cloudwatch

cloudwatch is a skill for Claude Code, Codex from Arvo-AI/aurora. It costs 22 tokens per session (453 once invoked), scanned A, original, Apache-2.0.

An integration that receives Amazon CloudWatch alarm notifications through AWS SNS webhooks and creates incidents automatically. CloudWatch is AWS's service for monitoring cloud resources and metrics.

In plain words
What is it for?
It helps investigate alarms involving EC2 servers, RDS databases, Lambda functions, or EKS clusters, including their metrics, logs, alarm history, and related incidents.
Why use it?
It turns monitoring alarms into incidents without someone having to copy them by hand. It also gives the agent context for investigating the affected AWS resource, logs, and related incidents.

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/arvo-ai/aurora/cloudwatch
Any agent
npx skills add Arvo-AI/aurora --skill cloudwatch
Clone the repo
git clone --depth 1 https://github.com/Arvo-AI/aurora

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 cloudwatch

README.md
[![agentmods](https://agentmods.dev/badge/skills/arvo-ai/aurora/cloudwatch.svg)](https://agentmods.dev/skills/arvo-ai/aurora/cloudwatch)
Your own site
<a href="https://agentmods.dev/skills/arvo-ai/aurora/cloudwatch"><img src="https://agentmods.dev/badge/skills/arvo-ai/aurora/cloudwatch.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 453 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 $0.00022 $0.00453
Opus 5 $0.00011 $0.00227
Sonnet 5 $0.00004 $0.00091
Haiku 4.5 $0.00002 $0.00045

Measured 4d ago against content hash 39d18515cffc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloudwatch 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.

server/chat/backend/agent/skills/integrations/cloudwatch/SKILL.md · 59 lines

What it actually says

CloudWatch Integration

Overview

Amazon CloudWatch alarm integration. Aurora receives alarm state-change notifications from CloudWatch via AWS SNS webhooks and creates incidents automatically.

Instructions

IMPORTANT — NO CLI SUPPORT

  • Do NOT use cloud_exec('cloudwatch', ...) — there is no CloudWatch CLI connector.
  • You CAN use cloud_exec('aws', ...) to query CloudWatch metrics and logs via the AWS CLI.

WHAT YOU CAN DO

  • Investigate infrastructure: If an alarm references a specific AWS resource (EC2, RDS, Lambda, EKS), use the AWS cloud provider tool (cloud_exec with 'aws') to investigate.

CRITICAL RULES

  • NEVER call cloud_exec with provider='cloudwatch' — it will fail.
  • Use the alert context already available in the conversation.
  • For deeper investigation, use the AWS provider tools for the affected resource.

RCA Investigation Workflow (read-only)

During RCA the agent may:

  • Query CloudWatch alarms history for the affected account/region
  • Cross-reference with EC2, RDS, Lambda, EKS metrics for the affected resource
  • Look up related incidents with the same alarm_name
  • Check AWS CloudWatch Logs for errors near the alarm fire time

The agent must never write or modify CloudWatch alarms during RCA.

Alarm State Mapping

CloudWatch State Aurora Behavior
ALARM Creates incident — severity high (or critical if "critical" in alarm name)
INSUFFICIENT_DATA No incident created (state recorded only)
OK Resolves matching open incident (no new incident created)
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 · 59 lines · 22 tokens per session scan A 39d18515cffc

Subscribe to this mod's changes

cloudwatch is a skill published in the GitHub repository Arvo-AI/aurora (404 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 453 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.

Related

Other skills, from other repositories