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 arjunprabhulal/devops-skills --skill well-architected-reviewgit clone --depth 1 https://github.com/arjunprabhulal/devops-skillsWrote 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/arjunprabhulal/devops-skills/well-architected-review)<a href="https://agentmods.dev/skills/arjunprabhulal/devops-skills/well-architected-review"><img src="https://agentmods.dev/badge/skills/arjunprabhulal/devops-skills/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/arjunprabhulal/devops-skills/well-architected-review"><img src="https://agentmods.dev/badge/skills/arjunprabhulal/devops-skills/well-architected-review.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 | $0.00115 | $0.01200 |
| Opus 5 | $0.00057 | $0.00600 |
| Sonnet 5 | $0.00023 | $0.00240 |
| Haiku 4.5 | $0.00012 | $0.00120 |
Grade A, and why
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 10d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Well-Architected Review
A well-architected review is worthless if it produces a scored checklist nobody acts on. The pillars — reliability, security, cost, performance, operational excellence, sustainability — exist in tension with each other, and the point of the review is to surface where a system has silently picked a tradeoff nobody signed off on, then rank what to fix.
Treat the review as a prioritization exercise, not a grading exercise. A review that doesn't end in an ordered, owned list of changes was not worth running.
For the full pillar-by-pillar question checklist, read references/review-checklist.md.
1. Scope the review to a system, not the whole estate
A review of "everything" produces shallow findings on everything and depth on nothing. Pick one system or one bounded set of services, understand its actual traffic and failure history, and review that deeply. Repeat for other systems on a cadence rather than trying to cover the whole estate in one pass.
Done when: the review's scope and boundary are written down before the first pillar is assessed.
2. Assess each pillar against evidence, not intent
For each pillar, ask what actually happens, not what the design intends:
- Reliability — has the stated failure domain (see
cloud-architecture) actually been tested, and doesdisaster-recoveryandchaos-engineeringcoverage exist for it? - Security — is access scoped by
iam-access-management, are secrets handled persecrets-management, hasvulnerability-managementrun recently? - Cost — does spend match the
cost-optimizationandresource-taggingexpectations, or has it drifted? - Performance — is there
load-testingevidence at expected peak, not just steady state? - Operational excellence — do
runbooksexist and match reality, ison-call-managementsane for this system's incident volume? - Sustainability — is compute and storage rightsized (
rightsizing), or is idle capacity running because nobody's looked?
What ships with it
1 file 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.
- 10d ago First seen · 99 lines · 115 tokens per session scan A 2fa71af3fe28
well-architected-review is a skill published in the GitHub repository arjunprabhulal/devops-skills (4 stars, last pushed 16d ago), licensed MIT. It adds 115 tokens to every session and 1,200 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
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-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-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-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-metrics-monitoring
Monitors and troubleshoots GKE TPU workloads, nodes, and node pools using GKE system metrics and PromQL. Use when monitoring TensorCore duty cycle, TPU memory, node readiness, multi-host TPU node pool availability, host maintenance or preemption interruptions, and calculating MTTR or MTBI metrics for GKE TPUs. Don't…
datalineage-summary
Summarizes Google Cloud Data Lineage graphs to help users debug data quality issues and understand data provenance for BQ/GCS. Use when summarizing upstream and downstream data flows, and presenting complex lineage data as an intuitive Markdown report. Don't use for generic BigQuery queries, editing lineage…