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 ellmos-ai/skills --skill rbx-devgit clone --depth 1 https://github.com/ellmos-ai/skillsWrote 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/ellmos-ai/skills/rbx-dev)<a href="https://agentmods.dev/skills/ellmos-ai/skills/rbx-dev"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/rbx-dev/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/ellmos-ai/skills/rbx-dev"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/rbx-dev.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 | $0.00182 | $0.02275 |
| Opus 5.5 | $0.00073 | $0.00910 |
| Sonnet 5.5 | $0.00036 | $0.00455 |
| Haiku 4.5 | $0.00018 | $0.00228 |
Grade A, and why
rbx-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 24d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hinweis: Nicht mit der Roblox Corporation affiliiert; „Roblox" ist eine Marke ihrer Inhaber. „rbx" ist das gängige Community-Kürzel.
Roblox-Dev — Meta-Skill für Roblox-Spieleentwicklung
Zweck
Der zentrale Einstieg für Roblox-Game-Dev mit einem Rojo-basierten, versionierbaren Workflow. Dieser Skill bündelt das übergreifende Wissen — Projektstruktur, Architektur-Pattern und die wichtigsten Luau-Fallstricke — und leitet für Spezialfragen an die drei Unterskills weiter:
| Unterskill | Wofür |
|---|---|
/rojo |
Filesystem→Studio-Sync, default.project.json, rokit/Wally/Lune, Projekt-Skelett, Sync-Probleme |
/rbx-studio |
Studio-Bedienung, Szene-vs-Code-Modus, Studio-MCP, Asset-Pipeline, Malware-Scan |
/game-design |
Rollen & Teilaufgaben, Entwicklungs-Chains, Game Design Document (KONZEPT.md), Multi-Agent |
Routing-Regel: Geht es um Sync/Build/Setup →
/rojo. Um Editor/Assets/Testen in Studio →/rbx-studio. Um Konzept/Rollen/Prozess →/game-design. Um Code-Architektur, Luau-Stolperfallen oder den Gesamtablauf → hier bleiben.
Stack auf einen Blick
- Sprache: Luau (
.luau, nicht.lua). Code englisch, Kommentare/Doku deutsch, UI-Texte deutsch. - Sync: Rojo via rokit (gepinnte Tool-Versionen). Dateisystem = Quelle der Wahrheit.
- Tools: Rojo (Sync/Build), Lune (Tests/Skripte außerhalb Studio), Wally (Packages), optional Knit (Service-/Controller-Framework, neue Projekte), Selene (Linter).
- Steuerung: Roblox-Studio-MCP für KI-gesteuerte Inspektion/Tests/Asset-Insertion.
Projektstruktur (Standard)
ProjektName/
├── default.project.json # Rojo-Mapping
├── rokit.toml # gepinnte Tool-Versionen
├── wally.toml # Package-Dependencies
├── KONZEPT.md # Game Design Document
├── src/
│ ├── shared/ # → ReplicatedStorage(.ProjektName.shared)
│ │ ├── Config.luau # zentrale Werte, States, Gameplay-Parameter
│ │ ├── GameEnums.luau # Enums, Remote-Namen, Konstanten
│ │ └── *Defs.luau # Datendefinitionen (Items, Einheiten, Level)
│ ├── server/ # → ServerScriptService(.ProjektName)
│ │ ├── Main.server.luau # EINZIGER Server-Entry-Point (Script)
│ │ └── *Manager.luau # ModuleScripts, von Main per require() geladen
│ ├── client/ # → StarterPlayerScripts(.ProjektName)
│ │ └── GameClient.client.luau # Client-Entry-Point (LocalScript)
│ └── gui/ # → StarterGui(.ProjektName)
│ └── *HUD.client.luau # GUI-Aufbau + Heartbeat-Loop
└── assets/ # optionale .rbxm/.rbxl (scriptfrei)
What ships with it
8 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.
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.
- 24d ago Changed · +182 tokens per session 0a489cbd2450
- 1mo ago First seen · 157 lines · 0 tokens per session scan A bfec3272c309
rbx-dev is a skill published in the GitHub repository ellmos-ai/skills (8 stars, last pushed 2d ago), licensed MIT. It adds 182 tokens to every session and 2,275 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
design-review
Reviews one design document for completeness, internal consistency, implementability, and design standards. Before handing to programmers.
art-bible
Author the Art Bible — visual identity gating asset production. Run before /map-systems.
asset-spec
Per-asset visual specs plus AI generation prompts from GDDs and character profiles. After the art bible.
localize
Localization pipeline — find hardcoded strings, extract string tables, cultural review, VO, RTL, enforce string freeze.
vertical-slice
Pre-production validation — end-to-end build to confirm the full loop is achievable before committing to Production. After GDDs, architecture, UX specs.
help
What should I do next? Use when stuck or you don't know what to do.