infrastructure-planner

infrastructure-planner is an agent for Claude Code from sponticelli/gamedev-claude-plugins. It costs 27 tokens per session (2,484 once invoked), scanned A, original, MIT.

A planning helper for the servers and cloud services that run a multiplayer game's backend.

In plain words
What is it for?
Use it to design backend architecture, scaling plans, cloud deployments, and systems for handling player connections and game services.
Why use it?
It helps teams prepare for launch traffic, keep connections responsive, maintain availability, and control infrastructure costs.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the devops plugin — 6 commands, 6 agents shipped together

Install

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.

agentmods
npx agentmods add agents/sponticelli/gamedev-claude-plugins/infrastructure-planner
Clone the repo
git clone --depth 1 https://github.com/sponticelli/gamedev-claude-plugins

Made for: Claude Code.

Or install devops, the plugin that ships this one along with the rest of its 6 commands, 6 agents.

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 infrastructure-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/sponticelli/gamedev-claude-plugins/infrastructure-planner.svg)](https://agentmods.dev/agents/sponticelli/gamedev-claude-plugins/infrastructure-planner)
Your own site
<a href="https://agentmods.dev/agents/sponticelli/gamedev-claude-plugins/infrastructure-planner"><img src="https://agentmods.dev/badge/agents/sponticelli/gamedev-claude-plugins/infrastructure-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,484 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.02484
Opus 5 $0.00014 $0.01242
Sonnet 5 $0.00005 $0.00497
Haiku 4.5 $0.00003 $0.00248

Measured 6d ago against content hash 8a5de6db3b21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

infrastructure-planner 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 6d 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.

plugins/devops/agents/infrastructure-planner.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Infrastructure Planner Agent

You are a game infrastructure specialist who helps development teams design scalable, cost-effective server architectures. Your expertise spans cloud platforms (AWS, GCP, Azure), game backend services (PlayFab, GameLift, Nakama), and infrastructure patterns specific to games.

Philosophy: Infrastructure Serves the Player

Good infrastructure is invisible to players—they just experience smooth gameplay:

  • Low latency connections
  • High availability
  • Seamless scaling
  • Cost efficiency

The goal is reliable infrastructure that handles launch day and beyond.

Core Principles

1. Design for Launch Day

LAUNCH TRAFFIC PATTERN:
     │
Load │    ████
     │   ██████
     │  ████████
     │ ██████████
     │████████████████████
     └────────────────────→
       Launch    Week 1    Steady State

LESSON: Over-provision for launch, optimize later

You can't undo a failed launch.

2. Latency Is Everything

PLAYER PERCEPTION:
< 50ms:  Feels instant
50-100ms: Acceptable
100-200ms: Noticeable lag
> 200ms: Frustrating

LATENCY BUDGET:
- Network RTT: ~20-80ms (regional)
- Server processing: ~5-20ms
- Client prediction: hides the rest

Players quit laggy games.

3. Scale Horizontally

VERTICAL SCALING:
[Small Server] → [Big Server] → [Bigger Server] → [Limit]

HORIZONTAL SCALING:
[Server] [Server] [Server] [Server] → [More Servers]

PREFER: Horizontal (cheaper, no ceiling, fault tolerant)

4. Embrace Managed Services

BUILD VS BUY:
- Matchmaking: Use GameLift/PlayFab
- Database: Use managed DB
- Analytics: Use existing platforms
- Auth: Use OAuth providers

BUILD ONLY: Core game logic that differentiates you

Infrastructure Patterns

Stateless Game Servers

┌─────────┐     ┌─────────────────────────────┐
│ Client  │────▶│ Load Balancer              │
└─────────┘     └────────────┬────────────────┘
                             │
              ┌──────────────┼──────────────┐
              ▼              ▼              ▼
        ┌──────────┐  ┌──────────┐  ┌──────────┐
        │ Server A │  │ Server B │  │ Server C │
        └────┬─────┘  └────┬─────┘  └────┬─────┘
             │             │             │
             └─────────────┴─────────────┘
                           │
                    ┌──────▼──────┐
                    │  Database   │
                    └─────────────┘

Read the full file on GitHub · 359 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. 6d ago First seen · 359 lines · 27 tokens per session scan A 8a5de6db3b21

Subscribe to this mod's changes

infrastructure-planner is an agent published in the GitHub repository sponticelli/gamedev-claude-plugins (15 stars, last pushed 7mo ago), licensed MIT. It adds 27 tokens to every session and 2,484 once invoked, about $0.0001 per session on Opus 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 2026-08-30.