GCP Architecture Framework Pillar Review

GCP Architecture Framework Pillar Review is a skill for Claude Code, Codex from niels-emmer/myace. It costs 41 tokens per session (1,003 once invoked), scanned A, original, MIT.

A checklist for reviewing Google Cloud infrastructure against six design areas: operations, security, reliability, cost, performance, and sustainability.

In plain words
What is it for?
Use it before making a significant GCP infrastructure change that affects access, scaling, reliability, monitoring, performance, or cost.
Why use it?
It helps reveal risks in a Google Cloud change that a general infrastructure review may miss, such as unsuitable service settings or missing monitoring.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for aider. Also seen: mentions Codex; built for aider; mentions OpenCode.

Good fit Use it before making a significant GCP infrastructure change that affects access, scaling, reliability, monitoring, performance, or cost.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/niels-emmer/myace/gcp-waf-review
Install

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.

Any agent
npx skills add niels-emmer/myace --skill gcp-waf-review
Clone the repo
git clone --depth 1 https://github.com/niels-emmer/myace

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for GCP Architecture Framework Pillar Review

README.md
[![agentmods](https://agentmods.dev/badge/skills/niels-emmer/myace/gcp-waf-review/github.svg)](https://agentmods.dev/skills/niels-emmer/myace/gcp-waf-review)
Your own site
<a href="https://agentmods.dev/skills/niels-emmer/myace/gcp-waf-review"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/gcp-waf-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.

agentmods 80×15 button for GCP Architecture Framework Pillar Review

Your own site · 80×15
<a href="https://agentmods.dev/skills/niels-emmer/myace/gcp-waf-review"><img src="https://agentmods.dev/badge/skills/niels-emmer/myace/gcp-waf-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,003 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.01003
Opus 5 $0.00020 $0.00502
Sonnet 5 $0.00008 $0.00201
Haiku 4.5 $0.00004 $0.00100

Measured 9d ago against content hash b114f1d74b0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

GCP Architecture Framework 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 9d 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.

collections/additional/gcp/skills/gcp-waf-review/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

The Google Cloud Architecture Framework is Google Cloud's set of design principles for building reliable, secure, cost-optimized, operationally excellent, performant, and sustainable workloads on GCP. This skill is the GCP-specific companion to iac-expert's generic well-architected-review skill: it maps each pillar to the concrete GCP services and decisions that actually move the needle, so a review checks real GCP constructs rather than abstract principles.

When to use it

Before calling any nontrivial GCP infrastructure change done — new resources, materially changed configuration, anything that affects how the workload is reached, scaled, secured, or paid for. Skip it for genuinely cosmetic changes (a label fix, a variable rename with no resource impact).

The pillars, and what to actually check in GCP

Operational excellence. Can this change be deployed, rolled back, and monitored the same way as the rest of the environment — same pipeline (Cloud Build / GitHub Actions), same alerting (Cloud Monitoring), same logging (Cloud Logging, Cloud Audit Logs)? Is there a way to tell the resource is healthy without logging into the console by hand? Does it run as code (IaC) rather than click-ops, so it's reproducible?

Security, privacy, and compliance. Does this follow private-by-default networking (no public IPs, VPC firewall rules scoped to least access) and service-account-over-long-lived-keys? Does it grant any new IAM role, and is it scoped to least privilege rather than a broad roles/owner/* grant? Does it introduce or remove a documented exception? Is Security Command Center posture and Cloud Audit Logs coverage still intact?

Reliability. Does the resource have a single point of failure it didn't have to have? Consider multi-zone deployment (a managed instance group across zones, a regional Cloud SQL/Spanner instance, a global/regional load balancer in front of multiple backends), GCS versioning and object lifecycle for durable data, and Cloud SQL automated backups. If it fails, what notices and how does recovery happen — automatically (Cloud Monitoring alarms, managed instance group autoscaling, Cloud DNS failover) or does someone have to intervene? Does the change affect an existing backup path?

Read the full file on GitHub · 88 lines

Changes

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.

  1. 9d ago First seen · 88 lines · 41 tokens per session scan A b114f1d74b0f

Subscribe to this mod's changes

GCP Architecture Framework Pillar Review is a skill published in the GitHub repository niels-emmer/myace (1 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 1,003 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.