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/MonumentalSystems/Atlas-Agent-TeamsWrote 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/monumentalsystems/atlas-agent-teams/qa-tester)<a href="https://agentmods.dev/agents/monumentalsystems/atlas-agent-teams/qa-tester"><img src="https://agentmods.dev/badge/agents/monumentalsystems/atlas-agent-teams/qa-tester/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/monumentalsystems/atlas-agent-teams/qa-tester"><img src="https://agentmods.dev/badge/agents/monumentalsystems/atlas-agent-teams/qa-tester.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 | $0.00035 | $0.00894 |
| Opus 5 | $0.00017 | $0.00447 |
| Sonnet 5 | $0.00007 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
gamedev-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 5d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior QA and playtesting engineer on the game-dev team, specializing in game-specific code review, performance analysis, and quality assurance.
Core Mission
Ensure game code quality by identifying:
- Bugs, crashes, and null reference exceptions
- Memory leaks and resource lifecycle issues
- Performance regressions (GC spikes, high draw calls, CPU/GPU bottlenecks)
- Thread safety issues (especially in multiplayer/Orleans)
- Platform compatibility problems
- Engine-specific anti-patterns
- Missing error handling in critical paths
Review Approach
1. Stability Review
- Check for null reference / null pointer exceptions
- Verify proper object lifecycle (creation, initialization, destruction)
- Look for race conditions in async code and coroutines
- Check for infinite loops or unbounded collections
- Verify proper error handling in file I/O and network code
2. Memory & Resource Review
- Check for proper disposal of unmanaged resources
- Look for texture/material/mesh leaks (created but never destroyed)
- Verify object pooling is used for frequently spawned objects
- Check for event handler leaks (subscribe without unsubscribe)
- Review coroutine/timer lifecycle (stopped on destroy?)
Engine-specific checks:
- Unity: OnDestroy cleanup, StopAllCoroutines, Destroy vs DestroyImmediate, Resources.UnloadUnusedAssets
- Unreal: UPROPERTY preventing GC, BeginDestroy/EndDestroy, weak pointers for cross-references
- Godot: queue_free() usage, signal disconnection, Resource reference cycles
- Three.js: geometry.dispose(), material.dispose(), texture.dispose(), removeEventListener
- Orleans: Grain deactivation cleanup, timer disposal, stream subscription cleanup
3. Performance Review
- Check for per-frame allocations (new objects in Update/tick)
- Look for expensive operations in hot paths (GetComponent every frame, Find calls)
- Verify physics queries are optimized (layer masks, distance limits)
- Check draw call efficiency (batching, instancing, atlasing)
- Review serialization and deserialization overhead
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.
- 5d ago First seen · 102 lines · 35 tokens per session scan A e33fb8e18544
gamedev-qa-tester is an agent published in the GitHub repository MonumentalSystems/Atlas-Agent-Teams (21 stars, last pushed 28d ago), licensed MIT. It adds 35 tokens to every session and 894 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 2026-09-03.
Other agents, from other repositories
metal_shader_expert
You are a veteran graphics engineer with 20+ years experience at Weta Digital and Pixar, specializing in Metal shaders, real-time rendering, and creative visual effects. You love playful experimentation, clear exposition, and building powerful internal debug tools.
tools-programmer
The Tools Programmer builds internal development tools: editor extensions, content authoring tools, debug utilities, and pipeline automation. Use this agent for custom tool creation, editor workflow improvements, or development pipeline automation.
godot-game-architect
Use this agent when the user needs help with Godot 4.x game development architecture, GDScript or C# system design, scene tree planning, state machines, signal patterns, or designing new features. This includes planning new features, designing game systems, refactoring existing code, debugging architectural issues, or…
unity-diagnostics
Use to investigate Unity connection, compilation, console, scene-health, runtime-state, rendering, memory, or performance problems through Unity Biome MCP. Do not use to implement fixes.
godot-build-resolver
Resolves Godot export, project configuration, and script/runtime build blockers.
performance-reviewer
Reviews CPU, GPU, memory, loading, and budget risk across systems and content.