aws-cloudformation-iam

aws-cloudformation-iam is a skill for Claude Code from giuseppe-trisciuoglio/developer-kit. It costs 54 tokens per session (1,170 once invoked), scanned A, original, MIT.

A set of AWS CloudFormation patterns for defining IAM roles, policies, permission boundaries, and trust relationships. IAM is AWS’s access-control system for deciding who or what may use resources.

In plain words
What is it for?
Use it to create service roles, model cross-account access, define managed or inline policies, export role or policy identifiers, and review access-control changes.
Why use it?
It helps keep permissions limited, understandable, and reusable while separating who may assume a role from what that role may do. It also addresses cross-account access and risky wildcard permissions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the developer-kit-aws plugin — 19 skills, 3 agents shipped together

Good fit Use it to create service roles, model cross-account access, define managed or inline policies, export role or policy identifiers, and review access-control changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/giuseppe-trisciuoglio/developer-kit/aws-cloudformation-iam
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.

Any agent
npx skills add giuseppe-trisciuoglio/developer-kit --skill aws-cloudformation-iam
Clone the repo
git clone --depth 1 https://github.com/giuseppe-trisciuoglio/developer-kit

Made for: Claude Code.

Or install developer-kit-aws, the plugin that ships this one along with the rest of its 19 skills, 3 agents.

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-cloudformation-iam

README.md
[![agentmods](https://agentmods.dev/badge/skills/giuseppe-trisciuoglio/developer-kit/aws-cloudformation-iam/github.svg)](https://agentmods.dev/skills/giuseppe-trisciuoglio/developer-kit/aws-cloudformation-iam)
Your own site
<a href="https://agentmods.dev/skills/giuseppe-trisciuoglio/developer-kit/aws-cloudformation-iam"><img src="https://agentmods.dev/badge/skills/giuseppe-trisciuoglio/developer-kit/aws-cloudformation-iam/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 aws-cloudformation-iam

Your own site · 80×15
<a href="https://agentmods.dev/skills/giuseppe-trisciuoglio/developer-kit/aws-cloudformation-iam"><img src="https://agentmods.dev/badge/skills/giuseppe-trisciuoglio/developer-kit/aws-cloudformation-iam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,170 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00054 $0.01170
Opus 5 $0.00027 $0.00585
Sonnet 5 $0.00011 $0.00234
Haiku 4.5 $0.00005 $0.00117

Measured 9d ago against content hash e94b30992163, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

aws-cloudformation-iam 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 9d 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.

plugins/developer-kit-aws/skills/aws-cloudformation/aws-cloudformation-iam/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AWS CloudFormation IAM Security

Overview

Use this skill to model IAM with CloudFormation in a way that stays secure, auditable, and maintainable.

The most important design concerns are:

  • separating trust policies from permission policies
  • preferring roles over long-lived users wherever possible
  • keeping least-privilege boundaries readable and reusable

Do not treat SKILL.md as a full IAM encyclopedia. Use the bundled references for larger policy examples and service-specific variants.

When to Use

  • Creating IAM roles for Lambda, ECS, EC2, Step Functions, or other AWS services
  • Defining inline policies, managed policies, and permission boundaries in CloudFormation
  • Modeling cross-account assume-role access with constrained trust policies
  • Exporting IAM role ARNs or managed policy ARNs to downstream stacks
  • Reviewing wildcard permissions, boundary drift, or role replacement risk
  • Creating reusable IAM stacks for platform or application teams

Instructions

1. Define the trust boundary first

Identify who or what assumes the role (service principal, cross-account principal, or federated identity), then write the trust policy with explicit principals and conditions before adding permissions.

2. Grant the minimum permission set

Use inline policies for role-specific access; use managed policies for shared patterns across principals. Scope actions and resources tightly, and use conditions where possible.

3. Apply permission boundaries for delegated role creation

Use permission boundaries when teams create or extend roles in their own stacks, when guardrails are needed around privileged services (IAM, KMS, Organizations), or to separate maximum allowed permissions from application-specific policies.

Name roles and policies consistently so stack outputs and audits remain easy to trace.

4. Model cross-account access

For cross-account roles: trust only the exact source account or principal, add sts:ExternalId conditions when appropriate, keep permission and trust policies separate, and export only the ARNs that consuming accounts need.

Read the full file on GitHub · 151 lines

Files

What ships with it

2 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. 9d ago First seen · 151 lines · 54 tokens per session scan A e94b30992163

Subscribe to this mod's changes

aws-cloudformation-iam is a skill published in the GitHub repository giuseppe-trisciuoglio/developer-kit (343 stars, last pushed 21d ago), licensed MIT. It adds 54 tokens to every session and 1,170 once invoked, about $0.0003 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.