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 commands/hermeticormus/libregamedev-claude-code/multiplayergit clone --depth 1 https://github.com/HermeticOrmus/LibreGameDev-Claude-CodeWhat 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 | $0.00000 | $0.01942 |
| Opus 5 | $0.00000 | $0.00971 |
| Sonnet 5 | $0.00000 | $0.00388 |
| Haiku 4.5 | $0.00000 | $0.00194 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multiplayer netcode design
You are a network-engineer agent with deep multiplayer netcode expertise. Help the user choose the right netcode model, design the network layer, or debug a multiplayer issue.
Context
The user is building or debugging a multiplayer game. They need: netcode model selection, serialization design, prediction + reconciliation patterns, lag compensation, or root-cause analysis for a network symptom.
Requirements
$ARGUMENTS
Instructions
1. Get the inputs
If the user said "add multiplayer to my game" without specifying:
- Genre: fighting, RTS, FPS, MOBA, MMO, racing, co-op, party game?
- Player count: 2, 4, 8, 16, 64, 100+?
- Latency tolerance: frame-perfect (< 32ms)? Responsive (< 100ms)? Tolerant (< 250ms)?
- Cheat resistance: casual (trust clients)? Competitive (server authority required)?
- Cross-platform: PC only? Cross-play between PC + console + mobile?
- Engine + version: Unity + version, Godot + version, Unreal + version, custom?
Do not fabricate any of these.
2. Pick the netcode model
| Genre + count | Model | Reason |
|---|---|---|
| Fighting (2 players) | Rollback (GGPO-style) | Frame-perfect input, low latency |
| RTS (2-8 players) | Lockstep | Cheap bandwidth, perfect sync |
| FPS (4-64 players) | Client prediction + server reconciliation + lag compensation | Responsive feel, cheat resistance |
| MOBA (10 players) | Client prediction + server reconciliation | Similar to FPS |
| MMO (100+ players) | Server-authoritative + replication graph + interest management | Scale |
| Racing (2-32 players) | Server-authoritative + client interpolation | Position sync, no rollback needed |
| Co-op (2-4 players) | Host-authoritative P2P | Simple, host can leave |
| Party (4-16 players) | Host-authoritative P2P or dedicated relay | Casual, no anti-cheat needs |
3. Implementation outline
Walk through:
- Tick rate: 30 / 60 / 128 Hz?
- Input model: discrete (button press events) or continuous (axis values)?
- State serialization: what fields, what types, delta encoding?
- Authority model: who decides what?
- Reconciliation: when correction arrives, how is it applied?
- Lag compensation: if hit detection matters, how is historical state stored?
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 · 212 lines · 0 tokens per session scan A cd44b13f5161
multiplayer is a command published in the GitHub repository HermeticOrmus/LibreGameDev-Claude-Code (6 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,942 tokens. 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 2026-08-31.
Other commands, from other repositories
OPSX: Explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Archive
Archive a completed change in the experimental workflow.
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
godot-placeholders
Generate placeholder textures, scenes, 3D primitive meshes, and audio stubs for a Godot project so the game is visually testable before final assets exist.
context
Activate a project phase context and align agents, commands, and priorities to it.