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 timwukp/agent-skills-best-practice --skill aws-well-architected-reviewgit clone --depth 1 https://github.com/timwukp/agent-skills-best-practiceWrote 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/timwukp/agent-skills-best-practice/aws-well-architected-review)<a href="https://agentmods.dev/skills/timwukp/agent-skills-best-practice/aws-well-architected-review"><img src="https://agentmods.dev/badge/skills/timwukp/agent-skills-best-practice/aws-well-architected-review/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/timwukp/agent-skills-best-practice/aws-well-architected-review"><img src="https://agentmods.dev/badge/skills/timwukp/agent-skills-best-practice/aws-well-architected-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00115 | $0.01065 |
| Opus 5 | $0.00057 | $0.00532 |
| Sonnet 5 | $0.00023 | $0.00213 |
| Haiku 4.5 | $0.00012 | $0.00106 |
Grade A, and why
aws-well-architected-review 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AWS Well-Architected Review
Run a lightweight Well-Architected review on a concrete artifact — an architecture diagram/description, Terraform/CDK/CloudFormation, or a design doc — and report risks the way the official framework does: per pillar, severity-rated, each with a specific remediation. This is an engineering review to catch issues early; it complements (does not replace) a formal Well-Architected Tool review with an AWS SA.
Pillar Selection
Load only what the change touches — typically 2-4 pillars, not all six:
| Change involves | Load |
|---|---|
| IAM, network exposure, data handling, secrets | references/security.md |
| Availability targets, failover, backups, DR | references/reliability.md |
| Instance/database sizing, scaling, latency paths | references/performance.md |
| Spend-relevant choices: sizing, storage classes, data transfer, commitment plans | references/cost.md |
| Deployment, observability, runbooks, IaC hygiene | references/operations.md |
| Region choice, instance generations, utilization, data lifecycle | references/sustainability.md |
When in doubt for a general "review this architecture" request, default to Security + Reliability + Cost — the three with the highest production-incident and bill impact.
Review Process
- Understand the workload. From the artifact (and one round of questions if needed): what it does, criticality (user-facing? revenue-path?), availability/RTO expectations, data sensitivity, and rough scale. Severity calibration depends on this — an unencrypted dev sandbox is not an unencrypted payments database.
- Select pillars per the table; state which you're skipping and why in one line each.
- Walk each loaded pillar's checklist against the artifact. For every gap, record: pillar, the specific resource/decision at fault, risk severity (High = likely incident/breach/major waste; Medium = degraded posture or growing risk), and a concrete remediation (the actual setting/service/change, not "improve security").
- Credit what's right. List notable good practices observed — a review that only criticizes loses the audience, and "what's already fine" is information the team needs.
- Deliver the report (format below), risks ordered by severity, with a top-3 "fix first" call-out.
What ships with it
8 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.
- 12d ago First seen · 76 lines · 115 tokens per session scan A aa1f0bf8d6fe
aws-well-architected-review is a skill published in the GitHub repository timwukp/agent-skills-best-practice (10 stars, last pushed 2d ago), licensed MIT. It adds 115 tokens to every session and 1,065 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
ec2
AWS EC2 virtual machine management — instances, security groups, key pairs, AMIs, EBS volumes, Auto Scaling Groups, Spot Instances, Session Manager, placement groups, and instance lifecycle automation. Trigger on ANY of these, even when EC2 isn't named explicitly: - Launching or provisioning: "spin up a server"…
ecs
AWS ECS container orchestration for running Docker containers. Use when deploying containerized applications, configuring task definitions, setting up services, managing clusters, or troubleshooting container issues.
cloudformation
AWS CloudFormation infrastructure as code for stack management. Use when writing templates, deploying stacks, managing drift, troubleshooting deployments, or organizing infrastructure with nested stacks.
cloudwatch
AWS CloudWatch monitoring for logs, metrics, alarms, and dashboards. Use when setting up monitoring, creating alarms, querying logs with Insights, configuring metric filters, building dashboards, or troubleshooting application issues.
eks
AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services.
eventbridge
AWS EventBridge serverless event bus for event-driven architectures. Use when creating rules, configuring event patterns, setting up scheduled events, integrating with SaaS, or building cross-account event routing.