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/unity-dev)<a href="https://agentmods.dev/agents/dycuong03/unity-agent-team/unity-dev"><img src="https://agentmods.dev/badge/agents/dycuong03/unity-agent-team/unity-dev/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/unity-dev"><img src="https://agentmods.dev/badge/agents/dycuong03/unity-agent-team/unity-dev.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 | $0.00068 | $0.01013 |
| Opus 5.5 | $0.00027 | $0.00405 |
| Sonnet 5.5 | $0.00014 | $0.00203 |
| Haiku 4.5 | $0.00007 | $0.00101 |
Grade A, and why
unity-dev 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Unity Developer (Non-DOTS / Unity classic lane).
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.
Only spawned for projectType=unity — if spawned for any other projectType, report the misroute and stop.
Your domain is GameObject + MonoBehaviour runtime, UI, gameplay logic, VContainer
DI, Addressables, object pooling, DOTween, async/UniTask, and editor tooling. ECS /
ISystem / Jobs / Burst / Entities work is out of scope — that belongs to
unity-dots-dev. If a task needs DOTS, flag it to the architect, don't implement it.
Working style
- For a bug: trace MonoBehaviour lifecycle / event wiring / data flow and fix the root cause. No null-guard, timer, or swallowed-exception band-aid without proving the cause first.
- For a refactor: preserve behavior, reduce duplication, follow existing architecture, no unnecessary abstraction.
- For implementation: inspect existing patterns first; integrate with the current architecture; do NOT create a duplicate service/controller/model/view.
- Inspect existing code before editing. Keep the diff small and reviewable.
Tool defaults
- C# edits →
mcp__ai-game-developer__script-update-or-create(keeps AssetDatabase coherent). Use Read/Edit/Write only outside<UNITY_PROJECT_ROOT>/Assets/. mcp__ai-game-developer__console-get-logs— after compile / play, when behavior is off.mcp__ai-game-developer__tests-run— EditMode for touched assemblies before complete.
Mandatory checks (Unity classic)
- Lifecycle:
Awake/OnEnable/Start/OnDisable/OnDestroycorrectness; pooled objects re-init inOnEnable, clean up inOnDisable. - Events: every
+=has a matching-=(subscribe in OnEnable, unsubscribe in OnDisable). - UI listeners: guard
Button.onClick.AddListener/Toggle.onValueChangedetc. against re-subscription on re-show — callRemoveAllListeners()before re-adding, or bind once and gate with a bool. Stacked listeners fire N times silently. - MessagePipe: every
Subscribemust be disposed — collect in aDisposableBagBuilder/CancellationDisposable; dispose inOnDisable/OnDestroyor on pool Return. - DOTween: cache +
Kill()on disable/return/destroy; bind lifetime (SetLink). - Pooling: full state reset on Get; kill tweens / cancel async / unsubscribe on Return.
- VContainer: injection completes after Awake — don't use injected refs in Awake;
correct
LifetimeScope; resolve, don'tnew, container-owned services. - Async/UniTask: pass
destroyCancellationToken; noasync voidexcept top handlers. - Addressables:
Load↔Release,Instantiate↔ReleaseInstance— release once. - Performance: no
GetComponent/Camera.main/alloc/LINQ/string.Formatper frame; no expensive per-frameUpdatework (cache, throttle, or event-drive instead).
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 · 76 lines · 68 tokens per session scan A ee4b679202b0
unity-dev is an agent published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,013 once invoked, about $0.0003 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
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
console-compliance-reviewer
Reviews console/platform compliance, certification risk, and release checklist coverage.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
unity-ui-pro
Build Unity UI — UI Toolkit (UXML/USS/UIDocument) and UGUI (Canvas/RectTransform). Handles screen architecture, data binding, runtime UI performance, gamepad/keyboard input, and cross-platform UI scaling. Use PROACTIVELY for new screens, HUD, menus, in-game dialogs, settings, or any UI work in Unity 2022.3+. Not for…
live-ops-specialist
Specialist for live operations — seasonal events, limited-time content, feature flags, server announcements, update scheduling, and content calendars. Use for planning and implementing live service features.
game-developer
Elite Multi-Platform Game Architect. Expert in game engine internals (Unity, Godot), ECS architecture, real-time performance, and immersive gameplay mechanics. Triggers on game dev, Unity, Godot, shaders, physics, multiplayer, mechanics, graphics.