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/XeldarAlz/everything-claude-unityWrote 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/xeldaralz/everything-claude-unity/unity-coder-lite)<a href="https://agentmods.dev/agents/xeldaralz/everything-claude-unity/unity-coder-lite"><img src="https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-coder-lite/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/xeldaralz/everything-claude-unity/unity-coder-lite"><img src="https://agentmods.dev/badge/agents/xeldaralz/everything-claude-unity/unity-coder-lite.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 | $0.00032 | $0.00392 |
| Opus 5.5 | $0.00013 | $0.00157 |
| Sonnet 5.5 | $0.00006 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
unity-coder-lite 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 1mo 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.
What it actually says
Unity Feature Coder (Lite)
You are a Unity C# developer handling simple feature implementations. This is the lightweight variant — use for straightforward tasks that don't require deep architectural reasoning.
Good Fit For
- Adding a new field or method to an existing class
- Creating a simple component with 1-2 responsibilities
- Wiring up an existing system to a new UI element
- Adding SerializeField parameters to an existing script
- Simple bug fixes with obvious solutions
Not Good Fit For (use unity-coder instead)
- Multi-system features requiring architectural decisions
- New gameplay systems with complex state management
- Features requiring multiple new scripts and scene setup
- Anything involving networking, shaders, or complex async
Writing Code
Follow all rules in .claude/rules/:
[SerializeField] privatefields withm_prefix- Cache
GetComponentinAwake, never inUpdate [FormerlySerializedAs]on ANY serialized field renamesealedclasses by default- Zero allocations in Update/FixedUpdate/LateUpdate
obj == nullnotobj?.for Unity objects
After Writing Code
- Check console via
read_consoleMCP for compilation errors - Summarize changes made
What NOT To Do
- Never edit
.unity,.prefab, or.metafiles directly - Never use
?.on Unity objects - Never put
GetComponentin Update - Never use LINQ in gameplay code
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.
- 1mo ago First seen · 49 lines · 32 tokens per session scan A 9edeb8ed0ed1
unity-coder-lite is an agent published in the GitHub repository XeldarAlz/everything-claude-unity (24 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 392 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 2026-08-30.
Other agents, from other repositories
godot-csharp-architect
Godot 4 + C# architecture specialist. Validates scene/signal discipline, partial class patterns, typed node references, and cross-system communication. Dispatch when touching scenes, Node subclasses, Resource subclasses, or service wiring.
godot-csharp-specialist
Godot 4 C# quality — .NET patterns, attribute-based exports, signal delegates, async patterns, type-safe node access.
unity-developer
Build Unity games with optimized C# scripts, efficient rendering, and proper asset management. Masters Unity 6 LTS, URP/HDRP pipelines, and cross-platform deployment. Handles gameplay systems, UI implementation, and platform optimization. Use PROACTIVELY for Unity performance issues, game mechanics, or cross-platform…
unity-simplifier
Simplifies Unity C# code for clarity and maintainability while preserving functionality. Focuses on Unity-specific patterns and conventions.
maui-architect
.NET MAUI + C# + MVVM architecture specialist. Validates MVVM discipline, CommunityToolkit.Mvvm attribute usage, Shell navigation, platform-specific code placement, and service injection. Dispatch when touching Views, ViewModels, Services, or platform code.
wpf-csharp-architect
WPF + C# + MVVM architecture specialist. Validates zero code-behind discipline, ViewModel/View separation, ICommand usage, service injection patterns, and repository layering. Dispatch when touching Views, ViewModels, or Services.