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 niels-emmer/myace --skill well-architected-reviewgit clone --depth 1 https://github.com/niels-emmer/myaceWrote 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/niels-emmer/myace/well-architected-review)<a href="https://agentmods.dev/skills/niels-emmer/myace/well-architected-review"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/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/niels-emmer/myace/well-architected-review"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/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 | $0.00040 | $0.00765 |
| Opus 5 | $0.00020 | $0.00382 |
| Sonnet 5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
Well-Architected Pillar 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 8d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Every major cloud provider publishes a "well-architected" style framework — Azure's Well-Architected Framework, AWS's Well-Architected Framework, Google Cloud's architecture framework — and they converge on essentially the same handful of pillars, phrased slightly differently. The value isn't in citing a specific provider's document; it's in the habit of checking a change against all of them instead of only the one pillar that happened to motivate the change. This skill is a short walk-through of what to check per pillar, provider-agnostic.
When to use it
Before calling any nontrivial infrastructure change done — new resources, materially changed configuration of existing ones, anything that affects how the system is reached, scaled, or paid for. Skip it for genuinely cosmetic changes (renaming a variable with no resource impact).
The pillars, and what to actually check
Security. Does this change follow private-by-default networking and managed-identity-over-secrets? Does it grant any new permission, and is that permission scoped to what's needed? Does it introduce or remove a documented exception?
Reliability. Does this resource have a single point of failure it didn't have to have (no redundancy, no multi-zone/multi-region option considered)? If it fails, what notices, and how does recovery happen — automatically, or does someone have to intervene? Does the change affect any existing failover or backup path?
Cost. Does the resource size/tier match actual expected load, or is it a guess that should be revisited after real usage data exists? Is there a cheaper resource type or pricing model (reserved/committed vs. on-demand, serverless vs. always-on) that fits the workload's actual traffic pattern? Is the cost attributable to a specific cost-center tag so it shows up in the right place later?
Operational excellence. Can this change be deployed, rolled back, and monitored the same way the rest of the environment is — same pipeline, same alerting, same logging conventions — or does it introduce a one-off process? Is there a way to tell the resource is healthy without logging into a console by hand?
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.
- 8d ago First seen · 44 lines · 40 tokens per session scan A 04c905f8c3e5
Well-Architected Pillar Review is a skill published in the GitHub repository niels-emmer/myace (1 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 765 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
loom-kubernetes
Kubernetes deployment, cluster architecture, security, and operations.
loom-prometheus
Prometheus monitoring and alerting for cloud-native observability.
terraform-infrastructure
Structures, writes, and reviews Terraform infrastructure code. Covers module layout, remote state, workspace strategy, variable and secrets handling, CI plan/apply pipeline, naming conventions, and multi-region deployment patterns (provider aliases, per-region state, failover strategies), while delegating shared risk…
design-aws-terraform-iac
Designs AWS-targeted Terraform infrastructure plans before implementation. Focuses on service selection, module boundaries, state/backends, environment separation, security/compliance guardrails, acceptance criteria, and explicit risk/validation assumptions.
loom-terraform
Infrastructure as Code with Terraform/OpenTofu.
loom-karpenter
Kubernetes node autoscaling and cost optimization with Karpenter.