AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
The deploy skill streamlines the process of moving applications to AWS by minimizing cognitive burden. It analyzes a codebase to identify the framework and dependencies, recommends appropriate AWS services based on established defaults, provides a monthly cost estimate, and generates secure infrastructure-as-code. The skill prioritizes cost-conscious dev-sized environments by default and integrates with specialized MCP servers for architecture knowledge, pricing, and IaC best practices.
What it does
- Scans codebases to determine the optimal AWS service stack.
- Provides monthly cost estimates for proposed infrastructure before deployment.
- Generates infrastructure-as-code with built-in security defaults.
- Performs automated security scans on generated IaC.
- Selects services based on a predefined matrix of web, database, and background task patterns.
- Handles migrations from platforms like Heroku or Render to Elastic Beanstalk.
When to use it
- When you need to deploy a new application to AWS but want to avoid manual infrastructure configuration.
- When you need a cost estimate for an AWS architecture before committing to deployment.
- When you want to ensure your infrastructure follows security best practices like encryption and least privilege.
- When migrating an existing application from a managed platform to AWS.
Advantages
- Reduces cognitive load by automating service selection and IaC generation.
- Ensures cost transparency by requiring estimates before deployment.
- Applies security defaults automatically to all generated infrastructure.
- Maintains consistency by using a standardized service selection matrix.
- Avoids deprecated services by enforcing current AWS recommendations.
Usage examples
- “Deploy my Django application to AWS.”
- The agent analyzes the Django codebase, recommends Fargate with an ALB, provides a monthly cost estimate, and generates the necessary IaC.
- “Estimate AWS cost for a static site.”
- The agent identifies the site as a static SPA, recommends Amplify Hosting, and provides a cost breakdown.
- “Generate infrastructure for my Node.js API.”
- The agent selects Fargate, calculates the monthly cost, and produces secure IaC templates.
Install
Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/awslabs/deploy/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip deploy.zip -d .agents/skills
Documentation by AWS Labs
Deploy on AWS
Take any application and deploy it to AWS with minimal user decisions.
Philosophy
Minimize cognitive burden. User has code, wants it on AWS. Pick the most straightforward services. Don't ask questions with obvious answers.
Workflow
Analyze - Scan codebase for framework, database, dependencies
Recommend - Select AWS services, concisely explain rationale
Estimate - Show monthly cost before proceeding
Generate - Write IaC code with security defaults applied
Deploy - Run security checks, then execute with user confirmation
Defaults
See defaults.md for the complete service selection matrix.
Core principle: Default to dev-sized (cost-conscious: small instance sizes, minimal redundancy, and non-HA/single-AZ defaults) unless user says "production-ready".
MCP Servers
awsknowledge
Consult for architecture decisions. Use when choosing between AWS services or validating that a service fits the use case. Helps answer "what's the right AWS service for X?"
Key topics: general for architecture, amplify_docs for static sites/SPAs,
cdk_docs and cdk_constructs for IaC patterns.
awspricing
Get cost estimates. Always present costs before generating IaC so user can adjust before committing. See cost-estimation.md for query patterns.
awsiac
Consult for IaC best practices. Use when writing CDK/CloudFormation/Terraform to ensure patterns follow AWS recommendations.
Principles
Concisely explain why each service was chosen
Always show cost estimate before generating code
Apply security defaults automatically (encryption, private subnets, least privilege)
Run IaC security scans (cfn-nag, checkov) before deployment
Don't ask "Lambda or Fargate?" - just pick the obvious one
If genuinely ambiguous, then ask
Never recommend AWS App Runner — it is in maintenance mode. Use ECS Express Mode instead.
When user explicitly requests a managed application platform or signals low infrastructure involvement, route to Elastic Beanstalk
References
Elastic Beanstalk skill
Files
- ATTRIBUTION.mdAdded by AutoGineer897 B
- LICENSELicence file added by AutoGineer9.9 KiB
- NOTICELicence file added by AutoGineer89 B
- SKILL.md2.6 KiB
- references/cost-estimation.md6.8 KiB
- references/defaults.md6.3 KiB
- references/security.md9.4 KiB
references/cost-estimation.md
Cost Estimation Patterns
Use the awspricing MCP server to get accurate cost estimates before generating IaC.
Workflow
Identify all AWS services in the architecture
Query pricing for each service
Calculate monthly estimates based on expected usage
Present total before proceeding
Service Codes
| Service | Code | Notes |
|---|---|---|
| Fargate | AmazonECS | Filter by usagetype containing "Fargate" |
| Aurora PostgreSQL | AmazonRDS | Filter: databaseEngine = "Aurora PostgreSQL" |
| Aurora MySQL | AmazonRDS | Filter: databaseEngine = "Aurora MySQL" |
| RDS PostgreSQL | AmazonRDS | Filter: databaseEngine = "PostgreSQL" |
| Amazon DocumentDB | AmazonDocDB | MongoDB-compatible managed database |
| ALB | AWSELB | Application Load Balancer |
| S3 | AmazonS3 | Storage and requests |
| CloudFront | AmazonCloudFront | CDN distribution |
| Amplify | AWSAmplify | Hosting, build minutes |
| Lambda | AWSLambda | Requests and duration |
| DynamoDB | AmazonDynamoDB | On-demand or provisioned |
| Secrets Manager | AWSSecretsManager | Per secret per month |
| Elastic Beanstalk | N/A (free service) | No EB charge; query EC2, AWSELB for actual costs |
| EKS | AmazonEKS | Cluster hour + Auto Mode per-instance management |
| CloudWatch | AmazonCloudWatch | Custom metrics per metric; log ingestion/storage |
| NAT Gateway | AmazonVPC | Per hour + per GB processed |
| CodeBuild | CodeBuild | Per build minute, by compute type |
Fargate Pricing
Fargate charges per vCPU-hour and per GB-hour. Query with usagetype filters:
usagetype: "USE1-Fargate-vCPU-Hours:perCPU" # vCPU pricing
usagetype: "USE1-Fargate-GB-Hours" # Memory pricingTypical small app (0.5 vCPU, 1GB):
us-east-1: ~$18/month running 24/7
Aurora Serverless v2 Pricing
Aurora Serverless v2 charges per ACU-hour (Aurora Capacity Unit).
Minimum: 0.5 ACU
1 ACU ≈ 2GB memory
Dev estimate (0.5-2 ACU range):
~$45-90/month depending on usage patterns
Production estimate (2-8 ACU range):
~$180-360/month depending on load
Amazon DocumentDB Serverless Pricing
Amazon DocumentDB Serverless charges per DCU-hour (DocumentDB Capacity Unit), storage (GB-month), and I/O (standard config only).
Minimum: 0.5 DCU
1 DCU ≈ 2 GiB memory
Dev estimate (0.5-2 DCU range, 10GB storage):
~$35-120/month depending on usage patterns (scales to 0.5 DCU when idle)
Production estimate (2-8 DCU range, 100GB storage, multi-AZ):
~$130-400/month depending on load
Elastic Beanstalk Pricing
Elastic Beanstalk itself has no service fee. Cost equals the underlying AWS resources provisioned for the environment (EC2, ELB, EBS, CloudWatch). Query awspricing MCP server for region-accurate estimates. Approximate us-east-1 pricing:
Dev web (1x t3.small + ALB): ~$35-40/month Dev worker (1x t3.small, no ALB): ~$15-20/month Production web (4x t3.medium + ALB, Multi-AZ): ~$150-200/month
Include EBS volume costs (8GB gp3 default: ~$1/month per instance).
Beanstalk Cluster mode (managed EKS)
Cluster mode has a different and higher cost floor than Standard mode, so a Standard-vs-Cluster comparison that prices only the EKS cluster, the nodes, and the ALB understates it. Price all of these:
| Line item | Applies |
|---|---|
| EKS cluster hour | Once per cluster, shared by every environment on the same subnets |
| EC2 instances for the replicas | Per workload |
| EKS Auto Mode management charge | Per instance, on top of the instance price, varying by instance type |
| ALB | Per environment, unless load-balancer-type is None |
| CloudWatch custom metrics | Three custom namespaces, on by default, scaling with replica count |
| CloudWatch logs | Four shared log groups created with no retention policy — nothing expires |
| NAT gateway or VPC endpoints | Private-subnet environments, which need egress to pull the image |
| CodeBuild + ECR | Only when Elastic Beanstalk builds the image from source |
Two of these are the ones that get missed. The custom metrics are a new line item
rather than a bigger one — Standard mode publishes to AWS/ElasticBeanstalk,
which CloudWatch provides free, while Cluster mode publishes per replica to paid
custom namespaces. And the log groups accumulate indefinitely, gaining a new set
of streams on every deployment, until someone sets retention.
Only the cluster hour is shared across environments. Everything else is per workload, so a second service on an existing cluster is cheaper than the first but not close to free. A single small service usually costs more in Cluster mode than the same service on one EC2 instance in Standard mode; the economics improve with the number of services sharing the cluster. Say so when presenting the comparison.
Quick Reference Estimates
Small web app (Fargate + Aurora Serverless v2 + ALB):
Dev: ~$70-100/month
Production: ~$200-400/month
Small web app (Fargate + Amazon DocumentDB Serverless + ALB):
Dev: ~$70-155/month
Production: ~$200-450/month
Static site / SPA (Amplify Hosting):
Low traffic: ~$0-5/month (free tier covers most small sites)
High traffic: ~$15-40/month
Static site (S3 + CloudFront):
Low traffic: ~$1-5/month
High traffic: ~$20-50/month
Serverless API (Lambda + API Gateway + DynamoDB):
Low traffic: ~$5-20/month
High traffic: scales with requests
Web app on Elastic Beanstalk:
Dev (1x t3.small + ALB): ~$35-40/month
Production (load-balanced, Multi-AZ): ~$80-200/month
Web app on EB + Aurora Serverless v2:
Dev: ~$80-130/month
Production: ~$200-400/month
Presenting Estimates
Always show:
Per-service breakdown
Monthly total
Key assumptions (e.g., "assumes 24/7 uptime", "assumes 1M requests/month")
Cost optimization tips if relevant
Requirements and compatibility
Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta
“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.
Needs: Needs an MCP server
Security
No issues found by our static scan· No issues found
A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.
Attribution and licence
- Published by
- AWS Labs
- Publisher
- AWS Labs (Official)
- Source
- awslabs/agent-plugins · plugins/deploy-on-aws/skills/deploy · commit fbefb37
- Licence
- Apache License 2.0 (redistribution allowed)
- LICENSE (added by AutoGineer from LICENSE)
- NOTICE (added by AutoGineer from NOTICE)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by AWS Labs.
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download deploy.zip