Intro
We keep running into the same issue with AI coding agents when building and deploying on AWS. Agents can handle easy tasks well, like spinning up an Amazon S3 bucket or launching an EC2 instance, but when you tasks starts to get complex, say wiring a serverless API with least-privilege permissions or standing up a data pipeline end to end, they do weird things like choosing a service that isn't the right fit for the job, misconfiguring a resource or looping on retries against something they've never seen.
This happens because the model is working from a training snapshot that's weeks to months old, and since then AWS has kept shipping new services and features the model has never seen. So if a task depends on a recently released service or feature, the agent doesn't accurately know how to achieve it..
Today, we've solved that problem with the Agent Toolkit for AWS . It gives your agent a live line to current AWS documentation, tested procedures and a secure way to build and deploy on AWS. It's free to use and you pay only for the AWS resources your agent spins up. Best of all, it supports the coding agents you already use, like Kiro, Claude Code, Cursor and Codex.
Go grab it here, install it locally so your agent can start using today.
The commands below are grouped by when you'll reach for them, from first setup through cleanup. Pin this cheat sheet somewhere handy!
Set up and connect
aws configure agent-toolkitDetects your coding agent and sets up the skills and the AWS MCP Server.
npx skills add aws/agent-toolkit-for-aws/skillsInstalls the AWS skills for MCP-compatible agents.
Find the right skill
aws agent-toolkit list-available-skillsLists every skill in the catalog, so you see the full menu before you install.
aws agent-toolkit search-skills --search-query serverlessSearches skills by topic, so you skip the scroll. Swap serverless for whatever you're building.
Review before you install
aws agent-toolkit get-skill-metadata --skill-name aws-serverlessShows a skill's version, description, and file list before you commit to it.
aws agent-toolkit get-skill-file --skill-name aws-cdk --file-path SKILL.mdPulls a single file so you can read exactly what a skill tells your agent to do.
Install and take inventory
aws agent-toolkit add-skill --skill-name aws-serverlessInstalls one skill on demand, so you add only what the task needs.
aws agent-toolkit list-installed-skillsShows what's installed, on which agent, and where.
Keep current and clean up
aws agent-toolkit update-skill --skill-name aws-serverlessUpdates an installed skill to its latest version.
aws agent-toolkit remove-skill --skill-name aws-cdkRemoves a skill you no longer need.
Try it out yourself
Connect the toolkit, then hand your agent a task like "Create an S3 bucket with versioning enabled and a lifecycle policy that transitions objects to Amazon S3 Glacier after 90 days." Watch what happens now that it's grounded in current AWS knowledge instead of working from memory.
Save this cheat sheet and grab the toolkit here.
Top comments (0)