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 IdoCohen560/claude-unity-game-studio --skill uw-network-setupgit 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/uw-network-setup)<a href="https://agentmods.dev/skills/idocohen560/claude-unity-game-studio/uw-network-setup"><img src="https://agentmods.dev/badge/skills/idocohen560/claude-unity-game-studio/uw-network-setup.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 | $0.00149 | $0.01976 |
| Opus 5 | $0.00075 | $0.00988 |
| Sonnet 5 | $0.00030 | $0.00395 |
| Haiku 4.5 | $0.00015 | $0.00198 |
Grade A, and why
uw-network-setup 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 4d 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 uw-network-setup — 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Network Setup
Generate networking code adapted to the project's chosen package.
Before You Start
- Read
docs/ProjectConfig.yamlfor:networking— the package name ("ngo","mirror","photon", or"none"). If"none", stop — do not generate networking code.architecture_pattern—"so-first"or"di-first"(affects how network services are wired).mcp.unity_mcp— iftrue, callrefresh_unityafter creating files.
- Read
docs/TDD_Template.mdfor the authority matrix (who owns what data). - Read
docs/CODING_STANDARDS.mdfor async patterns (Awaitable+CancellationToken) and class structure. - Read
docs/NAMING_CONVENTIONS.mdfor file/class naming.
Package Quick Reference
Each package has a detailed reference file. Read the relevant one before generating code:
- NGO (Netcode for GameObjects): references/ngo.md — Unity's first-party solution. Uses
NetworkVariable,[Rpc]attributes. - Mirror: references/mirror.md — Community open-source. Uses
[SyncVar],[Command]/[ClientRpc]. - Photon (PUN2/Fusion): references/photon.md — Cloud-hosted. Uses
IPunObservable,[PunRPC].
Core Patterns (All Packages)
State Synchronization
Every package has a mechanism for syncing state from server/host to clients. The pattern is the same — only the syntax differs.
| Package | Sync Mechanism | Change Callback | Example |
|---|---|---|---|
| NGO | NetworkVariable<T> |
.OnValueChanged += handler |
_health.OnValueChanged += OnHealthChanged; |
| Mirror | [SyncVar(hook = nameof(...))] |
Hook method | [SyncVar(hook = nameof(OnHealthChanged))] |
| Photon | IPunObservable |
OnPhotonSerializeView |
Manual read/write in serialize callback |
Remote Procedure Calls (RPCs)
RPCs let clients request actions on the server, or the server push updates to clients.
NGO:
[Rpc(SendTo.Server)]
public void RequestDamageServerRpc(int amount)
{
// Runs on server — validate before applying
if (amount < 0 || amount > MAX_DAMAGE) return;
_health.Value = Mathf.Max(0, _health.Value - amount);
}
[Rpc(SendTo.ClientsAndHost)]
public void PlayHitEffectClientRpc()
{
// Runs on all clients — visual/audio only, no game state
}
What ships with it
3 files 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.
- 4d ago First seen · 197 lines · 149 tokens per session scan A 26f062d18f8b
uw-network-setup is a skill published in the GitHub repository IdoCohen560/claude-unity-game-studio (18 stars, last pushed 2mo ago), licensed MIT. It adds 149 tokens to every session and 1,976 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to uw-network-setup, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
api-design
Designs REST, GraphQL, and gRPC APIs (OpenAPI/schema/proto output) and reviews existing APIs for consistency, best practices, and breaking change risks.
architecture-design
Designs new systems from requirements: C4 model diagrams, service boundaries, API contracts, data design, failure modes, and cross-cutting concerns.
cloudflare-durable-objects
Cloudflare Durable Objects for stateful coordination and real-time apps. Use for chat, multiplayer games, WebSocket hibernation, or encountering class export, migration, alarm errors.
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".
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…