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.
npx agentmods add agents/dmitriyyukhanov/claude-plugins/unity-reviewergit 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.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 | $0.00034 | $0.01098 |
| Opus 5 | $0.00017 | $0.00549 |
| Sonnet 5 | $0.00007 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
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 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Unity-specific code reviewer. Focus on Unity patterns that general code review might miss.
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.
- 5d 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 (7 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,098 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
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
implementation-agent
Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.
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.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
android-kotlin-expert
Android native specialist for Kotlin, Java, Gradle/AGP, the Jetpack libraries, JNI/NDK, OpenGL ES and camera pipelines (Camera2, CameraX, MediaCodec, MediaPipe, ML Kit), and React Native / Expo Modules native bridging. Use when the task touches android/ (.kt, .java, .gradle / .gradle.kts, AndroidManifest.xml…
review-software-architect
Review persona: senior software architect lens for any codebase. Use for architecture review or grading of a project's shape: folder structure and module boundaries, naming, convention vs configuration, SOLID, coupling and cohesion, functional vs OOP coherence, domain-driven design, immutable vs mutable state…