A guide for choosing, adapting, evaluating, and deploying AI models with Amazon SageMaker, AWS's managed machine-learning service, or Amazon Bedrock. It covers model work from initial planning through production endpoints.

Use it to define an AI use case, select a model, prepare datasets, fine-tune with methods such as supervised training or preference tuning, evaluate results, and deploy or diagnose endpoints.

It helps organize the many decisions involved in preparing data, tuning a model, measuring its results, and putting it into use.

aws-ai-ml — Skill for Claude Code and Codex by aws

About the project

Agent Toolkit for AWS is a collection of AWS-supported MCP servers, skills, plugins, commands, and hooks that help AI coding agents build, deploy, and manage applications on AWS. It is used by developers working with AWS services through agents such as Claude Code, Codex, Cursor, and Kiro. The catalogue entries are the toolkit's own agent extensions for AWS development and operations.

aws/agent-toolkit-for-aws · 2,559 stars · on GitHub

Install

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.

Any agent

npx skills add aws/agent-toolkit-for-aws --skill aws-ai-ml

Clone the repo

git clone --depth 1 https://github.com/aws/agent-toolkit-for-aws

Made for: Claude Code, Codex.

Or install aws-core, the plugin that ships this one along with the rest of its 24 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aws/agent-toolkit-for-aws/aws-ai-ml/github.svg)](https://agentmods.dev/skills/aws/agent-toolkit-for-aws/aws-ai-ml)

Your own site

<a href="https://agentmods.dev/skills/aws/agent-toolkit-for-aws/aws-ai-ml"><img src="https://agentmods.dev/badge/skills/aws/agent-toolkit-for-aws/aws-ai-ml/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aws/agent-toolkit-for-aws/aws-ai-ml"><img src="https://agentmods.dev/badge/skills/aws/agent-toolkit-for-aws/aws-ai-ml.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 203 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,426 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

Socket pass 24 Aug 2026
Snyk warn 24 Aug 2026
NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Prompt Injection · line 37
Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What 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 5.1	$0.00203	$0.01426
Opus 5	$0.00102	$0.00713
Sonnet 5	$0.00041	$0.00285
Haiku 4.5	$0.00020	$0.00143

Measured 9d ago against content hash 2d67532aa2a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aws-ai-ml 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 9d ago.

The scan reads SKILL.md. This mod also ships 20 executable files (references/dataset-evaluation/scripts/format_detector.py, references/dataset-transformation/code_templates/transformation.py, references/dataset-transformation/scripts/transformation_tools.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/aws-core/skills/aws-ai-ml/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AWS AI/ML Model Customization

Domain expertise for fine-tuning and deploying models on Amazon SageMaker. Covers the full model customization lifecycle from planning through production deployment.

Routing

Match the user's intent to the appropriate reference folder and load only that content.

User intent	Reference	When to use
Plan a model customization project, discover scope of work, resume or modify a plan	references/planning/	User's request relates to model customization or deployment (fine-tuning, training, building, customizing, reviewing data, deploying or standing up a model — including selecting or deploying an off-the-shelf or base model with no training — or getting advice on approach). Always co-activate with other intents to discover full scope. Load this reference FIRST when the request matches multiple rows in this table — read its plan templates before routing to a single-action reference.
Define the business problem, success criteria, or use case spec	references/use-case-specification/	User says "define my use case", "capture requirements", "what should I decide up front", or as default first step in any plan. Skip only if user explicitly declines.
Select or change a base model	references/model-selection/	User asks which model to use, mentions a model name or family, or wants to evaluate what's available. Always activate model-selection even for known model names because the exact Hub model ID must be resolved. Recommended: route to use-case-specification first to capture requirements — this produces better filtering results. Routing to use-case-specification first is not required if user provides a specific model name/ID or declines. If intent is ambiguous (fine-tune vs deploy as-is), model-selection MUST confirm which path before proceeding. Base model filtering for deployment MUST go through select-for-deployment.md and its scripts for any final recommendation.
Choose a fine-tuning technique (SFT, DPO, RLVR, RLAIF)	references/finetuning-technique/	User has decided to fine-tune and needs to choose a technique, or technique needs validation against the selected model's recipes. Requires a base model to be selected first.
Validate dataset quality and format	references/dataset-evaluation/	User says "is my dataset okay", "check my training data", "I have my own data", or before starting any fine-tuning job.
Transform or convert a dataset between formats	references/dataset-transformation/	User says "transform", "convert", "reformat", or dataset schema needs to change. Always use this rather than writing inline transformation code.
Generate fine-tuning code and start training	references/finetuning/	User says "start training", "fine-tune my model", "I'm ready to train", or plan reaches the finetuning step. Supports SFT, DPO, RLVR, RLAIF trainers.
Evaluate or benchmark a trained model	references/model-evaluation/	User says "evaluate my model", "run a benchmark", "test model performance", "compare models". Supports LLM-as-Judge and Custom Scorer.
Deploy a model to endpoint or Bedrock	references/model-deployment/	User says "deploy my model", "create an endpoint", "make it available". Handles Nova vs OSS deployment pathways.
Set up IAM roles, S3 buckets, SDK configuration	references/sdk-getting-started/	User says "set up", "getting started", "check my environment", "configure SDK", or as first step in any plan involving SageMaker training/evaluation/deployment.
Manage project directory and artifacts	references/directory-management/	Starting a new project, resuming existing one, or when PLAN.md needs to be associated with a project directory.
Set up, update, or delete a SageMaker Managed MLflow app	references/manage-mlflow/	User says "set up MLflow", "create MLflow app", "update my MLflow app", "delete my MLflow app", "I need an MLflow server", asks "what is SageMaker MLflow", or a workflow needs an MLflow backend and none is connected.
Diagnose a failing or unhealthy SageMaker endpoint	references/endpoint-diagnostics/	User reports endpoint errors, latency, inference failures, or a deployment that failed. "What's the status of my endpoint?", "Is my endpoint erroring?", "My endpoint failed — why?", "How many instances are running behind my endpoint?", "Is the latency my model or SageMaker?", "Show me the container logs for my endpoint." NOT for training-job issues, endpoint deletion, scaling changes, or new deployments.

Read the full file on GitHub · 51 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

9d ago First seen · 51 lines · 203 tokens per session scan A 2d67532aa2a7

Subscribe to this mod's changes

aws-ai-ml is a skill published in the GitHub repository aws/agent-toolkit-for-aws (2,559 stars, last pushed today), licensed Apache-2.0. It adds 203 tokens to every session and 1,426 once invoked, about $0.0010 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.

Cloud Data and AI DevOps and cloud

tensorrt-llm

High-throughput LLM inference on NVIDIA GPUs.

NousResearch/hermes-agent · 18 tokens

google-cloud-solution-guided-gke-ai-migration

Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…

google/skills · 157 tokens

agent-platform-tuning

Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).

google/skills · 64 tokens

agent-platform-endpoint-management

Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…

google/skills · 64 tokens

gke-inference

Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).

google/skills · 74 tokens

modal

Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.

K-Dense-AI/scientific-agent-skills · 65 tokens