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 skills add sethdford/claude-skills --skill multi-region-designgit clone --depth 1 https://github.com/sethdford/claude-skillsWrote 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/skills/sethdford/claude-skills/multi-region-design)<a href="https://agentmods.dev/skills/sethdford/claude-skills/multi-region-design"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/multi-region-design/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/skills/sethdford/claude-skills/multi-region-design"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/multi-region-design.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 | $0.00036 | $0.00624 |
| Opus 5 | $0.00018 | $0.00312 |
| Sonnet 5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
multi-region-design 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 12d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Region Design
Architect globally distributed systems with low latency, data sovereignty, and automatic failover.
Context
You are designing systems spanning multiple regions. Plan data replication, edge caching, latency optimization, and compliance. Read user distribution, latency requirements, and regulatory constraints.
Domain Context
Based on global infrastructure design (Netflix, Google, Cloudflare):
- Latency: User experiences slowness if round-trip > 100ms. Multi-region with CDN typically needed for global audience.
- Data Replication: Eventual consistency (asynchronous) for high availability. Strong consistency harder to achieve globally; usually not needed.
- Compliance: GDPR requires EU data in EU. PIPL requires China data in China. Design for data residency.
- Edge Computing: Run compute near users; offload from central region
- DNS-Based Routing: Route users to nearest healthy region using geo-DNS
Instructions
-
Map User Distribution: Where are users? 50% US-East, 30% Europe, 20% Asia? Design regions to minimize latency to majority.
-
Plan Data Replication: How quickly must data replicate to other regions? Realtime streaming (DynamoDB global tables) or batch (daily sync)? Cost increases with replication frequency.
-
Implement Read Replicas: Let each region read locally. Writes go to primary region, asynchronously replicate to replicas. Handle read-after-write consistency issues.
-
Set Up Failover: Primary region fails, automatically route to standby region. Traffic reroutes via DNS or load balancer health checks. Test failover regularly.
-
Optimize Latency: CDN caches static content near users. API Gateway in each region. Database read replicas local to region. Monitor latency by region; identify bottlenecks.
Anti-Patterns
- Multi-Region Without Plan: "Let's just replicate everything globally." Result: complexity, cost, hard to debug. Guard: Design for specific latency/compliance needs; multi-region is expensive.
- Strong Consistency Globally: Require all regions to immediately see writes. Result: latency, complexity. Guard: Accept eventual consistency; design application for it.
- No Failover Testing: Assume it works. Result: regional failure becomes outage. Guard: Monthly failover drills; practice responding to regional incidents.
- Ignoring Data Residency: Replicate data to any region for performance. Result: compliance violation. Guard: Implement geofences; restrict EU data to EU regions.
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.
- 12d ago First seen · 48 lines · 36 tokens per session scan A 06c3f9097e38
multi-region-design is a skill published in the GitHub repository sethdford/claude-skills (41 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 624 once invoked, about $0.0002 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 skills, from other repositories
enterprise-agent-ops
Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.
multi-tenant-architecture
Designs tenant isolation, hostname routing, custom-domain lifecycle, and plan limits on Cloudflare or Vercel. Use when asked to "isolate tenant data", "support custom domains", "build a white-label platform", or assess PSL registration. For general module structure use codebase-architecture; for SEO content use seo.
discovery-patterns
Configure ServiceNow Discovery — schedules, IP ranges, credential affinities, MID Server assignment, custom probes/sensors, identification rules, and run-status monitoring on discovery tables.
cloud-hosting-expert
Expert guide for deploying SaaS applications with multiple entry points on modern edge and serverless platforms like Vercel and Cloudflare / Panduan ahli untuk mendeploy aplikasi SaaS dengan multiple entry points di platform edge dan serverless modern seperti Vercel dan Cloudflare.
deno-deploy
Use when deploying Deno apps to production, asking about Deno Deploy, or working with deno deploy CLI commands. Covers deployment workflows, environment variables, KV database access, custom domains, the --tunnel flag for local development, and the deno deploy command reference.
aws-cdk
Create and review Java AWS CDK v2 infrastructure code organized with the BCE (Boundary-Control-Entity) pattern — scaffold the project, wire the app entry point, pin regions in a central Stacks interface, model business components named after AWS services, and keep stacks thin over reusable constructs. Use whenever…