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 rules/thinktidevibes/2d-survival-multiplayer-game/guidegit clone --depth 1 https://github.com/thinktidevibes/2D-Survival-Multiplayer-GameWrote 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/rules/thinktidevibes/2d-survival-multiplayer-game/guide)<a href="https://agentmods.dev/rules/thinktidevibes/2d-survival-multiplayer-game/guide"><img src="https://agentmods.dev/badge/rules/thinktidevibes/2d-survival-multiplayer-game/guide.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 | $0.00000 | $0.01225 |
| Opus 5 | $0.00000 | $0.00613 |
| Sonnet 5 | $0.00000 | $0.00245 |
| Haiku 4.5 | $0.00000 | $0.00122 |
Grade A, and why
guide 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
2D Survival Multiplayer Architecture Guidelines
This rules file specifies the architecture, patterns, and conventions for the Vibe Coding 2D Survival Multiplayer project. AI assistants should use this information to understand the codebase structure and make appropriate recommendations.
Core Architecture
The project implements a client-server architecture with these primary components:
- Backend: SpacetimeDB module written in Rust (
server/) for game logic, state management, and data persistence - Frontend: React/TypeScript client (
client/) for rendering, input handling, and user interface - Communication Layer: SpacetimeDB for real-time synchronization between clients and server
Server Architecture
The backend is organized into these logical components:
- Schema Definitions: Tables defined in
server/lib.rswith#[spacetimedb::table]attributes - Game Logic: Reducer functions (
#[spacetimedb::reducer]) implementing core gameplay mechanics - Module Organization: Functionality separated into domain-specific files (e.g.,
environment.rs,inventory_management.rs)
Key Server Patterns
-
Table Schema Convention:
- Use snake_case for table names (
name = "player") - Mark tables as
publicwhen client access is required - Use
Identitytype for player identification - Implement
Clonefor all table structures
- Use snake_case for table names (
-
Reducer Implementation:
- Use
#[spacetimedb::reducer]and appropriate return types - Implement core game logic in separate modules
- Handle identity connection/disconnection explicitly
- Use
ctx.dbto access database tables
- Use
-
Database Access Pattern:
- Access tables via
ctx.db.table_name() - Use
.identity().find(id),.identity().update(data), etc. for operations - Handle errors with
Result<(), String>return types
- Access tables via
Client Architecture
The client follows these organizational principles:
- Core Components: Main game loop in
App.tsx, rendering inGameScene.tsx - Component Structure: Character system in
Player.tsx, UI inPlayerUI.tsx - State Management: React hooks for local state, SpacetimeDB subscriptions for shared state
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 · 152 lines · 0 tokens per session scan A 013cee65ec07
guide is a cursor rule published in the GitHub repository thinktidevibes/2D-Survival-Multiplayer-Game (11 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,225 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 2026-08-30.
Other cursor rules, from other repositories
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
narrative-writing
游戏叙事写作助手行为约束(game-narrative-mcp).
meta-quest-agentic-tools
Use Meta Quest Agentic Tools for Meta Quest and Horizon OS samples.
00-project-overview
Base project rule — purpose, constraints, and defaults for mcp-5etools.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.