CommunityWriting & Editinggithub.com

alexaiarchitect/agentcore-skills

>- Scaffold Amazon Bedrock AgentCore resources as infrastructure as code: a Runtime (ECR repository, service role, `aws_bedrockagentcore_agent_runtime` with a JWT authorizer and lifecycle settings), a Gateway (role, JWT authorizer, pinned MCP revisions, one target), Identity (Cognito M2M client plus an OAuth2 credential provider with write-only secrets) or Memory (memory, strategies, customer-managed key). Terraform modules are the default and the recommendation; a TypeScript CDK stack with the `aws-bedrockagentcore` L1 constructs and the AgentCore CLI (`@aws/agentcore`) commands are offered for teams already on them. Every write is shown as a plan first (`--dry-run`), existing files are never overwritten without `--force`, and nothing is planned or applied. Use when asked to "create an AgentCore runtime", "scaffold a gateway", "add AgentCore memory", "write the Terraform for AgentCore", "start a new AgentCore stack", or "give me the CDK for this". Don't use for a gateway in front of an existing Lambda, HT...

What is agentcore-skills?

agentcore-skills is a Claude Code agent skill that >- Scaffold Amazon Bedrock AgentCore resources as infrastructure as code: a Runtime (ECR repository, service role, `aws_bedrockagentcore_agent_runtime` with a JWT authorizer and lifecycle settings), a Gateway (role, JWT authorizer, pinned MCP revisions, one target), Identity (Cognito M2M client plus an OAuth2 credential provider with write-only secrets) or Memory (memory, strategies, customer-managed key). Terraform modules are the default and the recommendation; a TypeScript CDK stack with the `aws-bedrockagentcore` L1 constructs and the AgentCore CLI (`@aws/agentcore`) commands are offered for teams already on them. Every write is shown as a plan first (`--dry-run`), existing files are never overwritten without `--force`, and nothing is planned or applied. Use when asked to "create an AgentCore runtime", "scaffold a gateway", "add AgentCore memory", "write the Terraform for AgentCore", "start a new AgentCore stack", or "give me the CDK for this". Don't use for a gateway in front of an existing Lambda, HT...

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/alexaiarchitect/agentcore-skills/tree/HEAD/skills/agentcore-create

Installed? Explore more Writing & Editing skills: steipete/notion, langchain-ai/langchain, bytedance/podcast-generation · View all 6 →

View original→Browse all skills

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentation

Create AgentCore resources as IaC

A new AgentCore resource should arrive as a reviewed module in the same tree as everything else the team deploys, not as a console click nobody can reproduce. This skill writes small, flat Terraform modules — one main.tf, variables.tf, outputs.tf, versions.tf — that the user wires from their root module. The modules are deliberately boring: every argument is explained in a comment, secrets are write-only, and the gateway is never created without an authorizer.

${CLAUDE_SKILL_DIR} is set by the skill runtime to this skill's own directory. Use it verbatim in every command below; a sibling skill's scripts are at ${CLAUDE_SKILL_DIR}/../<skill>/scripts/.

Flow

  1. Discover first, so the module lands next to the existing ones and the region is known:

    python3 ${CLAUDE_SKILL_DIR}/../agentcore-discover/scripts/discover.py <project> --focus agentcore,region,terraform

    If the AgentCore CLI or CDK already owns AgentCore resources (DSC004 territory), offer the matching --iac instead of Terraform.

  2. Plan the write.

    python3 ${CLAUDE_SKILL_DIR}/scripts/scaffold.py <project> --component runtime --dry-run

    --component gateway|identity|memory, --iac terraform|cdk|cli, --name, --out-dir, --protocol HTTP|MCP|A2A|AGUI (runtime).

  3. Options. Terraform module (recommended, free), CDK stack (free), or the AgentCore CLI commands (free to print; agentcore deploy itself is aws).

  4. Confirm with AskUserQuestion, then run the same command without --dry-run. Pass --force only when the user asked to replace a file after seeing the plan.

  5. Verify. Run the review on the result and show it:

    python3 ${CLAUDE_SKILL_DIR}/../agentcore-review/scripts/review.py <project>

Decision rules

  • Terraform first. It is what the first user runs, and the only option where this plugin's review, deploy plan and CI policy all apply. The hashicorp/aws provider covers every core resource; see provider-coverage.md for what needs awscc or the CLI.
  • A module is wired, not applied. The script prints the module block to add; it never edits the root module.
  • Write-only secrets need Terraform 1.11+. The generated versions.tf says so; older Terraform must use a sensitive variable and accept that the secret is in state (ACR031).
  • The starter toolkit is not offered. Its CLI is no longer supported; the AgentCore CLI is the CLI alternative.

References

QuestionFile
What each generated module contains and whyterraform-modules.md
The CDK and AgentCore CLI paths, and when to choose themcdk-and-cli-alternatives.md
Which resources hashicorp/aws covers; awscc and CLI fallbacksprovider-coverage.md

Scripts

CommandDoesExit codes
scripts/scaffold.py <project> --component C [--iac terraform|cdk|cli] [--dry-run] [--force] [--json]plans and writes a module, a CDK stack, or prints CLI commands0 written/planned, 1 nothing to write, 2 bad arguments

Completion checklist

  • Discovery ran, and the chosen IaC matches whoever already owns AgentCore resources.
  • The write plan was shown from --dry-run and confirmed before writing.
  • The module wiring block was given to the user, not written into their root module.
  • review.py ran on the result and its findings were shown.

Individual skills in this repo

This repo contains 4 individual skills — each has its own dedicated page.

alexaiarchitect/agentcore-skills

>- Put Amazon Bedrock AgentCore infrastructure behind a plan-only CI gate. Generates a GitHub Actions workflow that, on pull requests touching the infrastructure, runs the static AgentCore review (`ACR0xx`), `terraform fmt -check`, `init`, `validate`, a saved `plan` (Terraform or Terragrunt) with a read-only OIDC role, `show -json`, and the plan policy (`CI0xx`: no delete or replace of memories, gateways, credential providers, workload identities, user pools or tables without an explicit per-address allowance; no `*` on `*`; no gateway with `authorizer_type = NONE`; pinned MCP revisions), then uploads the plan JSON. Nothing in it applies. The plugin's stdlib-only library is vendored into `ci/agentcore/` so the job needs nothing from the plugin, and action pins are reused from the repository's own SHA-pinned workflows. `policy_check.py` also runs locally on any saved plan. Use when asked to "add CI for the AgentCore Terraform", "gate the plan", "block destructive changes", "policy check the plan", "plan on ...

alexaiarchitect/agentcore-skills

>- Estimate what Amazon Bedrock AgentCore will cost per month from a usage profile, line by line with the formula for each line, and put a budget and a usage alarm around it. Prices the published AgentCore rate card (Gateway invocations, search and tool indexing; Identity token requests, free through Runtime or Gateway; Runtime vCPU-hours billed only while active and GB-hours; Memory short-term events — per 1,000 events until 2026-10-05, per GB from 2026-10-06 — and long-term records and retrievals; Evaluations tokens), prices model tokens only at the user's own per-1,000 rates, and lists what it does not price (Lambda, API Gateway, CloudWatch, X-Ray, DynamoDB) so the total is never mistaken for the bill. Generates an AWS Budget filtered to AgentCore with forecast and actual alerts, plus a CloudWatch alarm on gateway invocations, as Terraform after a dry run. Findings are the `CST0xx` band. Use when asked "what will AgentCore cost", "estimate the gateway bill", "is there a free tier", "memory pricing chang...

alexaiarchitect/agentcore-skills

>- Plan the deployment of Amazon Bedrock AgentCore infrastructure and its rollback, and hand the user the exact commands — never running them. Finds the root module (or Terragrunt stack) that actually reaches the AgentCore resources, orders what comes up (identity and roles, then gateway, runtime and memory, then targets and strategies, then log delivery), flags where a first apply trips (IAM propagation, creation-only semantic search, Transaction Search before TRACES delivery, an old provider lock, no remote backend), checks published quotas (targets per gateway, tools per target), and emits init / validate / plan-to-file / show -json / policy check / apply of that saved plan, the post-apply checks, and the rollback for each kind of change. Findings are the `DPL0xx` band; the cost tier is `aws` because the commands create billable resources. Use when asked to "deploy the gateway", "apply this", "what order do I apply in", "how do I roll back", "will this hit a quota", "give me the terraform commands". Don...

alexaiarchitect/agentcore-skills

>- Inventory a project for Amazon Bedrock AgentCore work and report before advising. Finds existing AgentCore resources and which tool owns them (Terraform `aws_bedrockagentcore_*`/`awscc_*`, CDK constructs, the AgentCore CLI's `agentcore.json`, the deprecated starter toolkit's `.bedrock_agentcore.yaml`, boto3 `bedrock-agentcore` clients, the AgentCore Python SDK and `@requires_access_token`), the agent framework (Strands, LangGraph, LangChain, Claude Agent SDK, CrewAI, OpenAI Agents, ADK, raw), MCP servers and the API Gateway routes and Lambdas behind `/mcp`, Cognito pools, clients and JWT authorizers, the AWS region and per-service availability there, the hashicorp/aws constraint and lock, Terragrunt, and Lambda tracing. Read-only; findings are the `DSC0xx` band. Use when asked "what do I have", "is this on AgentCore", "inventory this repo", "which region are we in", "is AgentCore available in eu-central-1", "what framework is this agent", or before any other AgentCore skill on an unfamiliar project. Don...

Related Skills

steipete/notion

Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.

community

langchain-ai/langchain

The agent engineering platform.

community

bytedance/podcast-generation

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

community

composiohq/twitter-algorithm-optimizer

Analyze and optimize tweets for maximum reach using Twitter's open-source algorithm insights. Rewrite and edit user tweets to improve engagement and visibility based on how the recommendation system ranks content.

community

composiohq/competitive-ads-extractor

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

community

upstash/context7

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

community
← More Writing & Editing skills