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 match3git 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/match3)<a href="https://agentmods.dev/skills/xeldaralz/everything-claude-unity/match3"><img src="https://agentmods.dev/badge/skills/xeldaralz/everything-claude-unity/match3/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/match3"><img src="https://agentmods.dev/badge/skills/xeldaralz/everything-claude-unity/match3.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 | $0.00034 | $0.01862 |
| Opus 5 | $0.00017 | $0.00931 |
| Sonnet 5 | $0.00007 | $0.00372 |
| Haiku 4.5 | $0.00003 | $0.00186 |
Grade A, and why
match3 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Match-3 Puzzle Patterns
Grid System
public sealed class Board : MonoBehaviour
{
[SerializeField] private int _width = 7;
[SerializeField] private int _height = 9;
[SerializeField] private float _cellSize = 1f;
[SerializeField] private TileDefinition[] _tileTypes;
private Tile[,] _grid;
private void Awake()
{
_grid = new Tile[_width, _height];
}
public Vector3 GridToWorld(int x, int y)
{
float offsetX = (_width - 1) * 0.5f;
float offsetY = (_height - 1) * 0.5f;
return new Vector3((x - offsetX) * _cellSize, (y - offsetY) * _cellSize, 0f);
}
public bool IsValidPosition(int x, int y)
{
return x >= 0 && x < _width && y >= 0 && y < _height;
}
public Tile GetTile(int x, int y)
{
if (!IsValidPosition(x, y)) return null;
return _grid[x, y];
}
public void SetTile(int x, int y, Tile tile)
{
_grid[x, y] = tile;
if (tile != null)
{
tile.GridX = x;
tile.GridY = y;
}
}
}
Tile Definition
[CreateAssetMenu(menuName = "Match3/Tile Definition")]
public sealed class TileDefinition : ScriptableObject
{
[SerializeField] private string _tileId;
[SerializeField] private Sprite _sprite;
[SerializeField] private Color _color = Color.white;
[SerializeField] private TileType _type = TileType.Normal;
public string TileId => _tileId;
public Sprite Sprite => _sprite;
public Color Color => _color;
public TileType Type => _type;
}
public enum TileType
{
Normal,
StripedHorizontal,
StripedVertical,
Wrapped,
ColorBomb,
Blocker,
Ice,
Chain
}
Swap & Match Detection
public sealed class MatchDetector
{
private readonly Board _board;
private readonly List<MatchResult> _matchBuffer = new(16);
public MatchDetector(Board board) { _board = board; }
public List<MatchResult> FindAllMatches()
{
_matchBuffer.Clear();
FindHorizontalMatches();
FindVerticalMatches();
return _matchBuffer;
}
private void FindHorizontalMatches()
{
for (int y = 0; y < _board.Height; y++)
{
int matchStart = 0;
for (int x = 1; x <= _board.Width; x++)
{
bool matches = x < _board.Width &&
_board.GetTile(x, y) != null &&
_board.GetTile(matchStart, y) != null &&
_board.GetTile(x, y).Definition.TileId ==
_board.GetTile(matchStart, y).Definition.TileId;
if (!matches)
{
int length = x - matchStart;
if (length >= 3)
{
MatchResult match = new MatchResult();
match.Direction = MatchDirection.Horizontal;
for (int mx = matchStart; mx < x; mx++)
{
match.Tiles.Add(_board.GetTile(mx, y));
}
_matchBuffer.Add(match);
}
matchStart = x;
}
}
}
}
private void FindVerticalMatches()
{
for (int x = 0; x < _board.Width; x++)
{
int matchStart = 0;
for (int y = 1; y <= _board.Height; y++)
{
bool matches = y < _board.Height &&
_board.GetTile(x, y) != null &&
_board.GetTile(x, matchStart) != null &&
_board.GetTile(x, y).Definition.TileId ==
_board.GetTile(x, matchStart).Definition.TileId;
if (!matches)
{
int length = y - matchStart;
if (length >= 3)
{
MatchResult match = new MatchResult();
match.Direction = MatchDirection.Vertical;
for (int my = matchStart; my < y; my++)
{
match.Tiles.Add(_board.GetTile(x, my));
}
_matchBuffer.Add(match);
}
matchStart = y;
}
}
}
}
}
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 · 283 lines · 34 tokens per session scan A c04d5ed19b34
match3 is a skill published in the GitHub repository XeldarAlz/everything-claude-unity (23 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,862 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.