gcp-hcp: Skill for Claude Code

.claude/skills/walkthrough-hostedcluster-create/SKILL.md

walkthrough-hostedcluster-create is a skill for Claude Code from openshift-online/gcp-hcp. It costs 23 tokens per session (866 once invoked), scanned A, original, Apache-2.0.

A guided code-exploration workflow for tracing how a HostedCluster is created on Google Cloud. HostedCluster is a Kubernetes resource that describes a hosted control plane, while GKE is Google’s managed Kubernetes service.

In plain words
What is it for?
Use it to inspect the HyperShift repository, understand its HostedCluster types and Kubernetes custom resource definition, find validation rules, and trace Google Cloud-specific cluster creation.
Why use it?
It helps developers follow the entire creation path—from the API contract and validation to controller processing, GKE provisioning, and status updates—without guessing which code runs next.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is openshift-online/gcp-hcp's own configuration. It tells Claude Code how to work on gcp-hcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gcp-hcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to openshift-online/gcp-hcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/openshift-online/gcp-hcp/main/.claude/skills/walkthrough-hostedcluster-create/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/openshift-online/gcp-hcp

Made for: Claude Code.

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 walkthrough-hostedcluster-create

README.md
[![agentmods](https://agentmods.dev/badge/skills/openshift-online/gcp-hcp/walkthrough-hostedcluster-create/github.svg)](https://agentmods.dev/skills/openshift-online/gcp-hcp/walkthrough-hostedcluster-create)
Your own site
<a href="https://agentmods.dev/skills/openshift-online/gcp-hcp/walkthrough-hostedcluster-create"><img src="https://agentmods.dev/badge/skills/openshift-online/gcp-hcp/walkthrough-hostedcluster-create/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 walkthrough-hostedcluster-create

Your own site · 80×15
<a href="https://agentmods.dev/skills/openshift-online/gcp-hcp/walkthrough-hostedcluster-create"><img src="https://agentmods.dev/badge/skills/openshift-online/gcp-hcp/walkthrough-hostedcluster-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 866 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 $0.00023 $0.00866
Opus 5 $0.00012 $0.00433
Sonnet 5 $0.00005 $0.00173
Haiku 4.5 $0.00002 $0.00087

Measured 10d ago against content hash 77cfd45e548d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

walkthrough-hostedcluster-create 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.

.claude/skills/walkthrough-hostedcluster-create/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HostedCluster Create Flow

Trace the end-to-end flow of creating a HostedCluster on GCP — from API definition through controller reconciliation to GKE cluster provisioning and status updates.

Layer 1 — API Types

Start here. Find the HostedCluster API type definition in the hypershift repository. Show me:

  • The HostedClusterSpec and HostedClusterStatus structures
  • The GCP-specific platform configuration within the spec (look for the GCP platform type)
  • What GCP resources are encoded in the API types — what does a user declare when they want a cluster on GCP?
  • How the API types relate to the Kubernetes CRD that gets installed

Help me understand: the API types are the contract. Everything downstream is driven by what's declared here.

Layer 2 — Validation and Admission

Trace how HostedCluster creation requests are validated before they reach the controller. Find:

  • Webhook validators for the HostedCluster resource
  • GCP-specific validation logic — what GCP-specific fields are validated and why?
  • What preconditions must be met before a cluster can be created?
  • How validation errors are surfaced to the user

Help me understand: validation is the first line of defense. It catches misconfigurations before they become expensive reconciliation failures.

Layer 3 — Controller Reconciliation

This is the core of the system. Find the HostedCluster controller and trace its reconcile function. Show me:

  • How the controller detects a new HostedCluster (watch, queue, reconcile loop)
  • The structure of the reconciliation — is it a single function or broken into phases/sub-reconcilers?
  • How the controller delegates to platform-specific (GCP) logic
  • Error handling and retry patterns — what happens when a reconciliation step fails?
  • How the controller manages the lifecycle of child resources (what other Kubernetes objects does it create?)

Help me understand: the reconcile loop is the engine. It continuously drives the actual state toward the desired state declared in the API types.

Read the full file on GitHub · 81 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. 10d ago First seen · 81 lines · 23 tokens per session scan A 77cfd45e548d

Subscribe to this mod's changes

walkthrough-hostedcluster-create is a skill published in the GitHub repository openshift-online/gcp-hcp (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 866 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens