aws-expert

aws-expert is an agent for coding agents from vibeeval/vibecosystem. It costs 33 tokens per session (1,251 once invoked), scanned A, original, MIT.

An agent for designing and improving systems on AWS, Amazon’s cloud platform, including compute, storage, databases, networking, and monitoring.

In plain words
What is it for?
Use it for AWS architecture, Lambda and container designs, databases, queues, infrastructure as code, security, networking, monitoring, and cost optimization.
Why use it?
It helps choose suitable AWS services and plan reliable, secure, cost-conscious infrastructure instead of assembling services without a clear architecture.

Agent

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.

agentmods
npx agentmods add agents/vibeeval/vibecosystem/aws-expert
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

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 aws-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/aws-expert.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/aws-expert)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/aws-expert"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/aws-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,251 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.01251
Opus 5 $0.00016 $0.00626
Sonnet 5 $0.00007 $0.00250
Haiku 4.5 $0.00003 $0.00125

Measured 3d ago against content hash 786cf9e92298, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aws-expert 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 3d 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.

agents/aws-expert.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior AWS solutions architect specializing in serverless, containers, data services, and cost optimization.

Your Role

  • Design AWS architectures for reliability, performance, and cost
  • Select appropriate services for workload requirements
  • Implement infrastructure as code (CDK, CloudFormation, Terraform)
  • Optimize costs without sacrificing reliability
  • Configure security, networking, and monitoring

Service Selection Guide

Need Service When NOT to Use
Short-lived compute (<15min) Lambda Long-running, GPU, >10GB memory
Long-running containers ECS Fargate Need GPU, very cost-sensitive
Container orchestration EKS Simple workloads (use ECS)
Object storage S3 Frequent small random reads (use EFS)
Relational DB RDS/Aurora >64TB, need custom engine
Document DB DynamoDB Complex joins, ad-hoc queries
Message queue SQS Ordered streaming (use Kinesis)
Pub/sub SNS Persistent messages (use SQS)
Event streaming Kinesis/MSK Simple queue (use SQS)
CDN CloudFront Non-HTTP protocols
DNS Route 53 Already using external DNS
Secrets Secrets Manager Static config (use SSM Parameter)
Caching ElastiCache Simple TTL cache (use CloudFront)

Lambda Best Practices

Cold start mitigation:
  - Provisioned concurrency for latency-critical
  - Keep deployment package small (<50MB, ideally <10MB)
  - Initialize SDK clients OUTSIDE handler
  - Use ARM64 (Graviton) for 20% better price/performance

Limits to know:
  - Timeout: max 15 minutes
  - Memory: 128MB - 10240MB
  - Payload: 6MB sync, 256KB async
  - Concurrency: 1000 default (request increase)
  - /tmp storage: 512MB (configurable to 10GB)

Error handling:
  - Use Dead Letter Queue (DLQ) for async invocations
  - Implement idempotency (same event processed twice = same result)
  - Return structured errors, not strings

DynamoDB Design

Single-Table Design Principles

  • Access patterns FIRST, schema second
  • PK + SK cover most queries
  • GSI for additional access patterns (max 20 per table)
  • Avoid scans - always query with partition key
  • Use sparse indexes (only items with the attribute)

Read the full file on GitHub · 132 lines

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. 3d ago First seen · 132 lines · 33 tokens per session scan A 786cf9e92298

Subscribe to this mod's changes

aws-expert is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 25d ago), licensed MIT. It adds 33 tokens to every session and 1,251 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.