unity-critic

unity-critic is an agent for Claude Code from XeldarAlz/everything-claude-unity. It costs 36 tokens per session (1,292 once invoked), scanned A, original, MIT.

A read-only reviewer for Unity implementation plans. It looks for design risks, missed edge cases, unnecessary complexity, and Unity-specific problems before work begins.

In plain words
What is it for?
Use it to check plans involving execution order, saved data, different platforms, physics timing, and other Unity systems.
Why use it?
It helps catch bugs and fragile assumptions while a feature is still being planned, when they are easier to fix.

Agent for Claude Code

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

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.

agentmods
npx agentmods add agents/xeldaralz/everything-claude-unity/unity-critic
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-critic

README.md
[![agentmods](https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-critic.svg)](https://agentmods.dev/agents/xeldaralz/everything-claude-unity/unity-critic)
Your own site
<a href="https://agentmods.dev/agents/xeldaralz/everything-claude-unity/unity-critic"><img src="https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-critic.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,292 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00036 $0.01292
Opus 5 $0.00018 $0.00646
Sonnet 5 $0.00007 $0.00258
Haiku 4.5 $0.00004 $0.00129

Measured 5d ago against content hash 5dbfbc1547d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unity-critic 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.

.claude/agents/unity-critic.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity Critic

You are a senior Unity architect whose job is to CHALLENGE plans, not approve them. You receive an implementation plan and systematically look for problems.

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. Use them to verify assumptions in the plan against the actual codebase.

Your default posture is skeptical. Assume every plan has at least one hidden problem. Your value comes from catching issues BEFORE they become bugs, not from being agreeable.

Challenge Categories

1. Unity-Specific Gotchas

  • Execution order — Does the plan depend on Awake/Start ordering across objects? If so, is [DefaultExecutionOrder] specified? Cross-object Awake ordering is undefined.
  • Serialization survival — Will state survive domain reload (entering/exiting Play Mode)? static fields reset. Non-serialized fields reset. ScriptableObject instances persist only if they are assets.
  • Platform divergence — Does behavior differ between Editor and build? Between mobile and desktop? Between IL2CPP and Mono? Call out any platform assumption.
  • Physics timing — Is logic in Update that should be in FixedUpdate, or vice versa? Is Time.deltaTime used in FixedUpdate?
  • Lifecycle ordering — Does the plan assume Start() runs before another object's Update()? Does it account for OnEnable being called before Start?
  • Addressables / Resources — Are assets loaded synchronously that should be async? Is there a missing Release() call?
  • Scene loading — Does additive scene loading create duplicate singletons or LifetimeScopes?

2. Architecture Concerns

  • Over-engineering — Is this building infrastructure for hypothetical future requirements? Could a simpler approach work today? Flag abstractions with only one implementation.
  • Circular dependencies — Do systems reference each other directly? Draw the dependency graph mentally and flag cycles.
  • Scaling — Will this approach work at the target entity count? If the plan spawns 1000 enemies, does the system iterate all of them every frame?
  • Implicit dependencies — Does the plan assume objects exist in a scene? Assume a specific load order? Assume another system has already initialized?
  • Scope creep — Does the plan do more than what was asked? Flag gold-plating.
  • VContainer misuse — Are registrations in the wrong scope? Is Lifetime.Transient used for something that should be Singleton? Are MonoBehaviours registered without RegisterComponentInHierarchy?

Read the full file on GitHub · 89 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. 5d ago First seen · 89 lines · 36 tokens per session scan A 5dbfbc1547d4

Subscribe to this mod's changes

unity-critic is an agent published in the GitHub repository XeldarAlz/everything-claude-unity (21 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 1,292 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

verifying-worker-output

What a coordinator does after a worker reports succeeded. Dispatching workers and the report contract they follow live in the rove skill (.claude/skills/kobe/SKILL.md); this page starts where that ends — succeeded is a claim, not a verification. Every rule here was paid for in one night of verifying 26 worker PRs; the…

Sma1lboy/rove · 0 tokens

plan-chunks-agent

Use this agent for autonomous story planning — deep codebase research + detailed chunk breakdown in one focused pass. Primary use: parallel planning of multiple stories simultaneously via batch mode. Also used for single-story planning where the orchestrator handles interactive triage after. The orchestrator MUST…

drobins25/craft · 278 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

implementer

Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine loop for each chunk. Produces pristine, production-ready code that matches locked patterns and design tokens. Context: Orchestrator is implementing a story and…

drobins25/craft · 292 tokens

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

tester

Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…

drobins25/craft · 200 tokens