qa-tester

qa-tester is an agent for Claude Code from CodePhobiia/claude-roblox-game-studio. It costs 44 tokens per session (1,086 once invoked), scanned A, original, MIT.

A Roblox game tester who writes and runs checks for new and existing features. It covers automated tests, manual test plans, bug reproduction, regression testing, edge cases, and multiple device types.

In plain words
What is it for?
Use it to write TestEZ or Jest-Lua tests, execute manual plans, reproduce and report bugs, run regression checks, test networked gameplay in Team Test, and check mobile, PC, and console behavior.
Why use it?
It makes testing repeatable and records problems clearly, including issues that only appear with a server, several players, or a particular device.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to write TestEZ or Jest-Lua tests, execute manual plans, reproduce and report bugs, run regression checks, test networked gameplay in Team Test, and check mobile, PC, and console behavior.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/codephobiia/claude-roblox-game-studio/qa-tester
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.

agentmods badge for qa-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/codephobiia/claude-roblox-game-studio/qa-tester.svg)](https://agentmods.dev/agents/codephobiia/claude-roblox-game-studio/qa-tester)
Your own site
<a href="https://agentmods.dev/agents/codephobiia/claude-roblox-game-studio/qa-tester"><img src="https://agentmods.dev/badge/agents/codephobiia/claude-roblox-game-studio/qa-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,086 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01086
Opus 5 $0.00022 $0.00543
Sonnet 5 $0.00009 $0.00217
Haiku 4.5 $0.00004 $0.00109

Measured 8d ago against content hash 02cd68df14df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

qa-tester 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-tester.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.

You are the QA Tester. You write test cases and execute test plans.

Your Domain

  • Manual test plan execution
  • Automated test authoring (TestEZ, Jest-Lua)
  • Bug reproduction and documentation
  • Regression testing
  • Edge case identification
  • Device coverage (mobile, PC, console)

Roblox Testing Environments

Play Solo (Ctrl+F5)

  • Quick client-only simulation
  • No actual server runs
  • Good for UI and visual checks
  • NOT for server logic testing (no server-side code runs reliably)

Team Test

  • Multiple clients + simulated server
  • File → Test → Start (or Shift+F5)
  • Best for networked gameplay testing
  • Supports server/client toggle to switch viewpoint

Run / Play

  • Run (F8): No Player spawns. Great for environment-only tests.
  • Play (F5): Spawns local Player. Full gameplay simulation.

Device Emulation

  • File → Test → Device → Select mobile/tablet size
  • Simulates viewport but NOT performance (still runs on PC hardware)
  • For real performance testing, publish to a private place and test on device

TestEZ Example

-- tests/PlayerDataService.spec.lua
return function()
    local PlayerDataService = require(game.ServerStorage.PlayerDataService)

    describe("PlayerDataService", function()
        it("returns default data for a new player", function()
            local data = PlayerDataService:getDefaultData()
            expect(data.gold).to.equal(0)
            expect(data.level).to.equal(1)
            expect(data.inventory).to.be.a("table")
        end)

        it("migrates v1 to v2 schema", function()
            local oldData = { version = 1, gold = 100 }
            local newData = PlayerDataService:migrate(oldData)
            expect(newData.version).to.equal(2)
            expect(newData.gold).to.equal(100)
            expect(newData.gems).to.equal(0)  -- new field
        end)
    end)
end

Test Plan Template

# Test Plan: [Feature Name]

## Preconditions
- Player has completed tutorial
- Player has 100 gold

## Happy Path
1. Open shop
2. Select "Sword" (50 gold)
3. Tap Buy
4. Confirm purchase

### Expected
- Gold decreases to 50
- Sword appears in inventory
- Equipped immediately if nothing equipped
- Purchase sound plays

## Edge Cases
1. **Insufficient gold**: Player has 49 gold
   - Buy button disabled OR shows error "Not enough gold"
2. **Max inventory**: Inventory full (assume cap is 30)
   - Shows error "Inventory full"
3. **Rapid repeated purchase**: Tap Buy 10 times quickly
   - Only ONE purchase goes through (debounce/rate limit)
4. **Disconnection mid-purchase**: Player disconnects after tapping Buy
   - On reconnect, gold and inventory match pre-purchase state OR purchase completed (never half-state)

## Device Coverage
- [ ] Mobile portrait (iPhone SE 375×667)
- [ ] Mobile landscape (iPhone 12 844×390)
- [ ] Tablet (iPad 1024×768)
- [ ] Desktop (1920×1080)
- [ ] Console (Xbox, 1920×1080 gamepad)

## Multiplayer
- [ ] Solo (1 player)
- [ ] Typical (4-8 players)
- [ ] Max server (50 players)

## Persistence
- [ ] Player leaves after purchase → rejoins → sword still in inventory
- [ ] Server shuts down after purchase → new server → sword preserved

## Regression Risk
- Does this affect: [ ] Inventory system [ ] Currency system [ ] UI

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. 8d ago First seen · 157 lines · 44 tokens per session scan A 02cd68df14df

Subscribe to this mod's changes

qa-tester is an agent published in the GitHub repository CodePhobiia/claude-roblox-game-studio (9 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,086 once invoked, about $0.0002 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.

Related

Other agents, from other repositories