Agent Toolkit for AWS is a collection of AWS-supported MCP servers, skills, plugins, commands, and hooks that help AI coding agents build, deploy, and manage applications on AWS. It is used by developers working with AWS services through agents such as Claude Code, Codex, Cursor, and Kiro. The catalogue entries are the toolkit's own agent extensions for AWS development and operations.
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.
npx skills add aws/agent-toolkit-for-aws --skill operate-on-awsgit clone --depth 1 https://github.com/aws/agent-toolkit-for-awsWrote 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.
[](https://agentmods.dev/skills/aws/agent-toolkit-for-aws/operate-on-aws)<a href="https://agentmods.dev/skills/aws/agent-toolkit-for-aws/operate-on-aws"><img src="https://agentmods.dev/badge/skills/aws/agent-toolkit-for-aws/operate-on-aws/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.
<a href="https://agentmods.dev/skills/aws/agent-toolkit-for-aws/operate-on-aws"><img src="https://agentmods.dev/badge/skills/aws/agent-toolkit-for-aws/operate-on-aws.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00242 | $0.06798 |
| Opus 5.5 | $0.00097 | $0.02719 |
| Sonnet 5.5 | $0.00048 | $0.01360 |
| Haiku 4.5 | $0.00024 | $0.00680 |
Grade C, and why
operate-on-aws scanned grade C 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 3d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
If the user is mid-outage and nothing is connected, **do not silently start a setup flow** — but do not refuse either. Setting up while production is down might genuinely be the fastest path, and that is their How it starts
The opening of the file, as written. The whole thing — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operate on AWS — AWS DevOps Agent for startups
Last updated: 2026-10-08
Philosophy
Most early-stage startups ship to production with no dedicated operations engineer. The people who build the product are also the on-call rotation. AWS DevOps Agent investigates incidents autonomously, finds probable root cause, and proposes fixes — but it is metered, and on most startup accounts it is paid for with AWS Activate credits the founder budgeted against runway.
So this skill has three non-negotiable rules:
1. Never connect or enable AWS DevOps Agent without first telling the user what it costs. One line, then proceed — the default is to continue. If they object, stop.
2. Never enable anything that copies their source code out of their AWS account unless they ask for it. The default is off. Say that it is off and how to turn it on; do not ask them to choose.
3. Never grant the agent access to their AWS account without saying what that access is. One line on what the role allows and how to revoke it, then create it — see Phase 2.5.
A startup running on credits is spending money it has budgeted against runway. Nobody should learn what something costs from a bill. Tell them first, every time, including when they are in a hurry.
You are the AI tool. Do not tell the user to paste anything into an AI tool.
Investigations do not filter personal data. AWS states plainly that DevOps Agent "does not filter PII information when summarizing data gathered during investigations, recommendation evaluations, or chat responses", and recommends redacting PII before it reaches observability logs. So an investigation over logs containing user emails, addresses or tokens will surface them in its findings.
Raise this before the first investigation for anyone whose logs plausibly carry customer data — which at an early-stage startup is most of them. It is a one-line warning that costs nothing and prevents a genuinely bad surprise:
"One thing worth knowing: the agent doesn't strip personal data out of what it reads. If your logs carry customer emails or tokens, they can show up in the findings. Worth a look at what you're logging."
What ships with it
7 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.
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.
- 3d ago Changed · +7 lines cd6c09e74ade
- 8d ago Changed · -1 lines · +2 tokens per session 94281cfb2fbf
- 14d ago First seen · 470 lines · 240 tokens per session scan C 0050236135bf
operate-on-aws is a skill published in the GitHub repository aws/agent-toolkit-for-aws (2,886 stars, last pushed yesterday), licensed Apache-2.0. It adds 242 tokens to every session and 6,798 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other skills, from other repositories
gke-workload-troubleshooting
Diagnoses GKE workload failures (CrashLoopBackOff, OOMKilled, ImagePullBackOff, Pending, etc.) via logs and events. Use when pods fail to start or crash repeatedly. Don't use for GKE cluster infrastructure provisioning, node pool creation, or non-Kubernetes Google Cloud services.
gke-workload-scaling-troubleshooting
Diagnoses GKE HorizontalPodAutoscaler (HPA) failures — metrics showing as , FailedGetResourceMetric / FailedGetScale / FailedComputeMetricsReplicas events, missing Pod resource requests, custom/external metrics-pipeline breakage (FailedGetExternalMetric / FailedGetCustomMetric, unavailable metrics adapter…
gke-ai-troubleshooting-tpu-mxla-hang
Diagnose GKE Cloud TPU multi-slice training hangs (Megascale HANGDETECTED logs and hang monitored events) using the ML Diagnostics Megascale XLA (MXLA) Hang Analyzer (gcloud alpha mldiagnostics monitored-events) and 1-minute Cloud Monitoring multi-slice latency metrics (kubernetes.io/container/multislice/).…
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-node-unresponsive-timeout
Diagnose and mitigate GKE TPU or GPU nodes stuck in NotReady / NodeStatusUnknown ("Kubelet stopped posting node status") due to host kernel panics, hardware lockups, or disabled node auto-repair. Use when nodes stop heartbeating beyond the node auto-repair threshold and pods remain stuck in Terminating. Don't use for…