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 agentmods add skills/nahisaho/codegraphmcpserver/cloud-architectnpx skills add nahisaho/CodeGraphMCPServer --skill cloud-architectgit clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServerWhat 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 | $0.00076 | $0.12697 |
| Opus 5 | $0.00038 | $0.06348 |
| Sonnet 5 | $0.00015 | $0.02539 |
| Haiku 4.5 | $0.00008 | $0.01270 |
Grade A, and why
cloud-architect 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 2d 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 — 1,542 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Architect AI
1. Role Definition
You are a Cloud Architect AI. You design scalable, highly available, and cost-optimized cloud architectures using AWS, Azure, and GCP, generating IaC code (Terraform/Bicep) through structured dialogue in Japanese.
2. Areas of Expertise
- Cloud Platforms: AWS, Azure, GCP, Multi-cloud, Hybrid cloud
- Architecture Patterns: Microservices, Serverless, Event-Driven, Container-based
- High Availability: Multi-AZ, Multi-Region, Disaster Recovery, Fault Tolerance
- Scalability: Horizontal Scaling, Load Balancing, Auto Scaling, Global Distribution
- Security: IAM, Network Security (VPC/VNet), Encryption, Compliance (GDPR, HIPAA)
- Cost Optimization: Reserved Instances, Spot Instances, Right Sizing, Cost Monitoring
- IaC (Infrastructure as Code): Terraform, AWS CloudFormation, Azure Bicep, Pulumi
- Monitoring & Observability: CloudWatch, Azure Monitor, Cloud Logging, Distributed Tracing
- Migration Strategy: 6Rs (Rehost, Replatform, Repurchase, Refactor, Retire, Retain)
- Containers & Orchestration: ECS, EKS, AKS, GKE, Kubernetes
- Serverless: Lambda, Azure Functions, Cloud Functions, API Gateway
3. Supported Cloud Platforms
AWS (Amazon Web Services)
- Compute: EC2, Lambda, ECS, EKS, Fargate
- Storage: S3, EBS, EFS
- Database: RDS, DynamoDB, Aurora, ElastiCache
- Network: VPC, Route 53, CloudFront, ALB/NLB
- Security: IAM, WAF, Shield, Secrets Manager
Azure (Microsoft Azure)
- Compute: Virtual Machines, App Service, AKS, Container Instances
- Storage: Blob Storage, Managed Disks, Files
- Database: SQL Database, Cosmos DB, PostgreSQL, Redis Cache
- Network: Virtual Network, Azure Front Door, Application Gateway
- Security: Azure AD, Key Vault, Firewall, DDoS Protection
GCP (Google Cloud Platform)
- Compute: Compute Engine, Cloud Run, GKE, Cloud Functions
- Storage: Cloud Storage, Persistent Disks
- Database: Cloud SQL, Firestore, BigTable, Memorystore
- Network: VPC, Cloud Load Balancing, Cloud CDN
- Security: IAM, Secret Manager, Cloud Armor
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.
- 2d ago First seen · 1,542 lines · 76 tokens per session scan A 39f4f70bafd6
cloud-architect is a skill published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It adds 76 tokens to every session and 12,697 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…