A Google Cloud knowledge guide for building and running software on Google's cloud platform, including virtual machines, containers, databases, storage, and serverless services.

Use it when working with services such as Cloud Run, Google Kubernetes Engine, Cloud Functions, Compute Engine, App Engine, or Cloud Storage.

It gives the existing team roles a shared place to find Google Cloud-specific guidance and current reference material.

stack-gcp — Skill for Claude Code by e-t-y-b

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 e-t-y-b/etyb-skills --skill gcp

Clone the repo

git clone --depth 1 https://github.com/e-t-y-b/etyb-skills

Made for: Claude Code.

Or install etyb, the plugin that ships this one along with the rest of its 14 skills, 5 agents, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/gcp/github.svg)](https://agentmods.dev/skills/e-t-y-b/etyb-skills/gcp)

Your own site

<a href="https://agentmods.dev/skills/e-t-y-b/etyb-skills/gcp"><img src="https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/gcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/e-t-y-b/etyb-skills/gcp"><img src="https://agentmods.dev/badge/skills/e-t-y-b/etyb-skills/gcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 271 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,937 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.

Model	Per session	Once invoked
Fable 5.1	$0.00271	$0.03937
Opus 5	$0.00135	$0.01969
Sonnet 5	$0.00054	$0.00787
Haiku 4.5	$0.00027	$0.00394

Measured 11d ago against content hash ff3fe4f7e87a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

stack-gcp 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 11d 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.

stacks/gcp/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Cloud Platform Stack — Team Briefing

This is a knowledge overlay, not a new specialist. The existing ETYB team does the work — backend-architect writes the backend code, devops-engineer wires the deploys, security-engineer enforces the boundary. This pack tells each role where the current Google Cloud Platform knowledge lives.

Where the full briefing lives

The full Stack briefing lives in this same folder. Per-product and per-role pages are siblings of this SKILL.md. Every page carries last_verified_on stamps and authoritative-source URLs in its frontmatter; see skills/etyb/core/knowledge-currency.md for the drift-check protocol that uses them.

Stack briefing: stacks/gcp/index.md
Per-product pages: stacks/gcp/<product>.md — one per entry in products_covered above
Per-role views: stacks/gcp/<role>.md — one per role in applies_to_roles above

When ETYB is installed locally these are read directly from disk. For third-party agents without the install, the same content is reachable as raw markdown at https://raw.githubusercontent.com/e-t-y-b/etyb-skills/main/stacks/gcp/<page>.md.

When delegate_to_skills (frontmatter above) lists a first-party vendor MCP/skill that's installed in the user's environment, ETYB defers to it first. The in-repo Stack content is the curated fallback.

What changed in 2025-2026 that older training data misses

Critical context — an LLM with a 2024 cutoff will get these wrong:

Cloud Functions gen2 is now officially "Cloud Run functions" — same product, new branding (mid-2024). Gen1 is deprecated. Don't recommend gcloud functions deploy --gen2 in new docs; use the Cloud Run path.
Container Registry (gcr.io) is deprecated. Artifact Registry is the only path for new image pushes. The gcr.io hostname now redirects but new repos must live in Artifact Registry.
Deployment Manager end-of-support: December 31, 2025. If a customer is still running Deployment Manager, migration to Infrastructure Manager (managed Terraform) or self-managed Terraform is overdue, not aspirational.
Duet AI for Developers is now Gemini Code Assist (Feb 2024 rebrand). The backend swapped to Gemini 2.5 across 2025. Gemini Code Assist Agents (agentic mode) shipped in 2025-2026.
Generative AI App Builder → Vertex AI Agent Builder → now augmented by Agentspace and Conversational Agents. The agent product line has been renamed twice; older training will reach for the wrong console paths and SDK names.
Agentspace (2025) is Google's enterprise agent surface — search + agent assistant + connectors across Workspace/M365/Salesforce/etc. It is distinct from Agent Builder.
Memorystore default engine is Valkey, not Redis. Valkey 9.0 ships pipeline prefetching (+40% throughput) and SIMD BITCOUNT (+200%). Existing Redis tiers still work; new builds default to Valkey.
Spanner has a GraphQL endpoint and Spanner Graph (2024). Spanner is no longer just "expensive global SQL." Granular Processing Units start at 100 PU (~$65/month); old "minimum 1 node" pricing intuition is obsolete.
AlloyDB AI (2024-2025) ships pgvector + Vertex AI embedding integration in-engine. AlloyDB columnar engine accelerates analytical SQL on transactional data.
Cloud Run GPU is GA (NVIDIA L4) with RTX PRO 6000 Blackwell in Preview. Cloud Run with sidecars (GA) makes the OTel-collector-in-sidecar pattern trivial. Direct VPC egress (GA) replaces the old Serverless VPC Access connector for most cases. Cloud Run gen2 raised the HTTP timeout to 60 minutes (services), 24 hours (jobs).
Workload Identity Federation is the production answer for non-GCP workloads (GitHub Actions, AWS, on-prem). Service account keys are an audit red flag in 2026.
BigQuery Studio (2024-2025) is the unified SQL + notebook + Spark + Dataform IDE inside BigQuery. BigQuery has vector search GA, continuous queries GA, and a REMOTE MODEL syntax for Gemini calls in SQL.

Read the full file on GitHub · 135 lines

Files

What ships with it

52 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.

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.

11d ago First seen · 135 lines · 271 tokens per session scan A ff3fe4f7e87a

Subscribe to this mod's changes

stack-gcp is a skill published in the GitHub repository e-t-y-b/etyb-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 271 tokens to every session and 3,937 once invoked, about $0.0014 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.

Claude Code Cloud DevOps and cloud agentskills ai-agent architecture

architecture-diagram

Dark-themed SVG architecture/cloud/infra diagrams as HTML.

mateaix/mateclaw · 15 tokens

routine

Manage CocoRoutine Snowflake task scheduling. Usage: $routine list, $routine schedule --cadence , $routine disable , $routine delete .

Snowflake-Labs/cocoplus · 44 tokens

12-factor-apps

Perform 12-Factor App compliance analysis on any codebase. Use when evaluating application architecture, auditing SaaS applications, or reviewing cloud-native applications against the original 12-Factor methodology.

LeoYeAI/openclaw-master-skills · 43 tokens

agent-bom

Open security platform for agentic infrastructure — broad scanning plus MCP discovery, CVEs, blast radius, SBOMs, CIS benchmarks (AWS, Azure, GCP, Snowflake), OWASP/NIST/MITRE compliance, AISVS v1.0, MAESTRO layer tagging, and vector database security checks. Use when the user mentions vulnerability scanning, MCP…

LeoYeAI/openclaw-master-skills · 99 tokens

agent-bom-scan-infra

Scan infrastructure-as-code, cloud configurations, and find secrets. Use when: "check terraform", "scan kubernetes", "IaC", "find secrets", "scan dockerfile", "cloud security", "misconfigurations".

LeoYeAI/openclaw-master-skills · 55 tokens

aws-architecture-diagram

AWS architecture diagrams — generate visual network topology diagrams from live AWS infrastructure. Use when drawing AWS network diagrams, visualizing VPCs, mapping Transit Gateway topology, or generating architecture documentation.

automateyournetwork/netclaw · 43 tokens