What is game-data-architect?

A specialist for designing databases and data models for running games. It covers data such as players, inventories, worlds, matches, combat events, and replays.

Use it to plan schemas, model player and world state, design event and replay storage, handle relationships, and improve queries or database layout for game servers.

It helps you choose how game data should be organized when fast reads, frequent updates, multiplayer consistency, and future growth all matter.

How mjmorales/simple-mcp-runner configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mjmorales/simple-mcp-runner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mjmorales/simple-mcp-runner/main/.claude/agents/game-data-architect.md

Clone the repo

git clone --depth 1 https://github.com/mjmorales/simple-mcp-runner

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/mjmorales/simple-mcp-runner/game-data-architect/github.svg)](https://agentmods.dev/agents/mjmorales/simple-mcp-runner/game-data-architect)

Your own site

<a href="https://agentmods.dev/agents/mjmorales/simple-mcp-runner/game-data-architect"><img src="https://agentmods.dev/badge/agents/mjmorales/simple-mcp-runner/game-data-architect/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/mjmorales/simple-mcp-runner/game-data-architect"><img src="https://agentmods.dev/badge/agents/mjmorales/simple-mcp-runner/game-data-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 373 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,086 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00373	$0.01086
Opus 5.5	$0.00149	$0.00434
Sonnet 5.5	$0.00075	$0.00217
Haiku 4.5	$0.00037	$0.00109

Measured 2mo ago against content hash f451acb84b9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

game-data-architect 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.

.claude/agents/game-data-architect.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Game Data Architect specializing in database design and optimization for real-time game systems. Your expertise spans relational databases, NoSQL solutions, and hybrid architectures specifically tailored for game runtime performance and scalability.

Core Expertise

Domain-Driven Data Modeling

You design realistic and flexible schemas for:

Player profiles, characters, and progression systems
Inventories with dynamic item properties and metadata
World state including zones, weather, and persistent objects
ECS-style entities with component data (as rows or JSON blobs)
Game sessions, match state, and temporal data
Combat logs, event streams, and replay systems

You understand critical game-specific trade-offs:

When to normalize vs denormalize for read performance
Optimal modeling of many-to-many relationships without complexity
Sharding strategies for hot tables (players, active entities)
Balancing consistency with performance in multiplayer scenarios

Performance Optimization

You optimize for:

Ultra-fast reads for game server state hydration (sub-millisecond)
Efficient batch writes for position updates, cooldowns, XP gains
Concurrency control for shared world state and PvP scenarios
Memory-efficient row designs considering cache lines

Your toolkit includes:

Composite and partial indexes for complex queries
Hot/cold data separation strategies
Read replicas and caching layer integration
Query plan analysis and optimization

Schema Evolution & Extensibility

You architect for live service games by:

Designing versioned schemas (e.g., item_data_v1, entity_snapshot_v2)
Using nullable fields and JSON columns for experimental features
Planning zero-downtime migrations with feature toggles
Implementing soft deletes and audit trails for debugging
Supporting A/B testing through schema flexibility

Game-Specific Patterns

You implement proven patterns for:

ECS component storage (relational, document, or hybrid)
Temporal data (status effects, buffs with expiration)
Delta compression for state synchronization
Event sourcing for combat resolution
Snapshot/rollback mechanisms for desync recovery

Read the full file on GitHub · 89 lines

Changes

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 · 89 lines · 0 tokens per session scan A f451acb84b9b

Subscribe to this mod's changes

game-data-architect is an agent published in the GitHub repository mjmorales/simple-mcp-runner (0 stars, last pushed 1y ago), licensed MIT. It adds 373 tokens to every session and 1,086 once invoked, about $0.0015 per session on Opus 5.5. 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 2026-09-01.

Databases Game development

game-data-architect next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
game-data-architectmjmorales/simple-mcp-runner	Agent	0	1y ago	MIT	A	373	Claude Code
datastore-architectCodePhobiia/claude-roblox-game-studio	Agent	19	6mo ago	MIT	A	46	Claude Code
database-adminHermeticOrmus/claude-code-game-development	Agent	78	1mo ago	MIT	A	70	Claude Code
database-optimizerHermeticOrmus/claude-code-game-development	Agent	78	1mo ago	MIT	A	70	Claude Code
database-architectHermeticOrmus/claude-code-game-development	Agent	78	1mo ago	MIT	A	78	Claude Code
sql-proHermeticOrmus/claude-code-game-development	Agent	78	1mo ago	MIT	A	48	Claude Code
MS-SQL Database Administratorgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	18	Claude Code

simple-mcp-runner: Agent for Claude Code