rhdh-operator-pr-test

rhdh-operator-pr-test is a skill for Claude Code, Codex from redhat-developer/rhdh-skills. It costs 99 tokens per session (683 once invoked), scanned A, original, Apache-2.0.

A procedure for testing a Red Hat Developer Hub operator pull request on a live OpenShift cluster. An operator is software that manages an application on OpenShift, and a pull request is a proposed code change.

In plain words
What is it for?
Use it to deploy CI-built operator images or bundles from a pull request, verify them with OpenShift’s command-line tool, and report the result.
Why use it?
It checks whether the proposed operator change works in a real cluster and records evidence, with rollback steps if needed.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the plugins plugin — 17 skills shipped together

Good fit Use it to deploy CI-built operator images or bundles from a pull request, verify them with OpenShift’s command-line tool, and report the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhat-developer/rhdh-skills/rhdh-operator-pr-test
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 redhat-developer/rhdh-skills --skill rhdh-operator-pr-test
Clone the repo
git clone --depth 1 https://github.com/redhat-developer/rhdh-skills

Made for: Claude Code, Codex.

Or install plugins, the plugin that ships this one along with the rest of its 17 skills.

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 rhdh-operator-pr-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhat-developer/rhdh-skills/rhdh-operator-pr-test.svg)](https://agentmods.dev/skills/redhat-developer/rhdh-skills/rhdh-operator-pr-test)
Your own site
<a href="https://agentmods.dev/skills/redhat-developer/rhdh-skills/rhdh-operator-pr-test"><img src="https://agentmods.dev/badge/skills/redhat-developer/rhdh-skills/rhdh-operator-pr-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 683 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 $0.00099 $0.00683
Opus 5 $0.00049 $0.00342
Sonnet 5 $0.00020 $0.00137
Haiku 4.5 $0.00010 $0.00068

Measured 8d ago against content hash 0fd027b36bcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rhdh-operator-pr-test 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.

skills/plugins/rhdh-operator-pr-test/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RHDH Operator PR Test

Deploy the PR's CI-built bundle onto a live cluster and verify the change there. GitHub code review belongs to /rhdh-pr-review.

Start here

Follow workflows/test-operator-pr.md from the top. Load references/operator-pr-images.md when extracting or validating CI image URLs.

Gates

Gate Required check If fail
Forge /rhdh-forge is installed and returns the PR Stop; name /setup-rhdh-skills install
oc oc is on PATH Stop; name /setup-rhdh-skills
Cluster oc whoami succeeds Stop; the human runs oc login, or follows the rhdh-test-instance provision path in the workflow
Repository The PR is redhat-developer/rhdh-operator Stop; this skill tests that repository only

Boundaries

  • /rhdh-forge owns GitHub reads. Invoke it by name with the PR URL or number and consume repository, number, state, files, diff, head and base refs, and comments. Do not parse the URL here or copy a fetch workflow.
  • /rhdh-pr-review owns analyzing the diff for merge comments and posting a GitHub review.
  • /rhdh-local owns a local compose runtime, not a live OpenShift cluster.
  • /rhdh-overlay owns overlay PR artifact checks, not operator bundles.
  • /rhdh-context locates an RHDH checkout when a local rhdh-test-instance tree is needed. Do not add it as a catalog dependency.

Writes

Posting a /test comment, applying or deleting cluster resources, and deploying or rolling back an RHDH instance are external writes: invoke /mutation-gate and follow it. A cluster operation's target names the namespace; a comment's target names the repository and PR number. A request to test approves no write.

Deploy the full PR bundle or manifests, not only the operator binary image. Preserve the original cluster state and report it with cleanup.

Completion

Complete when the report names the PR and images used, one result per live check, the overall verdict, the deployed bundle or manifests, original and final cluster state, rollback commands, cleanup status, and the outcome of every approved write including skipped ones. Do not cache cluster state inside the skill directory.

Read the full file on GitHub · 61 lines

Files

What ships with it

3 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.

  1. 8d ago First seen · 61 lines · 99 tokens per session scan A 0fd027b36bcf

Subscribe to this mod's changes

rhdh-operator-pr-test is a skill published in the GitHub repository redhat-developer/rhdh-skills (16 stars, last pushed 4d ago), licensed Apache-2.0. It adds 99 tokens to every session and 683 once invoked, about $0.0005 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 2026-08-30.