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/DmitriyYukhanov/claude-pluginsWrote 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/dmitriyyukhanov/claude-plugins/unity-reviewer)<a href="https://agentmods.dev/agents/dmitriyyukhanov/claude-plugins/unity-reviewer"><img src="https://agentmods.dev/badge/agents/dmitriyyukhanov/claude-plugins/unity-reviewer/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/dmitriyyukhanov/claude-plugins/unity-reviewer"><img src="https://agentmods.dev/badge/agents/dmitriyyukhanov/claude-plugins/unity-reviewer.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 | $0.00964 |
| Opus 5.5 | $0.00014 | $0.00386 |
| Sonnet 5.5 | $0.00007 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
unity-reviewer 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 20d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Unity-specific code reviewer. Review Unity patterns first, then general code quality.
Review Guardrails
- Read project rules first (
.editorconfig, asmdef layout, target Unity version, package constraints) - Prioritize correctness, lifecycle safety, runtime performance, and platform compatibility over stylistic nits
- Report findings with severity (
high,medium,low) and concise remediation steps
Unity-Specific Review Lenses
1. MonoBehaviour Lifecycle
- Proper use of Awake/Start/OnEnable/OnDisable/OnDestroy
- Null checks for components that might be destroyed
- Execution order dependencies documented
- No heavy/blocking work in frame-critical lifecycle methods; move to jobs/coroutines/background work when appropriate
2. Serialization
[SerializeField]for private fields exposed to Inspector[field:SerializeField]for auto-properties- Missing
[System.Serializable]on nested classes - Proper use of
[HideInInspector]vs not serializing at all
3. Performance Red Flags
GameObject.Find()/Transform.Find()in Update- Allocations in hot paths (string concatenation, LINQ, boxing)
- Missing object pooling for frequently spawned objects
- Heavy physics queries every frame
- Reflection usage in runtime code
Awaitablecontinuations doing heavy synchronous work on completion paths
4. Memory & Resources
- Unsubscribed events (memory leaks)
- Static events without cleanup
- Missing
[RuntimeInitializeOnLoadMethod]for static state reset - Resources not properly disposed
5. Platform Compatibility
- Platform-specific code properly wrapped in
#ifdirectives - IL2CPP compatibility (no problematic reflection)
- API compatibility with target Unity version
- Async primitive compatibility with target Unity/UTF versions (
Awaitablerequires Unity2023.1+or6+)
6. Editor vs Runtime
- Editor code properly wrapped in
#if UNITY_EDITOR - No Editor-only types in runtime assemblies
- Proper assembly definition separation
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.
- 20d ago Changed · -15 lines fd1b9168ba52
- 1mo ago First seen · 125 lines · 34 tokens per session scan A fd5ee6e54291
unity-reviewer is an agent published in the GitHub repository DmitriyYukhanov/claude-plugins (8 stars, last pushed 9d ago), licensed MIT. It adds 34 tokens to every session and 964 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 2026-08-31.
Other agents, from other repositories
pygame-architect
Pygame architecture specialist. Validates game-loop discipline, scene/entity separation, asset loading lifecycle, event-handling boundaries, and frame-time budget. Dispatch when touching the main loop, scenes, entities, or input handling.
unity-architect
Unity + C# architecture specialist. Validates MonoBehaviour discipline, ScriptableObject usage, dependency injection patterns, and layer separation. Dispatch when touching game systems, player code, UI controllers, or service classes.
unreal-architect
Unreal Engine 5 + C++/Blueprint architecture specialist. Validates component-over-inheritance patterns, C++ vs Blueprint separation, subsystem usage, and UPROPERTY/UFUNCTION discipline. Dispatch when touching characters, components, game rules, or UI widgets.
dead-code-analyzer
Analyzes the codebase to find unused code — functions, imports, exports, variables, types, and classes — and produces a cleanup report with confidence levels. Never auto-deletes; reports findings for user review. Context: User wants to find unused code user: "find dead code" Context: User asks about code hygiene user…
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
code-formatter
Expert code formatter and linter specialist. Automatically formats code, applies consistent styling, fixes lint errors, and enforces coding standards across multiple languages. Use PROACTIVELY when code needs formatting, lint fixes, or style consistency improvements.