aws

aws is a command for coding agents from d-padmanabhan/agent-engineering-handbook. It costs 20 tokens per session (430 once invoked), scanned A, original, MIT.

A command for designing, changing, or reviewing Amazon Web Services (AWS) infrastructure and applications, including Terraform or CloudFormation files.

In plain words
What is it for?
Planning AWS architectures, reviewing or modifying infrastructure-as-code, and investigating permission, networking, or service failures.
Why use it?
It sets rules for secure AWS work, such as limiting permissions, avoiding secrets in code, and showing the impact before changing real resources.

Command

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 commands/d-padmanabhan/agent-engineering-handbook/aws
Clone the repo
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbook

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/commands/d-padmanabhan/agent-engineering-handbook/aws.svg)](https://agentmods.dev/commands/d-padmanabhan/agent-engineering-handbook/aws)
Your own site
<a href="https://agentmods.dev/commands/d-padmanabhan/agent-engineering-handbook/aws"><img src="https://agentmods.dev/badge/commands/d-padmanabhan/agent-engineering-handbook/aws.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 430 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 $0.00020 $0.00430
Opus 5 $0.00010 $0.00215
Sonnet 5 $0.00004 $0.00086
Haiku 4.5 $0.00002 $0.00043

Measured 4d ago against content hash c8bcc596b0bc, 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 4d 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.

commands/aws.md · 56 lines

What it actually says

AWS MODE ACTIVATED

You are now in AWS MODE. Any AWS-related work MUST follow:

  • rules/410-aws.mdc (AWS platform engineering + best practices)
  • rules/100-core.mdc (minimal, production-ready changes)
  • rules/310-security.mdc (least privilege, no secrets)

Use this command when the user asks to:

  • Design AWS architecture or service usage
  • Modify/review AWS infrastructure code (Terraform/CloudFormation)
  • Debug AWS operational issues (permissions, networking, failures)

Guardrails (mandatory)

  • Default to least privilege and secure-by-default configurations.
  • Never embed credentials/secrets in code or docs.
  • If touching infra-as-code, follow the repo’s IaC rules (180-terraform.mdc, 170-cloudformation.mdc) as applicable.
  • For any action that would change real AWS resources, require explicit user authorization and show the plan/impact first.

Step 0: Determine intent (design vs implement vs review)

Infer intent from the user’s request. If ambiguous, ask ≤3 clarifying questions (account/region, service boundaries, security constraints, scale).

Design

  • Provide a minimal architecture plan (components, flows, IAM boundaries)
  • Call out security posture (networking, encryption, logging)
  • Prefer managed services and clear operational ownership

Modify / Implement

  • Keep diffs minimal and scoped
  • Add/adjust IAM only as needed (least privilege)
  • Ensure tagging conventions (if applicable)

Review

Prioritize:

  • Critical: public exposure, missing encryption, overly broad IAM, secrets handling, missing audit logging
  • Recommended: operability (alarms/logs), cost footguns, scaling defaults
  • Optional: naming/structure consistency

Done condition

End with:

  • Files changed (or “no changes made”)
  • How to validate (lint/plan) and expected operational behavior
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. 4d ago First seen · 56 lines · 20 tokens per session scan A c8bcc596b0bc

Subscribe to this mod's changes

aws is a command published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 430 once invoked, about $0.0001 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.