agentmods.dev

sample-sagemaker-agentic-model-deployment: Skill for Kiro

.kiro/skills/sagemaker-deploy/SKILL.md

sagemaker-deploy is a skill for Kiro from aws-samples/sample-sagemaker-agentic-model-deployment. It costs 67 tokens per session (2,445 once invoked), scanned A, original, MIT-0.

A deployment tool for supported open-weight Hugging Face models, which are models whose weights can be downloaded and run by others. It transfers a model to Amazon S3 and deploys it to a real-time Amazon SageMaker AI endpoint using vLLM or SGLang containers.

In plain words
What is it for?
Use it to stage models in S3, create and smoke-test SageMaker endpoints, and remove the deployed endpoint when finished.
Why use it?
It covers the path from model files to a live SageMaker endpoint, including a basic test and cleanup after deployment.

Skill for Kiro ✓ vendor

Written for Kiro: installed under .kiro/.

This is aws-samples/sample-sagemaker-agentic-model-deployment's own configuration. It tells Kiro how to work on sample-sagemaker-agentic-model-deployment itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sample-sagemaker-agentic-model-deployment configures →

not rated 5repo 3mo ago A scan 67 tokens MIT-0
View source ↗ aws-samples/sample-sagemaker-agentic-model-deployment
About the project

sample-sagemaker-agentic-model-deployment is a coding-agent workflow that takes an open-weight model from a public checkpoint to a deployed, benchmarked, and optimized endpoint on Amazon SageMaker AI. It is for automating model staging, serving-configuration selection, deployment, benchmarking, and optimization without manually writing the surrounding API and polling code. Its skills and instruction define the portable agent workflow.

aws-samples/sample-sagemaker-agentic-model-deployment · 5 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to aws-samples/sample-sagemaker-agentic-model-deployment. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aws-samples/sample-sagemaker-agentic-model-deployment/main/.kiro/skills/sagemaker-deploy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aws-samples/sample-sagemaker-agentic-model-deployment

Made for: Kiro.

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.

agentmods badge for sagemaker-deploy

README.md
[![agentmods](https://agentmods.dev/badge/skills/aws-samples/sample-sagemaker-agentic-model-deployment/sagemaker-deploy/github.svg)](https://agentmods.dev/skills/aws-samples/sample-sagemaker-agentic-model-deployment/sagemaker-deploy)
Your own site
<a href="https://agentmods.dev/skills/aws-samples/sample-sagemaker-agentic-model-deployment/sagemaker-deploy"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-sagemaker-agentic-model-deployment/sagemaker-deploy/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.

agentmods 80×15 button for sagemaker-deploy

Your own site · 80×15
<a href="https://agentmods.dev/skills/aws-samples/sample-sagemaker-agentic-model-deployment/sagemaker-deploy"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-sagemaker-agentic-model-deployment/sagemaker-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,445 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.
Origin unknown 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.02445
Opus 5.5 $0.00027 $0.00978
Sonnet 5.5 $0.00013 $0.00489
Haiku 4.5 $0.00007 $0.00245

Measured 2mo ago against content hash 742e0287c5e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sagemaker-deploy 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 2mo ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/config.py, scripts/deploy.py, scripts/smoke_test.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.

.kiro/skills/sagemaker-deploy/SKILL.md · 230 lines

The source is not reproduced here

Licensed MIT-0

The repository is licensed MIT-0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

5 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.

  1. 2mo ago First seen · 230 lines · 67 tokens per session scan A 742e0287c5e0

Subscribe to this mod's changes

sagemaker-deploy is a skill published in the GitHub repository aws-samples/sample-sagemaker-agentic-model-deployment (5 stars, last pushed 3mo ago), licensed MIT-0. It adds 67 tokens to every session and 2,445 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

CloudData and AIDevOps and cloud
Related

sagemaker-deploy compared with skills from other repositories

sagemaker-deploy next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sagemaker-deployaws-samples/sample-sagemaker-agentic-model-deploymentSkill53mo agoMIT-0A67Kiro
tensorrt-llmNousResearch/hermes-agentSkill261ktodayMITA18Claude Code, Codex
agent-platform-tuninggoogle/skillsSkill22kyesterdayApache-2.0A64Claude Code, Codex
google-cloud-solution-guided-gke-ai-migrationgoogle/skillsSkill22kyesterdayApache-2.0A157Claude Code, Codex
apigee-agent-gateway-governancegoogle/skillsSkill22kyesterdayApache-2.0A222Claude Code, Codex
modalK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA65Claude Code, Codex
gke-inferencegoogle/skillsSkill22kyesterdayApache-2.0A119Claude Code, Codex