ai-gateway-guardrails

ai-gateway-guardrails is a skill for Claude Code from aws-samples/sample-oh-my-aidlcops. It costs 83 tokens per session (1,375 once invoked), scanned A, original, MIT-0.

A set of safety checks for an AI gateway, the service that receives requests and sends them to language models. It covers personal-data removal, prompt-injection and jailbreak detection, harmful-content filtering, and allowed-tool checks.

In plain words
What is it for?
Use it when configuring gateway-level protections with services such as Bedrock Guardrails, NeMo Guardrails, Llama Guard, Bifrost, or LiteLLM, with audit records in Langfuse.
Why use it?
It helps stop sensitive data, unsafe instructions, harmful content, or unapproved tool calls from passing through the gateway.

Skill for Claude Code ✓ vendor

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the ai-infra plugin — 6 skills, 2 commands, 4 agents shipped together

Good fit Use it when configuring gateway-level protections with services such as Bedrock Guardrails, NeMo Guardrails, Llama Guard, Bifrost, or LiteLLM, with audit records in Langfuse.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aws-samples/sample-oh-my-aidlcops/ai-gateway-guardrails
About the project

sample-oh-my-aidlcops is a plugin marketplace for Claude Code and Kiro that packages practices for managing the AWS AI-Driven Development Lifecycle, including design correctness and agent safety. It is for teams using agents to develop and operate AWS systems with approval checkpoints. Its catalogue contains the marketplace's plugins, skills, agents, and commands.

aws-samples/sample-oh-my-aidlcops · 19 stars · on GitHub · aws-samples.github.io

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 aws-samples/sample-oh-my-aidlcops --skill ai-gateway-guardrails
Clone the repo
git clone --depth 1 https://github.com/aws-samples/sample-oh-my-aidlcops

Made for: Claude Code.

Or install ai-infra, the plugin that ships this one along with the rest of its 6 skills, 2 commands, 4 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 ai-gateway-guardrails

README.md
[![agentmods](https://agentmods.dev/badge/skills/aws-samples/sample-oh-my-aidlcops/ai-gateway-guardrails/github.svg)](https://agentmods.dev/skills/aws-samples/sample-oh-my-aidlcops/ai-gateway-guardrails)
Your own site
<a href="https://agentmods.dev/skills/aws-samples/sample-oh-my-aidlcops/ai-gateway-guardrails"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-oh-my-aidlcops/ai-gateway-guardrails/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 ai-gateway-guardrails

Your own site · 80×15
<a href="https://agentmods.dev/skills/aws-samples/sample-oh-my-aidlcops/ai-gateway-guardrails"><img src="https://agentmods.dev/badge/skills/aws-samples/sample-oh-my-aidlcops/ai-gateway-guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,375 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00083 $0.01375
Opus 5 $0.00042 $0.00687
Sonnet 5 $0.00017 $0.00275
Haiku 4.5 $0.00008 $0.00137

Measured 11d ago against content hash 88e2d044571d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-gateway-guardrails scanned grade A with 1 finding 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 11d 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- `allowed-tools: ["*"]` — 전체 허용 = 정책 없음

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/ai-infra/skills/ai-gateway-guardrails/SKILL.md · 126 lines

The source is not reproduced here

Licensed MIT-0

The repository is licensed MIT-0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 11d ago First seen · 126 lines · 83 tokens per session scan A 88e2d044571d

Subscribe to this mod's changes

ai-gateway-guardrails is a skill published in the GitHub repository aws-samples/sample-oh-my-aidlcops (19 stars, last pushed today), licensed MIT-0. It adds 83 tokens to every session and 1,375 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.