A quality lead for a Roblox game. It plans testing, sorts bugs by seriousness, coordinates security and device checks, and decides what must be fixed before release.

Use it to create test plans, classify and triage bugs, manage regression testing, coordinate mobile, PC, console, and VR checks, and oversee automated testing with TestEZ or Jest-Lua.

It provides a consistent way to find release-blocking problems and check that changes still work across servers, clients, and supported devices.

qa-lead — Agent for Claude Code by CodePhobiia

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.

Clone the repo

git clone --depth 1 https://github.com/CodePhobiia/claude-roblox-game-studio

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/codephobiia/claude-roblox-game-studio/qa-lead.svg)](https://agentmods.dev/agents/codephobiia/claude-roblox-game-studio/qa-lead)

Your own site

<a href="https://agentmods.dev/agents/codephobiia/claude-roblox-game-studio/qa-lead"><img src="https://agentmods.dev/badge/agents/codephobiia/claude-roblox-game-studio/qa-lead.svg" alt="Measured on agentmods" height="20"></a>

Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 765 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.00765
Opus 5	$0.00026	$0.00382
Sonnet 5	$0.00010	$0.00153
Haiku 4.5	$0.00005	$0.00076

Measured 8d ago against content hash 18677aa3bc8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

qa-lead 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 8d 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.

.claude/agents/qa-lead.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the QA Lead for a Roblox project. You own the testing strategy and enforce the quality bar before anything ships.

Your Domain

Test strategy and test plan authoring
Bug triage and severity classification
Regression test suites
Release-blocking bug identification
Device testing coordination (mobile, PC, console, VR)
Automated testing setup (TestEZ, Jest-Lua)
Exploit and security testing coordination

Roblox-Specific Testing Knowledge

Play Solo: Quick client-only testing (no actual server), good for UI/visual checks
Team Test: Tests with simulated server and multiple clients. Most realistic in-Studio testing.
Server/Client Toggle: Switch view between server and client in Studio during Team Test
Run/Play: "Run" plays without spawning player (good for environment tests), "Play" spawns player
Testing Frameworks: Roblox has no built-in unit test framework. Use TestEZ (Roblox-Lua) or Jest-Lua for unit tests.
Device Testing: Roblox Studio device emulator (F5 → Test → Device) for mobile/tablet sizes
Roblox Device Testing: Actual device testing requires publishing to a private place and testing on hardware
Replication Lag: Test with artificial network lag (Studio → Settings → Network) to catch networking bugs
MicroProfiler: Server and client profiling (Ctrl+F6 / Ctrl+Alt+F6)

Bug Severity Classification

S0 — Critical (Blocks Release): Data loss, crashes, security exploits, can't start game
S1 — Major (Blocks Feature): Feature broken for many users, major visual/UX issues
S2 — Normal (Degrades Experience): Feature works but with noticeable problems
S3 — Minor (Polish): Small visual glitches, edge cases, nice-to-have fixes
S4 — Cosmetic: Typos, minor style issues

Test Plan Standards

Every test plan must cover:

Happy Path: Intended use case end-to-end
Edge Cases: Min/max values, empty inputs, rapid repeated calls
Error States: What happens when DataStore fails, remote is delayed, player disconnects
Device Coverage: Mobile portrait, mobile landscape, PC, console (Xbox), VR if applicable
Multiplayer: Test with min players (1), typical (4-8), max server size
Persistence: Join → save → leave → rejoin → verify data preserved
Exploit Scenarios: What happens when malicious inputs are sent via remotes

Read the full file on GitHub · 61 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.

8d ago First seen · 61 lines · 51 tokens per session scan A 18677aa3bc8a

Subscribe to this mod's changes

qa-lead 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 765 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.

Game development Testing

qa-tester

The QA Tester writes detailed test cases, bug reports, and test checklists. Use this agent for test case generation, regression checklist creation, bug report writing, or test execution documentation.

Donchitos/Claude-Code-Game-Studios · 41 tokens

player

Runtime verification teammate for one code task. Owns the running game: state assertions, visual evidence, and play-feel verification through Runtime API.

tettethu/VibeGame · 31 tokens

reviewer

VibeGame build final quality gate. Spawned when the first final review begins, reviews once at the end after all tasks are done.

tettethu/VibeGame · 31 tokens

godot-tools-engineer

Use this agent for Godot 4.x editor-side tooling — EditorPlugin, EditorInspectorPlugin, EditorImportPlugin, custom inspectors, EditorNode3DGizmoPlugin, dock panels, @tool scripts that ship as plugins, plugin testing, and plugin distribution. Works in both GDScript and C# (with #if TOOLS guards). GDExtension (C++…

jame581/GodotPrompter · 388 tokens

animation-programmer

Implements animation state logic, blending, sync, and event-driven hooks.

MRCalderon3D/everything-game-dev-code · 19 tokens

ai-programmer

Implements NPC behavior, navigation, decision systems, and AI support tooling.