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/qa-tester)<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>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 | $0.00044 | $0.01086 |
| Opus 5 | $0.00022 | $0.00543 |
| Sonnet 5 | $0.00009 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
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.
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
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 · 157 lines · 44 tokens per session scan A 02cd68df14df
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.
Other agents, from other repositories
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
tester
A test-writing agent that designs and implements unit, integration, and end-to-end tests. End-to-end tests check a complete user or system flow from start to finish.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
test-expert-csk
Test expert. Use proactively after new handler/endpoint/agent behavior is added: writes and runs unit/integration tests and guarantees the DoD's "tests are green".
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…