Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Simone-Tarantino/godot-superpowersnpx agentmods add skills/simone-tarantino/godot-superpowers/using-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/using-godot-superpowers)<a href="https://agentmods.dev/skills/simone-tarantino/godot-superpowers/using-godot-superpowers"><img src="https://agentmods.dev/badge/skills/simone-tarantino/godot-superpowers/using-godot-superpowers/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.
<a href="https://agentmods.dev/skills/simone-tarantino/godot-superpowers/using-godot-superpowers"><img src="https://agentmods.dev/badge/skills/simone-tarantino/godot-superpowers/using-godot-superpowers.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00134 | $0.04074 |
| Opus 5 | $0.00067 | $0.02037 |
| Sonnet 5 | $0.00027 | $0.00815 |
| Haiku 4.5 | $0.00013 | $0.00407 |
Grade A, and why
using-godot-superpowers 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 10d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using godot-superpowers
This file loads automatically whenever Claude touches a Godot project (matched via paths above). Read it first.
Authoritative source: query the
godot-docsMCP server before emitting any Godot 4.x API in code or examples — class names, method signatures, signal payloads, and feature availability change between minor versions. Pre-trained knowledge drifts; the MCP does not. Ifgodot-docsMCP is unavailable, link the equivalent page on https://docs.godotengine.org/en/stable/ instead of guessing. (Full rationale and version-detection workflow in the "The other rule" section below.)
Agent picker (decision table)
Use this table FIRST. It maps situation → exact Agent tool call. Always invoke via Agent with subagent_type: "<name>".
| Situation | Agent | Why this one |
|---|---|---|
Wrote a batch of .gd .tscn .tres .gdshader (3+ files) or a single risky one |
file-verifier |
Recommended after milestone-sized batches; skip for single trivial edits — Haiku, isolated, returns findings only |
| Implementing milestone with 3+ files or 2+ subsystems | orchestrator |
Decomposes, dispatches workers + verifier in parallel, keeps main context flat |
| Milestone batch finished — confirm integration before declaring done | milestone-integrator |
Aggregates verifier verdicts + tests, runs --quit-after 1 smoke on main scene (with --check-only fallback), flips plan status |
.tscn / .tres corrupted by merge or refactor (broken IDs / UIDs / <<<<<<< markers) |
merge-specialist |
Repair scene grammar, dedupe ids, fix paths, restore UIDs from git — text repair, not redesign |
| Designing scene tree / collision layout / node hierarchy | scene-architect |
.tscn structure + layer math without writing scripts |
| Reviewing GDScript for quality / API drift / conventions | code-reviewer |
Sonnet review against Godot 4.x best practices |
| Writing GUT / GdUnit4 tests, pre-release checklist | qa-tester |
Test scaffolding + coverage gaps |
| Designing mechanics, balancing, level pacing | game-designer |
GDD-side reasoning, not code |
| Audio pipeline, bus layout, AudioManager pattern | sound-designer |
Pairs with sfx-generator skill |
| Asset generation, art bible, palette/style guide | art-director |
Generates sprites / textures / 3D models via PixelLab / ComfyUI MCP when available; falls back to placeholders + free CC0 sources otherwise |
| Slow frame, profiler spike, GC churn investigation | performance-profiler |
Root-cause analysis, not blanket optimization |
| Configuring export presets / signing / CI build matrix | export-engineer |
Haiku, mechanical export config |
| "Which addon should I use for X?" / installing addons | addon-curator |
Haiku, recommendations only |
| Project still on Godot 3.x — port to 4.x | gdscript-migrator |
yield/KinematicBody*/onready var rewrites |
| Bug report from playtester → reproduce + fix + regression test | playtest-analyst |
Triage + fix path |
| Codebase research ("where is X?", "find all callers") | Explore (built-in) |
Read-only, isolated, cheap |
| One-shot single-file edit, known fix | direct skill / direct edit | Don't dispatch — overhead > value |
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.
- 10d ago First seen · 199 lines · 134 tokens per session scan A cd778f718cd6
using-godot-superpowers is a skill published in the GitHub repository Simone-Tarantino/godot-superpowers (2 stars, last pushed 4mo ago), licensed MIT. It adds 134 tokens to every session and 4,074 once invoked, about $0.0007 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…