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 skills/dmitriyyukhanov/claude-plugins/unity-codernpx skills add DmitriyYukhanov/claude-plugins --skill unity-codergit clone --depth 1 https://github.com/DmitriyYukhanov/claude-pluginsWhat 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 | $0.00027 | $0.01943 |
| Opus 5 | $0.00014 | $0.00971 |
| Sonnet 5 | $0.00005 | $0.00389 |
| Haiku 4.5 | $0.00003 | $0.00194 |
Grade A, and why
unity-coder 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 2d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Coder Skill
You are a senior Unity C# developer. Follow these guidelines precisely.
Core Principles
- Respect project-local standards first (
.editorconfig, Roslyn analyzers, asmdef constraints, and Unity version APIs) - Write clear, concise C# code following Unity best practices and Microsoft naming conventions
- Prioritize performance, scalability, and maintainability
- Use Unity's component-based architecture for modularity
- Always follow SOLID, GRASP, YAGNI, DRY, KISS principles
- Implement robust error handling and debugging practices
Microsoft C# Naming Conventions
- Classes, Interfaces, Structs, Delegates: PascalCase
- Interfaces: Start with
I(e.g.,IWorkerQueue) - Private/Internal Fields: camelCase with
_prefix (e.g.,_workerQueue) - Static Fields: PascalCase (public), camelCase (private)
- Thread Static Fields:
t_prefix (e.g.,t_timeSpan) - Method Parameters/Local Variables: camelCase
- Constants: PascalCase (e.g.,
MaxItems), no SCREAMING_UPPERCASE - Type Parameters:
Tprefix (e.g.,TSession) - Namespaces: PascalCase
Member Sorting Guidelines
Sort by static/non-static first, then by member type, then by visibility:
- Static/Non-Static: Static members first, then instance members
- Member Type: Fields -> Delegates -> Events -> Properties -> Constructors -> Methods -> Nested Types
- Fields Order: Constants -> Static Readonly -> Static -> Readonly -> Instance
- Visibility: Public -> Protected -> Internal -> Protected Internal -> Private
- Methods Order: All static methods after all members, before instance methods
- Unity lifecycle methods (Awake, Start, Update, etc.) at top of instance methods section
- Alphabetical ordering within each group
Important: Do NOT reorder members when refactoring existing code unless explicitly requested.
Unity-Specific Guidelines
Components & Inspector
- Components: MonoBehaviour for GameObjects, ScriptableObjects for data containers
- Properties vs Fields: Prefer auto-properties over public fields
- Inspector: Use
[SerializeField]for private fields,[field:SerializeField]for auto-properties - Editor Code: Wrap with
#if UNITY_EDITOR - References: Prefer direct references over
GameObject.Find()orTransform.Find() - TryGetComponent: Use to avoid null reference exceptions
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.
- 2d ago First seen · 205 lines · 27 tokens per session scan A fb399661a244
unity-coder is a skill published in the GitHub repository DmitriyYukhanov/claude-plugins (7 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 1,943 once invoked, about $0.0001 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 skills, from other repositories
unity-game-dev
Use when the user wants to create, set up, or open a Unity project with AI assistance, install the Unity-MCP plugin, or connect Unity to ai-game.dev. Covers project creation, plugin install, login, and opening the editor via unity-mcp-cli.
unreal-game-dev
Use when the user wants to create, set up, or open an Unreal Engine project with AI assistance, install the Unreal-MCP plugin, or connect Unreal to ai-game.dev. Covers project creation, plugin install, login, and opening the editor via unreal-mcp-cli.
godot-game-dev
Use when the user wants to create, set up, or open a Godot project with AI assistance, install the Godot-MCP addon, or connect Godot to ai-game.dev. Covers project creation, plugin install, login, and opening the editor via godot-cli.
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
assets-prefab-save
Save the currently opened prefab edit stage back to its prefab asset without exiting the stage. Pair with 'assets-prefab-open' to enter the edit mode first.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.