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 cloud-architecturegit 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/cloud-architecture)<a href="https://agentmods.dev/skills/sethdford/claude-skills/cloud-architecture"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/cloud-architecture/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/cloud-architecture"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/cloud-architecture.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 | $0.00037 | $0.00677 |
| Opus 5 | $0.00018 | $0.00338 |
| Sonnet 5 | $0.00007 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
cloud-architecture 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Architecture
Design scalable, cost-effective, secure cloud infrastructure on AWS, GCP, or Azure.
Context
You are designing cloud infrastructure. Select services, plan scaling, networking, security, and cost. Read requirements, existing infrastructure, regulatory constraints, and team cloud maturity.
Domain Context
Based on cloud architecture best practices (AWS Well-Architected Framework, Google Cloud Architecture Framework):
- Compute: Servers (EC2/Compute Engine), containers (ECS/GKE), functions (Lambda/Cloud Functions), management burden increases
- Storage: Object storage (S3), databases (RDS/Cloud SQL), data warehouses (Redshift/BigQuery)
- Networking: VPC isolation, subnets, security groups, load balancing, DNS
- Observability: Metrics, logs, traces; CloudWatch, Stackdriver, DataDog
- Compliance: Shared responsibility; you manage application, cloud owns infrastructure
Instructions
-
Select Core Services: What workloads? Web app → App Engine/Elastic Beanstalk. Data processing → Spark on Kubernetes. Database → RDS PostgreSQL. Data warehouse → BigQuery.
-
Design Resilient Architecture: Multi-AZ (availability zone) for redundancy. Health checks and auto-recovery. Load balancing across instances. Plan RPO/RTO requirements.
-
Plan Networking: VPC with public and private subnets. Bastion for private access. Security groups restrict traffic. NAT Gateway for outbound access. CloudFlare or WAF for DDoS.
-
Implement Security: IAM roles (principle of least privilege). Encrypt data at rest (KMS) and in transit (TLS). Secrets management (Secrets Manager/Vault). Regular patching.
-
Cost Optimize: Reserved instances for predictable workloads (30-70% discount). Spot instances for batch/non-critical (70% discount). Right-size instances; monitor utilization. Use managed services to reduce operational overhead.
Anti-Patterns
- Lift-and-Shift Without Optimization: Move VMs to cloud as-is. Result: expensive, not cloud-native. Guard: Rearchitect for cloud; use managed services where appropriate.
- Single-AZ for Critical Services: Cut costs by using single availability zone. Result: outage when AZ fails. Guard: Multi-AZ for production; single-AZ acceptable for non-critical dev.
- Ignoring Cloud-Native Patterns: Treat cloud like traditional datacenter. Result: underutilize auto-scaling, caching, global distribution. Guard: Design for elasticity; use services like CDN, auto-scaling groups.
- No Cost Monitoring: Assume cloud is cheaper than on-prem. Result: bill shock. Guard: Set up cost alerts; monitor per-service usage; optimize continuously.
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 · 48 lines · 37 tokens per session scan A 2cd47380c173
cloud-architecture is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 677 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.
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.
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.
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…