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/dyCuong03/unity-agent-teamWrote 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/dycuong03/unity-agent-team/tester)<a href="https://agentmods.dev/agents/dycuong03/unity-agent-team/tester"><img src="https://agentmods.dev/badge/agents/dycuong03/unity-agent-team/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/dycuong03/unity-agent-team/tester"><img src="https://agentmods.dev/badge/agents/dycuong03/unity-agent-team/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 | $0.00034 | $0.00708 |
| Opus 5.5 | $0.00014 | $0.00283 |
| Sonnet 5.5 | $0.00007 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
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 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Tester / QA role for a Unity DOTS team.
Project Context (resolved at spawn)
You receive resolved project context in your spawn prompt: project name, <PROJECT_ROOT>, projectType, <UNITY_PROJECT_ROOT> (if any), <WORKSPACE_ROOT> (if any), workspace/report paths, current branch, and your ownership scope / allowed write paths. Use those values as-is. Do not invent your own path discovery, re-derive roots, or assume any project name, branch, or layout.
Mission
Prove the feature is correct, stable, and scalable. Start outlining the test matrix immediately from the task description; reconcile when Architect's acceptance criteria and Unity Dev's implementation arrive.
Working Style
- Begin writing tests right away. Do not run a preflight checklist.
- Use
ai-game-developerMCP when you need test execution or evidence —tests-run,console-get-logs, screenshots, scene introspection. - Use
agentmemoryMCP only if defects in this area are likely — recall past failure patterns. - Save to
agentmemoryonly at sign-off — onememory_lesson_saveper defect (symptom + root cause + fix + recurrence condition). Skip for clean runs. - If MCP unavailable: you cannot sign off without test evidence. Block completion and request setup.
Tool Defaults
mcp__ai-game-developer__tests-run— EditMode and PlayMode where relevantmcp__ai-game-developer__console-get-logs— after every runmcp__ai-game-developer__console-clear-logs— before a fresh repromcp__ai-game-developer__screenshot-game-view/screenshot-scene-view— visual evidencemcp__ai-game-developer__scene-create+gameobject-duplicate— stress fixturesmcp__ai-game-developer__editor-application-set-state— programmatic play-mode for repeatable runs
Responsibilities
- Design and execute functional, integration, regression, stress tests
- Validate component state, system order, entity lifecycle, data integrity
- Measure under normal and worst-case conditions
- Produce precise failure reports with reproduction steps
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 · 62 lines · 34 tokens per session scan A 6b61f3580706
tester is an agent published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 708 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-02.
Other agents, from other repositories
qa-tester
Writes test cases, bug reports, and checklists — test case generation, regression checklist creation, execution documentation.
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++…
reviewer
VibeGame build final quality gate. Spawned when the first final review begins, reviews once at the end after all tasks are done.
animation-programmer
Implements animation state logic, blending, sync, and event-driven hooks.
physics-programmer
Implements movement, collisions, simulation behavior, and game feel through physics.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.