.
Steps
1. Create the script
autoload/<snake_case_name>.gd:
extends Node
## {OneLinePurpose}.
## Registered as autoload "{PascalCaseName}". Access globally via {PascalCaseName}.
# signals
# enums
# constants
# vars
func _ready() -> void:
pass
extends Node is the safe default. Use Node2D / Node3D only if the autoload needs a transform (rare). Object won't work — autoloads must be Node.
2. Register in project.godot
Add under [autoload] (create the section if missing):
[autoload]
{PascalCaseName}="*res://autoload/{snake_case_name}.gd"
The leading * enables the singleton — without it, the script just gets instantiated as a child of the root node, NOT exposed by name.
Order matters: an autoload that depends on another must appear after it. Example: SceneManager depends on EventBus → list EventBus first.
3. Reload project
Either restart Godot or open Project Settings → Globals → Autoload to see the entry. The editor exposes the autoload to scripts only after registration is loaded.
4. Use it
# anywhere in any script
SaveManager.save_game(0)
EventBus.player_died.emit()
Decision rules
When to autoload
✅ Cross-scene state that must persist across scene changes (current run data, audio bus volumes, save slot)
✅ Cross-scene event hub (EventBus)
✅ Single-instance services (AudioManager, SaveManager, SceneManager)
✅ Settings / config that any scene reads
When NOT to autoload
❌ Anything tied to a specific scene's lifecycle (player, level)
❌ Anything you might want multiple of (camera rig, AI brain)
❌ Heavy _process work that runs even when irrelevant
❌ Things that should be Resource instead (pure data)
Alternatives
| Alternative | When |
|---|---|
Group + get_tree().call_group() |
Many-to-many broadcasts (alert all enemies) |
Static class (class_name X extends RefCounted) |
Pure utility functions, no state |
| Resource singleton via preload | Shared read-only data (curves, constants) |
| Service locator on a non-autoload root node | Tested apps where DI is preferred |
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 · 159 lines · 57 tokens per session scan A dc7219242f29
create-autoload is a skill published in the GitHub repository Simone-Tarantino/godot-superpowers (2 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,361 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 2026-08-31.
Other skills, from other repositories
game-build-team
Build a Godot 4 / GDScript game feature with a coordinated agent team — a Manager (you), a Creative Director, a Logic Developer, an Animation Developer, and a Tester — that iteratively and autonomously design, build, juice, and verify the feature against the project's design contract to a strict, un-skippable quality…
avatar-contribution-pr
Turn an avatar GitHub issue (from the in-app avatar-editor easter egg) into a merged sprite — validate the art, then either add a new module or replace an existing one, and open a PR that closes the issue. Handles both "Avatar contribution: " (a brand-new sprite) and "Avatar edit: " (a hand-redraw of an existing…
wavedash
Use when building, integrating, testing, uploading, publishing, or preparing a browser game for Wavedash, including CLI setup, Wavedash SDK features, multiplayer, achievements, leaderboards, cloud saves, player identity, user-generated content, store metadata, monetization, and content guidelines.
godot-engineer
!cat skills/shared/protocols/3d-spatial-foundations.md 2>/dev/null || true !cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/game-test-protocol.md 2>/dev/null || true…
bootstrap-game-qa-system
Use ONCE per browser-game project to set up the game-qa infrastructure. Copies the shipped runner template, the adapter skeleton, and the journey schema; gap-fills the project's existing debug system if one is present. Skip for non-game projects.
requesting-game-qa
Use ONLY for QA on browser-game feature work. Triggers when the engineer signals readiness for QA: "request QA on X", "verify X", "QA this", "ready for QA on X", "this should be ready, can we make sure it works?" Compiles a brief, drives test-plan sign-off, then hands off to game-qa. Skip for tooling, build scripts…