roblox-studio

roblox-studio is a skill for Claude Code, Codex from XAIHT/Tlamatini. It costs 120 tokens per session (2,514 once invoked), scanned A, original, MIT.

A runbook for building and editing Roblox Studio projects through an MCP connection. Roblox Studio is the editor used to create Roblox games and experiences.

In plain words
What is it for?
Use it to create or modify terrain, parts, scripts, models, and materials in an open Roblox Studio place.
Why use it?
It checks the Studio connection first and provides a structured way to build, inspect, and verify changes.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to create or modify terrain, parts, scripts, models, and materials in an open Roblox Studio place.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xaiht/tlamatini/roblox_studio
Install

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.

Any agent
npx skills add XAIHT/Tlamatini --skill roblox_studio
Clone the repo
git clone --depth 1 https://github.com/XAIHT/Tlamatini

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for roblox-studio

README.md
[![agentmods](https://agentmods.dev/badge/skills/xaiht/tlamatini/roblox_studio/github.svg)](https://agentmods.dev/skills/xaiht/tlamatini/roblox_studio)
Your own site
<a href="https://agentmods.dev/skills/xaiht/tlamatini/roblox_studio"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/roblox_studio/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.

agentmods 80×15 button for roblox-studio

Your own site · 80×15
<a href="https://agentmods.dev/skills/xaiht/tlamatini/roblox_studio"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/roblox_studio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,514 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.02514
Opus 5 $0.00060 $0.01257
Sonnet 5 $0.00024 $0.00503
Haiku 4.5 $0.00012 $0.00251

Measured 9d ago against content hash 6a89e65c4bc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

roblox-studio 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 9d 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.

Tlamatini/agent/skills_pkg/roblox_studio/SKILL.md · 157 lines

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.

Roblox Studio — build it right, build it once, make it look REAL

Runbook for anything built or edited in Roblox Studio. The tools are the External-MCP tools ext__Roblox_Studio__<tool> (need Multi-Turn + ACPX on). Work as an OPERATOR: preflight, build in a FEW big scripts, verify, report.

STEP 0 — Preflight (ALWAYS, before any build)

  1. external_mcp_status — is Roblox_Studio connected? If not: external_mcp_reconnect, then external_mcp_wait (a first-run stdio child takes seconds).
  2. list_roblox_studios → if more than one, set_active_studio on the intended one.
  3. get_studio_state — a place must be open with the plugin connected.
  4. No Studio connected: STOP and say "Open Roblox Studio with a place, make sure the MCP plugin is running, then say go." Never fake a build.

Tool map

Want to… Use
Run ANY Luau (terrain, parts, scripts, properties) execute_luau — the workhorse
Wait for an async generate_* job wait_job_finished
See errors / prints get_console_output
Read the scene tree inspect_instance, search_game_tree
AI-generate an organic mesh/model/material generate_mesh, generate_procedural_model, generate_material (async → poll)
Marketplace asset search_assetinsert_asset
Author/read scripts multi_edit, script_read, script_search, script_grep
See the result screen_capture

Use execute_luau for deterministic geometry; reserve the generative tools for organic one-off props.

GOLDEN RULES

  1. Batch — the ENTIRE build in one or a few looping execute_luau scripts, not one part per call.
  2. Realism = Terrain VOXELS + Perlin noise (below). Never landscape out of Parts, never symmetric concentric layers.
  3. Wrap every script in pcall, end with print("TLM_OK …") (else warn(err)), then confirm via get_console_output.
  4. Correct Luau typesVector3.new(x,y,z) takes three NUMBERS. "Unable to cast double to Vector3" means you passed a number where a Vector3 belongs: fix it, don't retry unchanged.
  5. Undo-friendlyChangeHistoryService:TryBeginRecording(...) / :FinishRecording(...).
  6. Never loop on a failing tool. Two errors → stop, read the console, fix the cause or say so honestly (the executor blocks a 3× repeat anyway).
  7. Verify, then report. "Done" only after the console (ideally a capture) confirms it.

Read the full file on GitHub · 157 lines

Changes

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.

  1. 9d ago First seen · 157 lines · 120 tokens per session scan A 6a89e65c4bc0

Subscribe to this mod's changes

roblox-studio is a skill published in the GitHub repository XAIHT/Tlamatini (16 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 2,514 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

develop-web-game

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with rendergametotext.

netease-youdao/LobsterAI · 64 tokens

threejs-animation

Three.js animation - keyframe animation, skeletal animation, morph targets, animation mixing. Use when animating objects, playing GLTF animations, creating procedural motion, or blending animations.

calesthio/OpenMontage · 40 tokens

threejs-geometry

Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.

calesthio/OpenMontage · 46 tokens

threejs-fundamentals

Three.js scene setup, cameras, renderer, Object3D hierarchy, coordinate systems. Use when setting up 3D scenes, creating cameras, configuring renderers, managing object hierarchies, or working with transforms.

calesthio/OpenMontage · 51 tokens

threejs-world-generation

Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs. Use for cinematic 3D terrain, semantic regions, procedural biomes, explicit landmarks, environmental scattering, camera fly-throughs, world diagnostics, or requests for a real 3D environment rather than generated 2D footage.…

calesthio/OpenMontage · 100 tokens

3d-asset-generation

Generate, reconstruct, inspect, and route production 3D assets for OpenMontage worlds using Atlas Cloud, fal.ai, licensed catalogs, and Blender.

calesthio/OpenMontage · 37 tokens