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 nonlooped/roblox-suite --skill roblox-coregit clone --depth 1 https://github.com/nonlooped/roblox-suiteWrote 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/nonlooped/roblox-suite/roblox-core)<a href="https://agentmods.dev/skills/nonlooped/roblox-suite/roblox-core"><img src="https://agentmods.dev/badge/skills/nonlooped/roblox-suite/roblox-core/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/nonlooped/roblox-suite/roblox-core"><img src="https://agentmods.dev/badge/skills/nonlooped/roblox-suite/roblox-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.01925 |
| Opus 5.5 | $0.00014 | $0.00770 |
| Sonnet 5.5 | $0.00007 | $0.00385 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade A, and why
roblox-core 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.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
roblox-core
Key sources: https://create.roblox.com/docs/en-us/scripting/services, https://create.roblox.com/docs/en-us/luau, https://create.roblox.com/docs/en-us/luau/tables, https://create.roblox.com/docs/en-us/luau/type-checking, https://create.roblox.com/docs/en-us/scripting/locations, https://create.roblox.com/docs/en-us/projects/data-model, https://create.roblox.com/docs/en-us/projects/client-server, https://create.roblox.com/docs/en-us/workspace/streaming, https://create.roblox.com/docs/en-us/scripting/multithreading, https://create.roblox.com/docs/en-us/scripting/attributes
Script initialization
local Service = game:GetService("ServiceName"). Do this once, name the variable after the service.local Module = require(ReplicatedStorage:WaitForChild("Module"))- Local helper functions.
- Connect to events.
Services are the primary way you access engine functionality instead of a traditional standard library.
Modern task library
Use the modern task API; the legacy globals wait(), spawn(), and delay() are deprecated/soft-deprecated:
task.wait(n?): yields for aboutnseconds (default one frame) and returns elapsed time.task.spawn(f, ...): schedulesfto run asynchronously.task.defer(f, ...): defersfuntil after the current event cycle.task.cancel(thread): cancels a thread returned bytask.spawn/task.defer.
For parallel code, task.desynchronize() and task.synchronize() move the current thread between the parallel and serial phases.
Services by purpose
Container / hierarchy services (visible in Explorer, part of the DataModel):
- Workspace (3D content)
- Lighting (environment, atmosphere, post effects)
- ReplicatedStorage / ReplicatedFirst (shared code & assets)
- ServerScriptService (server-only logic)
- StarterGui / StarterPlayer / StarterPack (templates cloned to players)
- Players, Teams, SoundService, etc.
Core runtime & scripting services:
- RunService: Heartbeat fires after physics on both sides; PreSimulation fires before physics on both sides; PreRender is client-only and fires before rendering.
- TweenService (see animation skill)
- CollectionService (tags)
- ContextActionService, UserInputService, GuiService
- ContentProvider (preloading)
What ships with it
4 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.
- 1mo ago Changed · -21 lines · -24 tokens per session d63eed537b70
- 1mo ago First seen · 158 lines · 59 tokens per session scan A e856c70d4fd6
roblox-core is a skill published in the GitHub repository nonlooped/roblox-suite (23 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 1,925 once invoked, about $0.0001 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.
Other skills, from other repositories
roblox-engineer
!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 !cat skills/shared/protocols/quality-gate.md 2>/dev/null || true !cat…
roblox-dev-skill
Verified, current Roblox and Luau knowledge for writing, reviewing and debugging Roblox game code. Use it for ANY task that involves Roblox, Luau or Roblox Studio, even a quick question or a one-line snippet: scripts and modules, RemoteEvents, DataStores and ProfileStore, ProcessReceipt and monetization, UI, the Input…
roblox-best-practices
Roblox and Luau game code standards. Writes, reviews, and fixes Script, LocalScript, and ModuleScript code and game systems such as shops, DataStore saves, RemoteEvents, combat, NPCs, and UI. Use when a request involves Luau code or a Roblox Studio project, even when Roblox is never named, when a game bug is reported…
rbx-dev
Meta-skill for complete Roblox game development with Rojo — the entry point that knows and unifies the three specialist skills /rojo (filesystem→Studio sync, project setup), /rbx-studio (editor, MCP, assets, malware scan) and /game-design (roles, workflows, GDD). Use this skill for ANY Roblox game-dev undertaking…
rojo
Operating Rojo — the filesystem-to-Roblox-Studio sync tool for professional Roblox development in VS Code / Claude Code instead of the Studio editor. Use this skill whenever Rojo is involved: rojo serve/rojo build, writing or debugging default.project.json, rokit/rokit.toml and tool versions (Rojo, Lune, Wally)…
roblox-studio
Build, inspect, repair, validate, and playtest Roblox Studio maps and Luau through the local bridge. Use for SceneSpecs, terrain, Studio edits, gameplay objects, visual checks, and Rojo output.