unity-reviewer

unity-reviewer is an agent for Claude Code from XeldarAlz/everything-claude-unity. It costs 45 tokens per session (907 once invoked), scanned A, original, MIT.

A read-only reviewer for Unity C# code. It checks correctness, performance, saved-data safety, architecture, and common Unity lifecycle and runtime mistakes.

In plain words
What is it for?
Use it to inspect scripts for event leaks, unsafe serialization changes, editor-only code in builds, allocation-heavy update loops, naming mismatches, and other Unity-specific problems.
Why use it?
It provides a focused review before changes are applied, helping find issues that ordinary C# review may miss in Unity projects.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the everything-claude-unity plugin — 42 skills, 27 commands, 20 agents, 5 hooks shipped together

Good fit Use it to inspect scripts for event leaks, unsafe serialization changes, editor-only…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xeldaralz/everything-claude-unity/unity-reviewer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/XeldarAlz/everything-claude-unity

Made for: Claude Code.

Or install everything-claude-unity, the plugin that ships this one along with the rest of its 42 skills, 27 commands, 20 agents, 5 hooks.

Wrote 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.

agentmods badge for unity-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-reviewer.svg)](https://agentmods.dev/agents/xeldaralz/everything-claude-unity/unity-reviewer)
Your own site
<a href="https://agentmods.dev/agents/xeldaralz/everything-claude-unity/unity-reviewer"><img src="https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 907 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00907
Opus 5 $0.00023 $0.00453
Sonnet 5 $0.00009 $0.00181
Haiku 4.5 $0.00005 $0.00091

Measured 6d ago against content hash 7f83e615daa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

.claude/agents/unity-reviewer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity Code Reviewer

You are a senior Unity code reviewer. Review code for correctness, performance, and Unity-specific issues.

You are strictly read-only. You may read and analyze code but must NEVER create, modify, or delete files. Your tools are limited to Read, Glob, and Grep. If you identify issues, report them with specific file:line references and suggested fixes — do not attempt to apply fixes yourself. Fixing is the responsibility of the unity-verifier agent.

Review Checklist

Critical (Must Fix)

  • Serialization safety — any renamed [SerializeField] fields without [FormerlySerializedAs]?
  • Unity null check — using ?. or is null on Unity objects instead of == null?
  • Editor in runtimeUnityEditor namespace used without #if UNITY_EDITOR guard?
  • File/class mismatch — MonoBehaviour class name doesn't match file name?
  • DOTween cleanup — tweens killed in OnDestroy? Missing DOTween.Kill(this)?
  • Event leaks — subscribed in OnEnable/Awake but not unsubscribed in OnDisable/OnDestroy?
  • Async void — naked async void instead of async UniTaskVoid or proper error handling?

Performance (Should Fix)

  • GC in Update — allocations in Update/FixedUpdate/LateUpdate?
    • GetComponent<T>() — cache in Awake
    • Camera.main — cache in Awake
    • new List<>, new Dictionary<> — pre-allocate and reuse
    • new WaitForSeconds() — cache as field
    • String concatenation with +
    • LINQ (.Where, .Select, .Any, .FirstOrDefault)
  • CompareTag — using tag == "string" instead of CompareTag()?
  • FindObjectOfType — called in Update? Cache the result.
  • SendMessage — using SendMessage/BroadcastMessage? Use events or direct refs.
  • Physics allocations — using RaycastAll instead of RaycastNonAlloc?
  • Hash cachingAnimator.StringToHash/Shader.PropertyToID called outside static readonly?

Architecture (Consider)

Read the full file on GitHub · 78 lines

Changes

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.

  1. 6d ago First seen · 78 lines · 45 tokens per session scan A 7f83e615daa8

Subscribe to this mod's changes

unity-reviewer is an agent published in the GitHub repository XeldarAlz/everything-claude-unity (21 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 907 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 2026-08-30.

Related

Other agents, from other repositories

style-analyzer

Use this agent after UI implementation or when the user requests design consistency audits. Ensures visual consistency, catches design drift from locked tokens, identifies technical debt in UI code, and guards the integrity of the design language. Context: Multiple UI components were built during the cycle. user…

drobins25/craft · 203 tokens

maze-architect

Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …

drobins25/craft · 157 tokens

verifier

Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…

drobins25/craft · 178 tokens

api-designer

REST and GraphQL API design and review specialist. Use PROACTIVELY when the user creates or modifies API endpoints, defines route handlers, or designs request/response schemas. Trigger on any API-related code changes, endpoint additions, or when reviewing API contracts.

VersoXBT/claude-initial-setup · 56 tokens

code-reviewer

Code quality, security, and maintainability reviewer. Use PROACTIVELY immediately after writing or modifying any code, before commits on modified files, during pull request reviews, and when refactoring existing code. MUST BE USED after implementing a feature or fix, before creating a commit, when reviewing PR diffs…

VersoXBT/claude-initial-setup · 94 tokens

database-reviewer

Database schema design, query optimization, and migration review specialist. Use PROACTIVELY when the user creates or modifies database schemas, writes complex queries, creates migrations, or works with ORMs. Trigger on any database-related code changes or performance issues involving data access.

VersoXBT/claude-initial-setup · 57 tokens