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 bcastelino/agent-skills-kit --skill multiplayergit clone --depth 1 https://github.com/bcastelino/agent-skills-kitWrote 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/bcastelino/agent-skills-kit/multiplayer)<a href="https://agentmods.dev/skills/bcastelino/agent-skills-kit/multiplayer"><img src="https://agentmods.dev/badge/skills/bcastelino/agent-skills-kit/multiplayer/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/bcastelino/agent-skills-kit/multiplayer"><img src="https://agentmods.dev/badge/skills/bcastelino/agent-skills-kit/multiplayer.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 | $0.00015 | $0.00645 |
| Opus 5.5 | $0.00006 | $0.00258 |
| Sonnet 5.5 | $0.00003 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
multiplayer 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 2mo 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
94% identical to multiplayer — 3 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multiplayer Game Development
Networking architecture and synchronization principles.
1. Architecture Selection
Decision Tree
What type of multiplayer?
│
├── Competitive / Real-time
│ └── Dedicated Server (authoritative)
│
├── Cooperative / Casual
│ └── Host-based (one player is server)
│
├── Turn-based
│ └── Client-server (simple)
│
└── Massive (MMO)
└── Distributed servers
Comparison
| Architecture | Latency | Cost | Security |
|---|---|---|---|
| Dedicated | Low | High | Strong |
| P2P | Variable | Low | Weak |
| Host-based | Medium | Low | Medium |
2. Synchronization Principles
State vs Input
| Approach | Sync What | Best For |
|---|---|---|
| State Sync | Game state | Simple, few objects |
| Input Sync | Player inputs | Action games |
| Hybrid | Both | Most games |
Lag Compensation
| Technique | Purpose |
|---|---|
| Prediction | Client predicts server |
| Interpolation | Smooth remote players |
| Reconciliation | Fix mispredictions |
| Lag compensation | Rewind for hit detection |
3. Network Optimization
Bandwidth Reduction
| Technique | Savings |
|---|---|
| Delta compression | Send only changes |
| Quantization | Reduce precision |
| Priority | Important data first |
| Area of interest | Only nearby entities |
Update Rates
| Type | Rate |
|---|---|
| Position | 20-60 Hz |
| Health | On change |
| Inventory | On change |
| Chat | On send |
4. Security Principles
Server Authority
Client: "I hit the enemy"
Server: Validate → did projectile actually hit?
→ was player in valid state?
→ was timing possible?
Anti-Cheat
| Cheat | Prevention |
|---|---|
| Speed hack | Server validates movement |
| Aimbot | Server validates sight line |
| Item dupe | Server owns inventory |
| Wall hack | Don't send hidden data |
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.
- 2mo ago First seen · 132 lines · 15 tokens per session scan A 288efdcded46
multiplayer is a skill published in the GitHub repository bcastelino/agent-skills-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 645 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to multiplayer, differing in 3 lines, and is treated as a copy.
multiplayer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| multiplayerbcastelino/agent-skills-kit | Skill | 2 | 3mo ago | MIT | A | 15 | Claude Code |
| researcherkeli-wen/agy-staff | Skill | 869 | 2d ago | MIT | A | 75 | Claude Code |
| reviewerkeli-wen/agy-staff | Skill | 869 | 2d ago | MIT | B | 94 | Claude Code |
| cloudflare-durable-objectssecondsky/claude-skills | Skill | 248 | 14d ago | MIT | A | 43 | Claude Code |
| dead-code-huntermagic5644/Graph-It-Live | Skill | 63 | yesterday | MIT | A | 165 | Claude Code |
| onboarding-expressmagic5644/Graph-It-Live | Skill | 63 | yesterday | MIT | A | 171 | Claude Code |
| debugging-workflowsCrowdStrike/foundry-skills | Skill | 39 | yesterday | MIT | A | 90 | Claude Code |