hypershift: Skill for Claude Code

.claude/skills/create-cpo-override/SKILL.md

create-cpo-override is a skill for Claude Code from openshift/hypershift. It costs 22 tokens per session (3,585 once invoked), scanned A, original, Apache-2.0.

An interactive procedure for creating image override entries for the control-plane-operator in a HyperShift Operator repository. It discovers container images, verifies fixes, edits a YAML configuration file, and prepares a pull request.

In plain words
What is it for?
Use it when adding or updating entries in `controlplaneoperator-overrides/assets/overrides.yaml`, including image inspection, fix verification, YAML editing, and pull-request preparation.
Why use it?
It brings image discovery and validation into one repeatable process and helps ensure the resulting override matches the repository’s validation checks.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

This is openshift/hypershift's own configuration. It tells Claude Code how to work on hypershift 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 hypershift configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is go test ./hypershift-operator/controlplaneoperator-overrides/....

Part of the hypershift plugin — 22 skills, 5 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to openshift/hypershift. 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/hypershift/main/.claude/skills/create-cpo-override/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/openshift/hypershift

Made for: Claude Code.

Or install hypershift, the plugin that ships this one along with the rest of its 22 skills, 5 agents.

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 create-cpo-override

README.md
[![agentmods](https://agentmods.dev/badge/skills/openshift/hypershift/create-cpo-override.svg)](https://agentmods.dev/skills/openshift/hypershift/create-cpo-override)
Your own site
<a href="https://agentmods.dev/skills/openshift/hypershift/create-cpo-override"><img src="https://agentmods.dev/badge/skills/openshift/hypershift/create-cpo-override.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Supply Chain · line 89
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • high Supply Chain · line 176
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • medium Data Exfiltration · line 90
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 177
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00022 $0.03585
Opus 5 $0.00011 $0.01792
Sonnet 5 $0.00004 $0.00717
Haiku 4.5 $0.00002 $0.00359

Measured 8d ago against content hash 7f02b0b7c8f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

create-cpo-override scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sH 'Accept: application/json' \
.claude/skills/create-cpo-override/SKILL.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create CPO Override

Synopsis

/create-cpo-override

Description

Interactively creates control-plane-operator (CPO) image override entries in hypershift-operator/controlplaneoperator-overrides/assets/overrides.yaml. Automates image discovery, fix verification, YAML editing, and PR preparation so the result is compatible with /validate-pr-override-images.

Prerequisites

  • skopeo installed
  • oc installed (for oc adm release info)
  • gh CLI authenticated
  • Local git repo has relevant release branches fetched (git fetch --all)
  • Internet access to quay.io and the Cincinnati API

Implementation

Follow the steps below in order. Each step builds on the previous one. Use AskUserQuestion for multi-choice prompts where indicated. For free-form inputs, ask the user directly in conversation.


Step 0 — Detect pull secret

Many OCP payload images require authentication. Before any image operations, probe for a working pull secret:

  1. Try a lightweight skopeo inspect against a known release payload image (e.g. quay.io/openshift-release-dev/ocp-release:4.18.0-multi). If it succeeds, the container runtime's default auth is sufficient — no extra flags needed.
  2. If that fails, check if $PULL_SECRET is set and points to an existing file. If so, retry with --authfile "$PULL_SECRET" (and use -a "$PULL_SECRET" for oc adm release info). Use this authfile for all subsequent image operations.
  3. If neither works, ask the user to provide a path to a pull secret file. If they don't have one, warn that payload-sourced images (Sources 1 & 2) will be unavailable and only Konflux images (Source 3, public on quay.io/redhat-user-workloads/) can be resolved automatically.

Step 1 — Gather inputs

Collect the following from the user. Ask all questions up front (or in logical groups) rather than one at a time.

1a. Platform(s)

Ask the user which platform(s) to override.

Options: aws, azure, or both.

Read the full file on GitHub · 400 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. 8d ago First seen · 400 lines · 22 tokens per session scan A 7f02b0b7c8f0

Subscribe to this mod's changes

create-cpo-override is a skill published in the GitHub repository openshift/hypershift (540 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 3,585 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

compute-env-setup

Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.

companion-inc/feynman · 45 tokens

securing-kubernetes-on-cloud

This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…

xalgorix/xalgorix · 80 tokens

detecting-privilege-escalation-in-kubernetes-pods

Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.

xalgorix/xalgorix · 40 tokens

implementing-rbac-hardening-for-kubernetes

Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.

xalgorix/xalgorix · 41 tokens

docker-socket-mount

Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.

PurpleAILAB/Decepticon · 67 tokens