setting-up-cloudwatch-alarm-notifications
An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: alerts, automation, aws, email, monitoring.
What it does
Sets up notification channels for CloudWatch alarms using SNS topics and subscriptions. Always use this skill when configuring alarm notifications — it creates encrypted SNS topics, configures topic policies for CloudWatch access, sets up email/SMS/webhook subscriptions, and links alarms to notification actions with proper security controls.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add aws/agent-toolkit-for-aws --skill setting-up-cloudwatch-alarm-notificationsOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/aws/agent-toolkit-for-aws
cp -r agent-toolkit-for-aws/skills/specialized-skills/operations-skills/setting-up-cloudwatch-alarm-notifications ~/.claude/skills/setting-up-cloudwatch-alarm-notificationsSafety box score
Grade C, moderate risk: 25 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill configures AWS CloudWatch alarm notification plumbing by creating SNS topics, subscriptions, topic policies, and alarm actions. The main risks are live AWS API changes, alert data leaving AWS to email/SMS/webhook endpoints, and a test step that intentionally flips alarms and can trigger real downstream notifications or automations.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 2 (moderate) | It directs the agent to execute AWS CLI commands via `call_aws`, including `aws sns create-topic`, `aws sns subscribe`, `aws cloudwatch put-metric-alarm`, and `aws cloudwatch set-alarm-state`. |
| Network access | 2 (moderate) | It creates SNS subscriptions for `email`, `sms`, and webhook endpoints, so notification payloads are sent off the machine/AWS account to external destinations. |
| Filesystem reach | 0 (none) | The skill only contains markdown guidance; it does not read, write, or delete local files outside the project. |
| Secrets & credentials | 0 (none) | It does not ask for passwords or access key material, and explicitly says `MUST NOT prompt to set, retrieve or use passwords`. |
| Privilege & persistence | 0 (none) | There is no sudo, service installation, shell startup modification, or other OS-level privilege change in the files. |
| Instruction hijack surface | 0 (none) | There is no hidden or remotely fetched instruction content, and the procedure does not tell the agent to ignore safeguards or conceal actions. |
| Irreversible actions | 3 (high) | Its purpose is to create and modify live AWS resources and send notifications, including `put-metric-alarm` and `set-alarm-state`, which can trigger real operational side effects. |
| Transparency | 0 (none) | All supplied files are readable markdown; there are no binaries, installers, or decoded-at-runtime blobs. |
Before installing
- Confirm the target AWS account, region, and alarm name; this skill will create SNS resources and change alarm actions.
- Check whether forcing the alarm into `ALARM` for testing is safe in this environment.
- Review the email/SMS/webhook endpoint carefully; notifications will be sent there.
- Record the current alarm configuration before allowing `put-metric-alarm` to run.
Rated 2026-10-19 by an automated review of 2 files from the skill's repository.
Source
- Repository
- aws/agent-toolkit-for-aws (all skills from this repository)
- Path
- skills/specialized-skills/operations-skills/setting-up-cloudwatch-alarm-notifications/SKILL.md
- Branch
- main
- Updated
- 2026-09-19
Related skills
- churn-prevention — When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies.
- cold-email — Write B2B cold emails and follow-up sequences that get replies.
- emails — When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program.
- loop-on-ci — Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
- marketing-loops — When the user wants to set up a recurring, self-running marketing workflow — a repeatable loop an AI agent runs on a cadence (weekly, daily.
- amazon-ses — Guides Amazon SES onboarding for domain-based email sending.