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 AshExplained/roblox-skills --skill roblox-luau-architecturegit clone --depth 1 https://github.com/AshExplained/roblox-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/ashexplained/roblox-skills/roblox-luau-architecture)<a href="https://agentmods.dev/skills/ashexplained/roblox-skills/roblox-luau-architecture"><img src="https://agentmods.dev/badge/skills/ashexplained/roblox-skills/roblox-luau-architecture/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/ashexplained/roblox-skills/roblox-luau-architecture"><img src="https://agentmods.dev/badge/skills/ashexplained/roblox-skills/roblox-luau-architecture.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 | $0.00057 | $0.00808 |
| Opus 5 | $0.00028 | $0.00404 |
| Sonnet 5 | $0.00011 | $0.00162 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
roblox-luau-architecture 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 11d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roblox Luau Architecture
Goal
Keep Roblox game code modular, server-authoritative, and easy to extend. Use Roblox Studio MCP to inspect existing scripts before changing architecture.
MCP Workflow
- Start with
list_roblox_studios,set_active_studioif needed, andget_studio_state. - Locate code with
script_searchorscript_grep. - Read relevant scripts with
script_readbefore editing. - Apply edits with
multi_edit. - Playtest with
start_stop_play. - Check
get_console_outputfor regressions.
Placement Rules
- Put authoritative game logic in
ServerScriptServiceor server-owned modules. - Put shared constants, type definitions, remotes, and pure shared helpers in
ReplicatedStorage. - Put player input, camera, local-only UI, and visual prediction in client scripts.
- Keep workspace scripts rare and intentional; prefer service-style scripts that manage tagged instances or configured folders.
- Avoid scattering duplicated constants across client and server.
Remote Boundaries
- Treat every client remote payload as untrusted.
- Prefer narrow remotes with explicit action names and typed payload checks.
- Rate-limit player-triggered remotes that can affect economy, inventory, combat, or placement.
- Use RemoteFunctions sparingly; avoid long-yielding server calls from the client.
- Never let the client decide currency, inventory, ownership, damage, quest completion, or purchase grants.
Module Pattern
Use modules for:
- Services with
InitandStartstyle lifecycle. - Data access wrappers.
- Economy calculations.
- Reward tables and balancing constants.
- UI controllers on the client.
- Shared utility functions that are deterministic and side-effect-light.
Keep modules small enough that another system can depend on them without importing unrelated behavior.
Prefer Deep Modules
Aim for deep modules: a lot of behavior behind a small, stable interface. A shallow module — where the interface is nearly as complex as its implementation — earns its keep only if it hides real complexity.
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.
- 11d ago First seen · 75 lines · 57 tokens per session scan A 81412a59800b
roblox-luau-architecture is a skill published in the GitHub repository AshExplained/roblox-skills (6 stars, last pushed 2mo ago), licensed MIT. It adds 57 tokens to every session and 808 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-unity-specialist
Invoke when the user works with Unity or asks about C#, MonoBehaviour, DOTS/ECS, Shader Graph, Addressables, UI Toolkit, URP/HDRP, or ScriptableObjects. Triggers on: "Unity", "MonoBehaviour", "DOTS", "ECS", "Shader Graph", "Addressables", "UI Toolkit", "URP", "HDRP", "ScriptableObject", ".unity", ".cs". Do NOT invoke…
game-unreal-specialist
Invoke when the user works with Unreal Engine 5 or asks about C++/Blueprints, GAS, replication, Nanite, Lumen, CommonUI, Enhanced Input, or World Partition. Triggers on: "Unreal", "UE5", "Blueprint", "GAS", "Nanite", "Lumen", "CommonUI", "Enhanced Input", "World Partition", ".uproject". Do NOT invoke for…
reflection-method-call
Call a C# method by reflection — including private methods. Requires a method schema obtained via 'reflection-method-find'. Supports static methods, instance methods (with optional target deserialization), and main-thread / off-thread execution.
script-execute
Compiles and executes C# code dynamically using Roslyn. Supports a full-code mode (default) and a body-only mode — see the skill body for the difference and for how to pass Unity object references as parameters.
reflection-method-find
Find C# methods across every loaded assembly by name / type / parameters — including private methods. Returns serialized MethodData entries usable as schemas for 'reflection-method-call'.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).