aws

aws is a skill for Claude Code, Codex from neverinfamous/memory-journal-mcp. It costs 72 tokens per session (673 once invoked), scanned A, original, MIT.

A set of standards for designing and managing AWS, Amazon's cloud platform.

In plain words
What is it for?
Use it when working with AWS IAM, S3, EC2, Lambda, API Gateway, ECS, EKS, CloudFormation, CDK, or Terraform.
Why use it?
It helps reduce security and deployment errors involving permissions, secrets, serverless functions, and cloud infrastructure.

Skill for Claude CodeCodex

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 skills/neverinfamous/memory-journal-mcp/aws
Any agent
npx skills add neverinfamous/memory-journal-mcp --skill aws
Clone the repo
git clone --depth 1 https://github.com/neverinfamous/memory-journal-mcp

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/aws.svg)](https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/aws)
Your own site
<a href="https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/aws"><img src="https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/aws.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 673 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 $0.00072 $0.00673
Opus 5 $0.00036 $0.00336
Sonnet 5 $0.00014 $0.00135
Haiku 4.5 $0.00007 $0.00067

Measured 5d ago against content hash 45cdf08282c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aws 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 5d 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.

skills/aws/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Amazon Web Services (AWS) Best Practices

STOP. Your knowledge of AWS may be outdated. Prefer retrieval over pre-training for any version-sensitive AWS configuration. Fetch current documentation when in doubt.

Production-grade standards for designing, deploying, and managing infrastructure on AWS.

1. Security & IAM (Identity and Access Management)

  • Principle of Least Privilege (PoLP): Never use * (wildcard) actions or resources in IAM policies unless absolutely required (e.g., specific S3 list actions). Scope policies to specific ARNs and exact actions.
  • Root Account: Never use the root account for day-to-day operations. Use AWS SSO (IAM Identity Center) or assume roles.
  • Secrets Management: Never hardcode secrets in code or environment variables attached to instances. Always use AWS Secrets Manager or AWS Systems Manager Parameter Store (SSM).

2. Serverless (Lambda & API Gateway)

  • Cold Starts: Minimize cold starts in Lambda by keeping deployment packages small. For Node.js/TypeScript, use tools like esbuild to bundle and tree-shake code.
  • Concurrency: Set reserved concurrency for critical functions to ensure they always have execution capacity.
  • Idempotency: Lambda functions should be idempotent, especially when triggered by SQS, SNS, or EventBridge, as AWS guarantees at-least-once delivery (not exactly-once).

3. Storage & Databases (S3, DynamoDB, RDS)

  • S3 Security: ALWAYS enable "Block Public Access" at the bucket level unless serving a static website. Enforce server-side encryption (AES256 or aws:kms).
  • DynamoDB: Prefer single-table design when access patterns are strictly known. Use On-Demand capacity for unpredictable workloads and Provisioned capacity (with Auto Scaling) for predictable workloads to save costs.
  • RDS: Never place RDS instances in public subnets. They must reside in private subnets, accessed via Bastion Hosts, VPN, or Session Manager.

4. Networking (VPC)

  • Multi-AZ: Always deploy critical resources (NAT Gateways, RDS, ALB, ECS) across at least two Availability Zones for high availability.
  • Security Groups: Security Groups are stateful. Only allow necessary inbound ports (e.g., 443 for HTTPS). Do not open 0.0.0.0/0 on port 22 or 3306.

Read the full file on GitHub · 40 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. 5d ago First seen · 40 lines · 72 tokens per session scan A 45cdf08282c3

Subscribe to this mod's changes

aws is a skill published in the GitHub repository neverinfamous/memory-journal-mcp (20 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 673 once invoked, about $0.0004 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.