What is analyze-prow-job-test-failure?

A command that investigates a failed test in a Prow CI job by comparing its logs and source code with job artifacts and cluster events.

Use it to diagnose failed OpenShift tests, including failures involving management or hosted clusters, and to produce a structured Markdown report.

It brings test errors and possible cluster problems together, so you do not have to inspect many logs separately.

analyze-prow-job-test-failure — Command for Claude Code by wangke19

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.

Clone the repo

git clone --depth 1 https://github.com/wangke19/gemini-ai-helpers

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/analyze-prow-job-test-failure/github.svg)](https://agentmods.dev/commands/wangke19/gemini-ai-helpers/analyze-prow-job-test-failure)

Your own site

<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/analyze-prow-job-test-failure"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/analyze-prow-job-test-failure/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/commands/wangke19/gemini-ai-helpers/analyze-prow-job-test-failure"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/analyze-prow-job-test-failure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 967 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	$0.00013	$0.00967
Opus 5	$0.00006	$0.00483
Sonnet 5	$0.00003	$0.00193
Haiku 4.5	$0.00001	$0.00097

Measured 11d ago against content hash bf579f3b7c21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

analyze-prow-job-test-failure 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.

extensions/ci/commands/analyze-prow-job-test-failure.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Name

ci:analyze-prow-job-test-failure

Synopsis

Generate a test failure analysis for the given test:

/ci:analyze-prow-job-test-failure <prowjob-url> [test-name] [--fast]

Description

Analyze a failed test by inspecting the test code in the current project and artifacts in Prow CI job. This is done by invoking the "Prow Job Analyze Test Failure" skill.

The command provides comprehensive analysis by:

Examining test failure stack traces and source code
Analyzing test execution timeline and cluster events during the test
Optionally extracting and analyzing must-gather data for cluster-level diagnostics
HyperShift support: Detects and analyzes both management cluster and hosted cluster must-gather data
Correlating cluster issues (degraded operators, failing pods, node problems) with test failures
Enhanced output: Structured Markdown format with clear sections and artifact organization

User Experience

Default (comprehensive analysis):

/ci:analyze-prow-job-test-failure <url>

No test name needed — analyzes all failed CI steps from JUnit XML, build logs, and step artifacts
Detects must-gather availability
Provides correlated step + cluster analysis
This is the common case for multi-step CI workflows (e.g. HyperShift, bare-metal OADP jobs)

With specific test name:

/ci:analyze-prow-job-test-failure <url> <test-name>

Focuses analysis on the named test's stack trace and logs

Fast mode (skip must-gather):

/ci:analyze-prow-job-test-failure <url> [test-name] --fast

Skips must-gather detection and extraction only
Scope is preserved: test-level when test-name is provided, step-level across all failed CI steps when omitted
Faster results, but may miss cluster-level root causes

HyperShift Support

For HyperShift jobs with hosted clusters, the command automatically:

Detects HyperShift dump archives in various locations (dump-management-cluster, hypershift-mce-dump, run-e2e-local, etc.)
Extracts archives containing management and/or hosted cluster data
Splits data into separate directories for independent analysis
Detects hosted cluster data within archives (hostedcluster-* directory)
Provides separate diagnostic sections for each cluster
Correlates issues across both clusters in root cause analysis

Read the full file on GitHub · 92 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.

11d ago First seen · 92 lines · 13 tokens per session scan A bf579f3b7c21

Subscribe to this mod's changes

analyze-prow-job-test-failure is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 967 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.

Debugging Testing extentions gemini-cli openshift redhat

qa-changes

This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…

OpenHands/extensions · 63 tokens

analyze-prow-job-test-failure