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.
git clone --depth 1 https://github.com/sponticelli/gamedev-claude-pluginsWrote 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/commands/sponticelli/gamedev-claude-plugins/infra-plan)<a href="https://agentmods.dev/commands/sponticelli/gamedev-claude-plugins/infra-plan"><img src="https://agentmods.dev/badge/commands/sponticelli/gamedev-claude-plugins/infra-plan/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.
<a href="https://agentmods.dev/commands/sponticelli/gamedev-claude-plugins/infra-plan"><img src="https://agentmods.dev/badge/commands/sponticelli/gamedev-claude-plugins/infra-plan.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00007 | $0.01059 |
| Opus 5 | $0.00003 | $0.00530 |
| Sonnet 5 | $0.00001 | $0.00212 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
infra-plan 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 9d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infrastructure Architecture Plan Generator
Generate a comprehensive infrastructure architecture plan for a game project.
Context Gathering
Before generating, understand:
Game Requirements
- Game type (single-player, multiplayer, live-service)
- Expected concurrent users (CCU)
- Real-time requirements (latency sensitivity)
- Data storage needs (player profiles, leaderboards, etc.)
Technical Context
- Preferred cloud provider (AWS, GCP, Azure)
- Budget constraints
- Team ops experience
- Existing infrastructure (if any)
Geographic Requirements
- Primary player regions
- Data residency requirements
- CDN needs
Output Format
# Infrastructure Architecture: [Project Name]
## Overview
**Game Type:** [Type]
**Cloud Provider:** [Provider]
**Target CCU:** [Number]
**Primary Region:** [Region]
## Architecture Diagram
[ASCII diagram of infrastructure]
## Components
### Compute Layer
| Component | Service | Specs | Quantity | Purpose |
|-----------|---------|-------|----------|---------|
| Game servers | [Service] | [Size] | [N] | Game logic |
| API servers | [Service] | [Size] | [N] | REST API |
### Data Layer
| Data Type | Service | Configuration | Purpose |
|-----------|---------|---------------|---------|
| Player profiles | [DB] | [Config] | Account data |
| Game state | [DB] | [Config] | Match data |
| Analytics | [DB] | [Config] | Telemetry |
### Supporting Services
| Service | Provider | Purpose |
|---------|----------|---------|
| Matchmaking | [Service] | Player matching |
| CDN | [Service] | Asset delivery |
| Auth | [Service] | Authentication |
## Scaling Strategy
### Auto-Scaling Rules
| Trigger | Action | Cooldown |
|---------|--------|----------|
| CCU > [N] | Add [N] servers | [Time] |
| CCU < [N] | Remove [N] servers | [Time] |
| CPU > [%] | Scale up | [Time] |
### Capacity Tiers
| Tier | CCU Range | Servers | Est. Cost/Month |
|------|-----------|---------|-----------------|
| Quiet | 0-1K | [N] | $[X] |
| Normal | 1K-10K | [N] | $[X] |
| Peak | 10K-50K | [N] | $[X] |
| Event | 50K+ | [N] | $[X] |
## Regional Distribution
| Region | Purpose | Services | Latency Target |
|--------|---------|----------|----------------|
| [Region] | Primary | All | <50ms |
| [Region] | Secondary | Game servers | <80ms |
## Cost Estimate
### Monthly Baseline
| Category | Service | Estimate |
|----------|---------|----------|
| Compute | [Service] | $[X] |
| Database | [Service] | $[X] |
| Network | [Service] | $[X] |
| Storage | [Service] | $[X] |
| **Total** | | **$[X]** |
### Launch Surge
**Duration:** [Time]
**Multiplier:** [X]x baseline
**Budget:** $[X]
## High Availability
### Redundancy
| Component | Strategy | RPO | RTO |
|-----------|----------|-----|-----|
| Database | Multi-AZ | 0 | <1 min |
| Game servers | Auto-replace | N/A | <2 min |
| API | Load balanced | N/A | <30 sec |
### Disaster Recovery
| Scenario | Response | Recovery Time |
|----------|----------|---------------|
| AZ failure | Failover | < 5 minutes |
| Region failure | DNS failover | < 15 minutes |
| Data corruption | Point-in-time | < 1 hour |
## Security
### Network Security
- VPC isolation
- Security groups
- Private subnets for databases
### Application Security
- TLS everywhere
- API authentication
- Rate limiting
### Data Security
- Encryption at rest
- Encryption in transit
- Regular backups
## Monitoring
### Metrics
| Metric | Alert Threshold | Response |
|--------|-----------------|----------|
| Server CPU | > 80% | Scale up |
| Error rate | > 1% | Investigate |
| Latency p95 | > 100ms | Investigate |
### Dashboards
- Player CCU
- Server health
- Error rates
- Latency percentiles
## Implementation Phases
### Phase 1: MVP
- Single region
- Basic scaling
- Managed services
### Phase 2: Production
- Multi-AZ
- Auto-scaling
- Monitoring
### Phase 3: Global
- Multi-region
- CDN
- Advanced DR
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.
- 9d ago First seen · 177 lines · 7 tokens per session scan A 1dcda433c67a
infra-plan is a command published in the GitHub repository sponticelli/gamedev-claude-plugins (15 stars, last pushed 8mo ago), licensed MIT. It adds 7 tokens to every session and 1,059 once invoked, about $0.0000 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.
Other commands, from other repositories
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
status
Show 3d-design team status and recent activity.
env
Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.
scan
Scan AWS account for cost optimization.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.