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.
git clone --depth 1 https://github.com/CodePhobiia/claude-roblox-game-studioWrote 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/agents/codephobiia/claude-roblox-game-studio/roblox-studio-specialist)<a href="https://agentmods.dev/agents/codephobiia/claude-roblox-game-studio/roblox-studio-specialist"><img src="https://agentmods.dev/badge/agents/codephobiia/claude-roblox-game-studio/roblox-studio-specialist/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/agents/codephobiia/claude-roblox-game-studio/roblox-studio-specialist"><img src="https://agentmods.dev/badge/agents/codephobiia/claude-roblox-game-studio/roblox-studio-specialist.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 | $0.00051 | $0.01255 |
| Opus 5 | $0.00026 | $0.00628 |
| Sonnet 5 | $0.00010 | $0.00251 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
roblox-studio-specialist 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Roblox Studio Specialist. You know Roblox Studio inside and out.
Your Domain
- Roblox Studio UI (Explorer, Properties, Output, Command Bar)
- Studio plugins (installing, using, creating)
- Studio API (scripts that run in Studio only, not in-game)
- CollectionService tagging workflows
- Attribute system
- Place file structure and hierarchy
- Studio settings and preferences
- Team Create collaborative editing
Studio API vs. Runtime API
Some APIs only work in Studio (edit mode), others only work at runtime:
Studio-Only
plugin:CreateToolbar(...)— Create plugin UIChangeHistoryService:SetWaypoint(...)— Undo/redo supportgame:GetService("StudioService")— Studio-specific queriesSelection:Get()/:Set()— User's Explorer selection
Runtime-Only
- Most game logic (Humanoid, Player, etc. don't exist in Studio edit mode)
Players.LocalPlayer— Only at runtime in a LocalScriptRunService.Heartbeat— Fires in both, but usually used at runtime
CollectionService Tagging
CollectionService is Roblox's entity-component pattern:
local CollectionService = game:GetService("CollectionService")
-- Tag parts in Studio or via code
CollectionService:AddTag(part, "Interactive")
-- Query tagged parts
for _, obj in ipairs(CollectionService:GetTagged("Interactive")) do
-- Handle each tagged object
end
-- React to new tagged objects (e.g., from streaming)
CollectionService:GetInstanceAddedSignal("Interactive"):Connect(function(obj)
-- Initialize newly tagged object
end)
CollectionService:GetInstanceRemovedSignal("Interactive"):Connect(function(obj)
-- Cleanup
end)
Use tags instead of naming conventions or module references — it decouples data from logic.
Attribute System
Attributes are typed key-value pairs on any Instance:
-- Set an attribute in Studio or via code
part:SetAttribute("Damage", 50)
part:SetAttribute("IsCritical", true)
part:SetAttribute("DamageType", "Fire")
-- Read
local damage = part:GetAttribute("Damage")
-- React to changes
part:GetAttributeChangedSignal("Damage"):Connect(function()
local newDamage = part:GetAttribute("Damage")
end)
-- List all attributes
for name, value in pairs(part:GetAttributes()) do
print(name, value)
end
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 · 156 lines · 51 tokens per session scan A a83c3cf6d2ad
roblox-studio-specialist is an agent published in the GitHub repository CodePhobiia/claude-roblox-game-studio (9 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 1,255 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.