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 skills add XeldarAlz/everything-claude-unity --skill puzzlegit 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/skills/xeldaralz/everything-claude-unity/puzzle)<a href="https://agentmods.dev/skills/xeldaralz/everything-claude-unity/puzzle"><img src="https://agentmods.dev/badge/skills/xeldaralz/everything-claude-unity/puzzle/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/skills/xeldaralz/everything-claude-unity/puzzle"><img src="https://agentmods.dev/badge/skills/xeldaralz/everything-claude-unity/puzzle.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 | $0.00033 | $0.01800 |
| Opus 5 | $0.00016 | $0.00900 |
| Sonnet 5 | $0.00007 | $0.00360 |
| Haiku 4.5 | $0.00003 | $0.00180 |
Grade A, and why
puzzle 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 8d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Puzzle Patterns
Undo System (Command Pattern)
public interface IGameCommand
{
void Execute();
void Undo();
}
public sealed class UndoManager
{
private readonly Stack<IGameCommand> _undoStack = new();
private readonly int _maxUndoSteps;
public UndoManager(int maxSteps = 50)
{
_maxUndoSteps = maxSteps;
}
public int UndoCount => _undoStack.Count;
public void Execute(IGameCommand command)
{
command.Execute();
_undoStack.Push(command);
if (_undoStack.Count > _maxUndoSteps)
{
// Trim oldest — would need a different data structure for efficiency
}
}
public bool Undo()
{
if (_undoStack.Count == 0) return false;
IGameCommand command = _undoStack.Pop();
command.Undo();
return true;
}
public void Clear()
{
_undoStack.Clear();
}
}
// Example: move a piece
public sealed class MovePieceCommand : IGameCommand
{
private readonly Piece _piece;
private readonly Vector2Int _fromPos;
private readonly Vector2Int _toPos;
public MovePieceCommand(Piece piece, Vector2Int from, Vector2Int to)
{
_piece = piece;
_fromPos = from;
_toPos = to;
}
public void Execute() { _piece.MoveTo(_toPos); }
public void Undo() { _piece.MoveTo(_fromPos); }
}
Level Pack System
[CreateAssetMenu(menuName = "Puzzle/Level Pack")]
public sealed class LevelPack : ScriptableObject
{
[SerializeField] private string _packId;
[SerializeField] private string _displayName;
[SerializeField] private Sprite _icon;
[SerializeField] private PuzzleLevel[] _levels;
[SerializeField] private bool _isLocked;
[SerializeField] private int _starsToUnlock;
public string PackId => _packId;
public string DisplayName => _displayName;
public IReadOnlyList<PuzzleLevel> Levels => _levels;
public bool IsLocked => _isLocked;
public int StarsToUnlock => _starsToUnlock;
}
[CreateAssetMenu(menuName = "Puzzle/Level")]
public sealed class PuzzleLevel : ScriptableObject
{
[SerializeField] private string _levelId;
[SerializeField] private int _parMoves; // 3 stars if completed in this many moves
[SerializeField] private int _maxMoves; // fail if exceeded (0 = unlimited)
[SerializeField] private float _parTime; // 3 stars if completed in this time
[SerializeField] private TextAsset _levelData; // JSON or custom format
public string LevelId => _levelId;
public int ParMoves => _parMoves;
public int MaxMoves => _maxMoves;
}
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.
- 8d ago First seen · 279 lines · 33 tokens per session scan A 6dedef75ca34
puzzle is a skill published in the GitHub repository XeldarAlz/everything-claude-unity (23 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 1,800 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 2026-09-03.
Other skills, from other repositories
software-ios-native
Guides native iOS with Swift, SwiftUI, UIKit interop, concurrency, and persistence. Use when building or reviewing iPhone/iPad apps after establishing runtime truth.
foundations-queueing-theory
Applies queueing theory (Little's Law, M/M/c, Erlang, Kingman, USL) to capacity and latency decisions. Use when load causes non-linear latency growth or queue overrun risk.
software-android-design
Designs and audits native Android interfaces. Use when reviewing Compose layout, typography, color, motion, or adaptive patterns on a verified emulator build.
software-android-native
Guides native Android development with Kotlin, Jetpack Compose, and Views interop. Use when building, rewriting, or reviewing modern Android apps after establishing runtime truth.
qa-testing-android
Designs Android testing with Espresso, UI Automator, and Compose. Use when planning device matrices, screenshot tests, CI flows, or flake-control workflows.
software-ios-design
Designs and audits native iOS interfaces. Use when reviewing or refining SwiftUI layout, typography, Liquid Glass, navigation, or dashboards on a freshly verified build.