open-mmorpg: Agent for Claude Code

.claude/agents/db.md

db is an agent for Claude Code from developerz-ai/open-mmorpg. It costs 83 tokens per session (703 once invoked), scanned A, original, MIT.

A specialist coding agent for the database and persistence layer of an online game. It handles durable ownership records in YugabyteDB, a distributed SQL database, and temporary data in Dragonfly, an in-memory data store.

In plain words
What is it for?
Use it for database schema and migration work, persistence code, the in-game ledger, idempotency, and protections against duplicate ownership or item grants.
Why use it?
It keeps important writes in one controlled database transaction instead of allowing game code or a cache to create inconsistent ownership or duplicate-item records. It also separates permanent data from temporary cached data.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is developerz-ai/open-mmorpg's own configuration. It tells Claude Code how to work on open-mmorpg itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything open-mmorpg configures →

Reuse

Borrowing it

Nothing to install: this file belongs to developerz-ai/open-mmorpg. 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/developerz-ai/open-mmorpg/main/.claude/agents/db.md
Clone the repo
git clone --depth 1 https://github.com/developerz-ai/open-mmorpg

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.

agentmods badge for db

README.md
[![agentmods](https://agentmods.dev/badge/agents/developerz-ai/open-mmorpg/db/github.svg)](https://agentmods.dev/agents/developerz-ai/open-mmorpg/db)
Your own site
<a href="https://agentmods.dev/agents/developerz-ai/open-mmorpg/db"><img src="https://agentmods.dev/badge/agents/developerz-ai/open-mmorpg/db/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.

agentmods 80×15 button for db

Your own site · 80×15
<a href="https://agentmods.dev/agents/developerz-ai/open-mmorpg/db"><img src="https://agentmods.dev/badge/agents/developerz-ai/open-mmorpg/db.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 703 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.00703
Opus 5.5 $0.00033 $0.00281
Sonnet 5.5 $0.00017 $0.00141
Haiku 4.5 $0.00008 $0.00070

Measured 15d ago against content hash c9e019dfe57f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

db 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 15d 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/db.md · 28 lines

How it starts

The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Database & Persistence specialist for Open-MMORPG. You own track 10: the one place ownership is written, and the anti-dupe guarantees that make the dupe path fail to compile.

Read before non-trivial work

  • Your track: docs/mvp/v1/10-database.md (PR batches D1–D8, Definition of Done).
  • Your specs: docs/specs/game-server/persistence/README.md, docs/specs/game-server/economy/README.md (ledger); docs/architecture/04-data-and-consistency.md, docs/initial-idea/04-data-storage.md.
  • The rules: root CLAUDE.md, docs/mvp/v1/01-workflow-and-parallelization.md, gold standards stack/rust-apis.md.
  • Use CodeGraph before grep when .codegraph/ exists.

Own / don't own

  • Own: crates/persistence (Yugabyte via sqlx, migrations, the ownership txn API, the ledger), crates/cache (Dragonfly, ephemeral/broadcast only), the DB schema.
  • Don't own: who calls the txn API (→ server), how state is shown (→ webclient reads worldsvc projections). You provide the safe write path; others use it.

Non-negotiable rules (this track is the #1 anti-dupe boundary)

  1. Ownership writes → one YugabyteDB transaction. Never through cache or bus. This is the single most important rule in the repo.
  2. crates/cache has no ownership-write API — enforce with types so the dupe path won't compile. Prove it with a "does-not-compile" test.
  3. Idempotent by key — every mutating op takes an idempotency key; retries never double-apply.
  4. Double-entry ledger — every value move is append-only and reconcilable; balances derive from the ledger.
  5. No secrets in errors or logs; typed errors (thiserror) with stable client codes.
  6. Async on the request/tick path — tokio + sqlx, never blocking or std::sync::Mutex.

How you work

Ship one fat, green PR per batch (small ≤300-LOC files, tests included — especially concurrent-contention/property tests that prove no dupe). No unwrap/expect off main/tests. Migrations run clean on a fresh DB in CI. bin/check green; land via the merge loop. Write the operator DB runbook (backup/restore/scale) in docs/operations/ as you go. Refuse and correct any design that writes ownership outside a Yugabyte txn or gives cache a persistence API.

Read the full file on GitHub · 28 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.

  1. 15d ago First seen · 28 lines · 83 tokens per session scan A c9e019dfe57f

Subscribe to this mod's changes

db is an agent published in the GitHub repository developerz-ai/open-mmorpg (12 stars, last pushed 6d ago), licensed MIT. It adds 83 tokens to every session and 703 once invoked, about $0.0003 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 2026-10-02.

Related

Other agents, from other repositories

ax-schema-reviewer

Reviews ax SurrealDB schema + ingest-stage changes for the registration gotchas that fail CI.

Necmttn/ax · 24 tokens

database-admin

Expert database administrator specializing in modern cloud databases, automation, and reliability engineering. Masters AWS/Azure/GCP database services, Infrastructure as Code, high availability, disaster recovery, performance optimization, and compliance. Handles multi-cloud strategies, container databases, and cost…

HermeticOrmus/claude-code-game-development · 70 tokens

database-architect

Expert database architect specializing in data layer design from scratch, technology selection, schema modeling, and scalable database architectures. Masters SQL/NoSQL/TimeSeries database selection, normalization strategies, migration planning, and performance-first design. Handles both greenfield architectures and…

HermeticOrmus/claude-code-game-development · 78 tokens

sql-pro

Master modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance tuning, data modeling, and hybrid analytical systems. Use PROACTIVELY for database optimization or complex analysis.

HermeticOrmus/claude-code-game-development · 48 tokens

godot-engineer

Use this agent when working on a Godot 4 project: designing Node trees and scenes, choosing signals or direct calls, handling shared Resources, picking physics bodies, writing typed GDScript or C#, or testing with GUT. It writes idiomatic Godot rather than Unity patterns translated over, and flags engine gotchas…

HermeticOrmus/LibreGameDev-Claude-Code · 74 tokens

network-engineer

Use this agent when adding or debugging multiplayer: choosing rollback, lockstep, or an authoritative server, client prediction and reconciliation, lag compensation for hit detection, bandwidth budgets, NAT traversal, or Godot and Unity netcode APIs. It picks the model that fits the genre and diagnoses rubber-banding…

HermeticOrmus/LibreGameDev-Claude-Code · 67 tokens