AWS Agent Skills is a collection of local instructions that help coding agents reason about AWS cloud services and engineering tasks. It supports agents working with areas such as identity, compute, storage, serverless, databases, networking, and security. The catalogue contains 18 service-focused skills and one plugin for using these capabilities with coding agents.
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.
npx skills add itsmostafa/aws-agent-skills --skill snsgit clone --depth 1 https://github.com/itsmostafa/aws-agent-skillsWrote 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.
[](https://agentmods.dev/skills/itsmostafa/aws-agent-skills/sns)<a href="https://agentmods.dev/skills/itsmostafa/aws-agent-skills/sns"><img src="https://agentmods.dev/badge/skills/itsmostafa/aws-agent-skills/sns/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.
<a href="https://agentmods.dev/skills/itsmostafa/aws-agent-skills/sns"><img src="https://agentmods.dev/badge/skills/itsmostafa/aws-agent-skills/sns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00032 | $0.02534 |
| Opus 5 | $0.00016 | $0.01267 |
| Sonnet 5 | $0.00006 | $0.00507 |
| Haiku 4.5 | $0.00003 | $0.00253 |
Grade A, and why
sns 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 10d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AWS SNS
Amazon Simple Notification Service (SNS) is a fully managed pub/sub messaging service for application-to-application (A2A) and application-to-person (A2P) communication.
Table of Contents
Core Concepts
Topics
Named channels for publishing messages. Publishers send to topics, subscribers receive from topics.
Topic Types
| Type | Description | Use Case |
|---|---|---|
| Standard | Best-effort ordering, at-least-once | Most use cases |
| FIFO | Strict ordering, exactly-once | Order-sensitive |
Subscription Protocols
| Protocol | Description |
|---|---|
| Lambda | Invoke Lambda function |
| SQS | Send to SQS queue |
| HTTP/HTTPS | POST to endpoint |
| Send email | |
| SMS | Send text message |
| Application | Mobile push notification |
Message Filtering
Route messages to specific subscribers based on message attributes.
Common Patterns
Create Topic and Subscribe
AWS CLI:
# Create standard topic
aws sns create-topic --name my-topic
# Create FIFO topic
aws sns create-topic \
--name my-topic.fifo \
--attributes FifoTopic=true
# Subscribe Lambda
aws sns subscribe \
--topic-arn arn:aws:sns:us-east-1:123456789012:my-topic \
--protocol lambda \
--notification-endpoint arn:aws:lambda:us-east-1:123456789012:function:my-function
# Subscribe SQS
aws sns subscribe \
--topic-arn arn:aws:sns:us-east-1:123456789012:my-topic \
--protocol sqs \
--notification-endpoint arn:aws:sqs:us-east-1:123456789012:my-queue
# Subscribe email
aws sns subscribe \
--topic-arn arn:aws:sns:us-east-1:123456789012:my-topic \
--protocol email \
--notification-endpoint [email protected]
boto3:
import boto3
sns = boto3.client('sns')
# Create topic
response = sns.create_topic(Name='my-topic')
topic_arn = response['TopicArn']
# Subscribe Lambda
sns.subscribe(
TopicArn=topic_arn,
Protocol='lambda',
Endpoint='arn:aws:lambda:us-east-1:123456789012:function:my-function'
)
# Subscribe SQS with filter
sns.subscribe(
TopicArn=topic_arn,
Protocol='sqs',
Endpoint='arn:aws:sqs:us-east-1:123456789012:order-queue',
Attributes={
'FilterPolicy': '{"event_type": ["order_created", "order_updated"]}'
}
)
What ships with it
1 file 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.
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.
- 10d ago First seen · 405 lines · 32 tokens per session scan A ba2221095e33
sns is a skill published in the GitHub repository itsmostafa/aws-agent-skills (1,152 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 2,534 once invoked, about $0.0002 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.
Other skills, from other repositories
multi-tenant-llm-hosting
Design secure, multi-tenant LLM hosting platforms with tenant isolation, quotas, billing attribution, noisy-neighbor protection, and per-tenant policy controls.
aws-lambda
Build and deploy serverless functions on AWS Lambda. Configure triggers, manage permissions, and optimize performance. Use when implementing serverless applications.
gcp-cloud-functions
Deploy serverless functions on Google Cloud Functions. Configure triggers and manage deployments. Use when implementing serverless workloads on GCP.
cloudflare-workers
Build and deploy edge functions with Cloudflare Workers and Wrangler. Use for APIs, cron jobs, and edge middleware.
aws-cli
CLI-first AWS orchestration skill for Lambda, ECS/Fargate, and S3 workflows rooted in .☁️ runbooks.
azure-functions
Build serverless applications on Azure Functions. Configure triggers, bindings, and deployment. Use when implementing serverless workloads on Azure.