315 Claude Code plugins · 382 MCP servers · refreshed 26 Oct 2026Get your plugin featured →

migration-to-aws

Plan a migration from Google Cloud Platform (and OpenAI/Gemini AI workloads) to AWS. Analyzes your Infrastructure-as-Code files, app code, and GCP billing data to discover resources, design an AWS architecture, estimate costs, and generate migration artifacts — including AI-provider mapping to Amazon Bedrock. Processing is local; your data stays in your environment.

plugin★ 25updated 26 Oct 2026by Amazon Web Services
paste into Claude Code
/plugin install migration-to-aws@claude-plugins-official

How to start

  1. Paste the command into Claude Code and press Enter.
  2. Restart Claude Code so the plugin loads.
  3. Just ask Claude. Its skills step in when your request fits.

What it adds

7 agents · 5 skills · 4 MCP servers

Agents Claude hands work to these

  • generic-phase-worker-rwGeneric, phase-AGNOSTIC worker that runs ONE migration phase's work (its fragments + assembler) in an isolated context and writes the phase's artifact(s) to di…
  • generic-phase-worker-rwxGeneric, phase-AGNOSTIC worker that runs ONE migration phase's work (its fragments + assembler) in an isolated context and writes the phase's artifact(s) to di…
  • llm2bedrock-code-analyzerAnalyze the local source repo, detect the AI framework and LLM SDK usage, map all call sites, identify prompts, and enumerate user-visible behavior-deltas for…
  • llm2bedrock-code-rewriterRewrite LLM SDK calls to Amazon Bedrock on a dedicated git branch, swap dependencies, generate tests, and apply the user-confirmed behavior-delta decisions. Re…
  • llm2bedrock-log-ingestorParse LLM API logs from the local repo, extract prompt/response pairs, and build a golden dataset (prompts.jsonl) for evaluation. Returns a structured ingestio…
  • llm2bedrock-prompt-evaluatorRun each golden prompt against the target Bedrock model via the pinned uv harness, score with LLM-as-judge, and report a pass rate. Handles throttling with bac…
  • llm2bedrock-report-generatorSynthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATI…

Skills Claude loads these when the task fits

  • agent-advisorUnified entry point for AI-agent work on AWS: evaluate and pick a runtime, generate a full migration plan (for existing workloads), and build an executable POC…
  • gcp-to-awsMigrate workloads from Google Cloud Platform to AWS — including AI and agentic workloads regardless of cloud provider. Triggers on: migrate from GCP, GCP to AW…
  • heroku-to-awsMigrate workloads from Heroku to AWS. Triggers on: migrate from Heroku, Heroku to AWS, move off Heroku, migrate Heroku app, migrate Heroku Postgres to RDS, mig…
  • llm-to-bedrockUse when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock — a pure model/SDK rewrite. End-to-end: ass…
  • tf-best-practices>-

MCP servers Connections it sets up for you

  • awsknowledgeRemote server at knowledge-mcp.global.api.aws
  • awspricingRuns locally with uvx
  • temporal-docsRemote server at temporal.mcp.kapa.ai
  • aws-pricing-calculatorRuns locally with npx

Read from the plugin's own files in awslabs/startups, 26 Oct 2026.

What it needs

No keys or settings: its files ask for none. A remote server may still ask you to sign in the first time.