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/idocohen560/claude-unity-game-studio/unity-save-systemnpx skills add IdoCohen560/claude-unity-game-studio --skill unity-save-systemgit clone --depth 1 https://github.com/IdoCohen560/claude-unity-game-studioWrote 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/idocohen560/claude-unity-game-studio/unity-save-system)<a href="https://agentmods.dev/skills/idocohen560/claude-unity-game-studio/unity-save-system"><img src="https://agentmods.dev/badge/skills/idocohen560/claude-unity-game-studio/unity-save-system.svg" alt="Measured on agentmods" 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 | $0.00065 | $0.03634 |
| Opus 5 | $0.00032 | $0.01817 |
| Sonnet 5 | $0.00013 | $0.00727 |
| Haiku 4.5 | $0.00006 | $0.00363 |
Grade B, and why
unity-save-system scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
GOTCHA: `BinaryFormatter` is a security hole -- deserialization can execute arbitrary code. Unity and Microsoft have deprecated it. If you find it in existing code, replace it immediately. `JsonUtility` cannot serialize This is a copy
100% identical to unity-save-system — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save/Load Systems -- Decision Patterns
Prerequisite skills:
unity-lifecycle(OnApplicationPause, OnApplicationQuit, quit sequence),unity-data-driven(JSON serialization, versioning),unity-packages-services(Cloud Save API),unity-async-patterns(BackgroundThreadAsync)
These patterns address the most common save system failure: Claude uses PlayerPrefs for everything, produces brittle serialization with no versioning, and ignores mobile-specific persistence requirements.
PATTERN: Serialization Format Selection
WHEN: Choosing how to serialize save data to disk
DECISION:
- JSON (
JsonUtility) -- Human-readable, debuggable, small save files. No dictionary/polymorphism. Best default for most games. - JSON (Newtonsoft) -- Full JSON features (dictionaries, polymorphism, LINQ). Slightly larger dependency. Best when save data is complex.
- Binary (custom or MessagePack) -- Performance-critical, large saves, anti-cheat (harder to edit). Not human-readable. Best for competitive games or very large worlds.
- BinaryFormatter -- NEVER USE. Security vulnerability (arbitrary code execution on deserialization). Deprecated by Unity and Microsoft.
SCAFFOLD (JSON save/load):
using System.IO;
using UnityEngine;
public static class SaveFileIO
{
public static void SaveJson<T>(T data, string fileName)
{
string path = GetSavePath(fileName);
string json = JsonUtility.ToJson(data, prettyPrint: true);
// Write to temp file first, then rename (atomic write)
string tempPath = path + ".tmp";
File.WriteAllText(tempPath, json);
if (File.Exists(path))
File.Replace(tempPath, path, path + ".bak");
else
File.Move(tempPath, path);
}
public static T LoadJson<T>(string fileName) where T : new()
{
string path = GetSavePath(fileName);
if (!File.Exists(path)) return new T();
string json = File.ReadAllText(path);
return JsonUtility.FromJson<T>(json);
}
public static bool SaveExists(string fileName) =>
File.Exists(GetSavePath(fileName));
public static void DeleteSave(string fileName)
{
string path = GetSavePath(fileName);
if (File.Exists(path)) File.Delete(path);
if (File.Exists(path + ".bak")) File.Delete(path + ".bak");
}
static string GetSavePath(string fileName) =>
Path.Combine(Application.persistentDataPath, fileName);
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 398 lines · 65 tokens per session scan B 5ed497c91af6
unity-save-system is a skill published in the GitHub repository IdoCohen560/claude-unity-game-studio (17 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 3,634 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). It is 100% identical to unity-save-system, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
swarm
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…
memory-loop-setup
Bootstrap the memory loop into any repo or Obsidian vault. Triggers: (1) "set up the memory loop / second brain / warm layer here" or "install this structure in another repo/vault", (2) a new project asking "make the AI remember across sessions and surfaces".
discord-intent-application
Helps write the justification text for Discord Developer Portal privileged intent applications (Message Content, Server Members, Presence) for a specific bot. Takes a plain-text description of the bot's functionality and/or an uploaded/local codebase, screens the bot's features against Discord's known rejection…
plan-architecture
Phase 2 of 5 — collaborative system design plus change-footprint mapping; outputs an ARCH doc for generate-tasks. Use only when the user asks to run Phase 2, plan the architecture, or design the solution — never trigger automatically from a design question.
plan-qa
Post-implementation QA planning — independent of /review (the developer chooses whether to run them sequentially or in parallel), only when the change has a running surface worth driving. Interviews the developer to turn the specs and the diff into an executable QA specification (specs/qa/QA- - .md) that /execute-qa…
review
Phase 5 of 5 — triage-first review orchestrator; dispatches up to 17 domain checks in parallel and compiles one report. Use only when the user asks to run Phase 5 or review a PR, branch, or set of changes — never trigger automatically after writing code.