robridge-tools

Rules for using RoBridge MCP to control Roblox Studio, the development tool for building Roblox games and experiences. They cover typed actions, asset searching, playtesting, logs, and stopping test sessions.

In plain words
What is it for?
Use them when creating or editing Roblox objects, scripts, interfaces, lighting, terrain, cameras, assets, or gameplay and then verifying those changes in Play mode.
Why use it?
They reduce mistakes when changing Roblox projects, especially by requiring real asset searches and testing player-visible features before claiming they work.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/allusia1/robridge/robridge-tools
Clone the repo
git clone --depth 1 https://github.com/Allusia1/RoBridge

Made for: Cursor.

Per session 394 This file is loaded in full into every session.
When invoked 394 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00394 $0.00394
Opus 5 $0.00197 $0.00197
Sonnet 5 $0.00079 $0.00079
Haiku 4.5 $0.00039 $0.00039

Measured 2d ago against content hash f9fdb621f583, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

robridge-tools 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 2d 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.

.cursor/rules/robridge-tools.mdc · 38 lines

What it actually says

RoBridge tool use

The MCP schemas are the catalog. Do not recopy actions into chat or extra docs. Call the tools.

Prefer typed tools

  • Instances, properties, scripts, UI, lighting, terrain, camera, assets, play — use the matching tool.
  • execute_luau is last resort when no typed action fits.
  • Related mutations go in one batch_execute, not many round-trips.

Assets

  • manage_assets search first, then insert an assetId from those results.
  • Never invent or hardcode rbxassetid values (sounds, animations, skyboxes, models).

Playtest new features

If the change is something a player can see or use in Play, playtest it before you say it works. Skip playtest for docs, dashboard CSS, rules, or schema-only edits.

  1. Prefer manage_studio run_test with a short Luau body that prints [ROBRIDGE_TEST] PASS or FAIL.
  2. World objects (crates, parts, clickables): manage_input walk_and_click.
  3. Screen / PlayerGui buttons: manage_ui click (or manage_input click_path).
  4. Read manage_logs. If it fails, fix once and retest.
  5. play_stop when you are done. Do not leave Play running.
  6. Tell the user what you tested and whether it passed.

Do not hand-roll play_start + logs + play_stop when run_test fits.

Studio

  • If a call says no Studio session, stop and say so. Do not fake results.
  • Keep the crate place clean unless the user asks to add more world content.
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. 2d ago First seen · 38 lines · 394 tokens per session scan A f9fdb621f583

Subscribe to this mod's changes

robridge-tools is a cursor rule published in the GitHub repository Allusia1/RoBridge (1 stars, last pushed 16d ago), licensed MIT. It adds 394 tokens to every session, about $0.0020 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.