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-game-loopnpx skills add IdoCohen560/claude-unity-game-studio --skill unity-game-loopgit 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-game-loop)<a href="https://agentmods.dev/skills/idocohen560/claude-unity-game-studio/unity-game-loop"><img src="https://agentmods.dev/badge/skills/idocohen560/claude-unity-game-studio/unity-game-loop.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 | $0.00073 | $0.06465 |
| Opus 5 | $0.00036 | $0.03232 |
| Sonnet 5 | $0.00015 | $0.01293 |
| Haiku 4.5 | $0.00007 | $0.00647 |
Grade A, and why
unity-game-loop 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.
This is a copy
100% identical to unity-game-loop — 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 — 795 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Loop & Progression -- Design Translation Patterns
Prerequisite skills:
unity-state-machines(session FSM),unity-game-architecture(events, Service Locator, bootstrap),unity-data-driven(SO configs for difficulty/pacing)
Claude's most common gameplay failure mode is building features in isolation without a unifying loop structure. It will create movement, inventory, combat, and crafting systems that all work independently but never form a cohesive game. The result is a playable sandbox with no progression, no session boundaries, no win/lose conditions, and no hooks for designers to tune pacing or difficulty. These patterns translate design intent ("the player explores, collects, crafts, then survives the night") into code architecture that enforces phase ordering, tracks session state, and exposes tuning surfaces to designers.
PATTERN: Core Loop Scaffolding
DESIGN INTENT: Designer describes the game as "explore, collect, craft, survive night" -- needs a code skeleton that enforces this cycle with extensible phases that run in order.
WRONG (Claude default):
// Systems built independently with no phase concept -- everything runs simultaneously.
// ExplorationManager, InventoryManager, CraftingManager, CombatManager all live in the scene
// and run their Update loops at the same time. There is no concept of "it is now the crafting
// phase" or "exploration has ended." The game is a flat sandbox.
public class GameManager : MonoBehaviour
{
[SerializeField] private ExplorationManager _exploration;
[SerializeField] private InventoryManager _inventory;
[SerializeField] private CombatManager _combat;
private void Start()
{
_exploration.Enable();
_inventory.Enable();
_combat.Enable(); // all systems active from frame 1
}
}
RIGHT:
// GameLoopController manages phase transitions via IGamePhase interface.
// Each phase gets Enter/Tick/Exit. Phases are configured as SO assets.
// Only one phase is active at a time, enforcing the designer's intended cycle.
public interface IGamePhase
{
/// <summary>Name shown in debug UI and logs.</summary>
string PhaseName { get; }
/// <summary>Called when this phase becomes active. Load assets, enable systems.</summary>
Awaitable EnterAsync(CancellationToken ct);
/// <summary>Called every frame while this phase is active.</summary>
void Tick(float deltaTime);
/// <summary>Called when transitioning away. Cleanup, disable systems.</summary>
Awaitable ExitAsync(CancellationToken ct);
}
[CreateAssetMenu(menuName = "Game Loop/Phase Config")]
public class GamePhaseConfig : ScriptableObject
{
[Tooltip("Display name for this phase")]
public string phaseName;
[Tooltip("Assembly-qualified type name of the IGamePhase implementation")]
public string phaseTypeName;
[Tooltip("Duration in seconds, 0 = phase decides when to end")]
public float maxDuration;
}
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 · 795 lines · 73 tokens per session scan A 9622d509c57c
unity-game-loop is a skill published in the GitHub repository IdoCohen560/claude-unity-game-studio (17 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 6,465 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to unity-game-loop, 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-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.
session-audit
Audit Claude Code session logs (/.claude/projects) for token waste and produce a ranked, attributed efficiency report (habit / skillfile / config). Use when the user asks to audit session efficiency, analyze token waste or cost blowups, review Claude Code usage cost, or asks "where are my tokens going".