unity-reviewer

unity-reviewer is a skill for Claude Code, Codex from TheArcForge/Hades. It costs 39 tokens per session (2,854 once invoked), scanned A, original, MIT.

A review checklist for Unity C# changes, focused on bugs that can break a game at runtime, performance problems, and maintainability. Unity is a game engine, and C# scripts control many of its behaviours and editor tools.

In plain words
What is it for?
Reviewing new or modified Unity MonoBehaviours and editor scripts, tracing their asset and code dependencies, and checking critical, performance, and style risks before completing a feature.
Why use it?
It helps catch problems after scripts are changed, including issues involving events, threads, object lifetimes, and dependent scenes or prefabs. Findings are ordered by severity so runtime-breaking issues receive priority.

Skill for Claude CodeCodex

Part of the hades plugin — 22 skills, 6 commands 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 skills/thearcforge/hades/unity-reviewer
Any agent
npx skills add TheArcForge/Hades --skill unity-reviewer
Clone the repo
git clone --depth 1 https://github.com/TheArcForge/Hades

Made for: Claude Code, Codex.

Or install hades, the plugin that ships this one along with the rest of its 22 skills, 6 commands.

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/skills/thearcforge/hades/unity-reviewer.svg)](https://agentmods.dev/skills/thearcforge/hades/unity-reviewer)
Your own site
<a href="https://agentmods.dev/skills/thearcforge/hades/unity-reviewer"><img src="https://agentmods.dev/badge/skills/thearcforge/hades/unity-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,854 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 $0.00039 $0.02854
Opus 5 $0.00019 $0.01427
Sonnet 5 $0.00008 $0.00571
Haiku 4.5 $0.00004 $0.00285

Measured 5d ago against content hash b99bdf408bb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

ClaudeCodePlugin/skills/unity-reviewer/SKILL.md · 374 lines

How it starts

The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity Code Reviewer

Run through these checks after modifying or creating C# scripts. Organized by severity: Critical first, then Performance, then Style. Fix Critical issues immediately — they will break the game at runtime. Batch Performance and Style issues where convenient.

When to Apply

  • After implementing any new MonoBehaviour or editor script
  • When superpowers:requesting-code-review is active and the changes involve Unity C#
  • When a bug report implicates event handling, threading, or object lifetime
  • Before marking any Unity feature task complete

Project Context Check

Before running the checklist, gather impact context using Hades Graph and memory:

find_references_to("<changed_script_path>")   — returns BOTH asset references (prefabs, scenes) AND C# code references (fields, parameters, constructors, casts, inheritance)
trace_dependencies("<changed_script_path>")   — what the changed script depends on
recall_memory("code review conventions style") — documented team conventions and past decisions

Use these results to:

  • Flag ripple risks (e.g., a change to a base class affects many dependents — find_references_to shows both prefab dependents and C# code dependents)
  • Adjust severity: a performance issue in a script referenced by 40 prefabs is higher priority than one referenced by 1
  • Verify the change aligns with team conventions before marking Style issues as acceptable
  • Do NOT use grep to find references — the graph is authoritative for both asset and code-level dependencies

Decision Framework

Critical (Will Break at Runtime)

CHECK: Missing Event Unsubscription

Wrong (common default):

void OnEnable() {
    GameEvents.OnPlayerDied += HandlePlayerDied;
}
// No OnDisable — listener persists after destroy, causes NullReferenceException

Right:

void OnEnable() {
    GameEvents.OnPlayerDied += HandlePlayerDied;
}
void OnDisable() {
    GameEvents.OnPlayerDied -= HandlePlayerDied;
}

Read the full file on GitHub · 374 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 · 374 lines · 39 tokens per session scan A b99bdf408bb8

Subscribe to this mod's changes

unity-reviewer is a skill published in the GitHub repository TheArcForge/Hades (27 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 2,854 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.