analyze-prow-job-install-failure

analyze-prow-job-install-failure is a command for Claude Code from wangke19/gemini-ai-helpers. It costs 10 tokens per session (1,788 once invoked), scanned A, original, Apache-2.0.

A command that investigates why an OpenShift installation failed in a Prow CI job by examining installer logs, collected log bundles, and system reports.

In plain words
What is it for?
Use it to diagnose failures during configuration, infrastructure setup, cluster startup or creation, and cluster-operator stability, then review the generated findings and next steps.
Why use it?
It focuses on the specific installation stage that failed instead of treating every installation failure as the same problem.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Good fit Use it to diagnose failures during configuration, infrastructure setup, cluster startup or creation, and cluster-operator stability, then review the generated findings and next steps.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/wangke19/gemini-ai-helpers/analyze-prow-job-install-failure
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.

agentmods badge for analyze-prow-job-install-failure

README.md
[![agentmods](https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/analyze-prow-job-install-failure/github.svg)](https://agentmods.dev/commands/wangke19/gemini-ai-helpers/analyze-prow-job-install-failure)
Your own site
<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/analyze-prow-job-install-failure"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/analyze-prow-job-install-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.

agentmods 80×15 button for analyze-prow-job-install-failure

Your own site · 80×15
<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/analyze-prow-job-install-failure"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/analyze-prow-job-install-failure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,788 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 $0.00010 $0.01788
Opus 5 $0.00005 $0.00894
Sonnet 5 $0.00002 $0.00358
Haiku 4.5 $0.00001 $0.00179

Measured 11d ago against content hash 61519a50601b, 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-install-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-install-failure.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Name

ci:analyze-prow-job-install-failure

Synopsis

/ci:analyze-prow-job-install-failure <prowjob-url>

Description

The ci:analyze-prow-job-install-failure command analyzes OpenShift installation failures in Prow CI jobs by downloading and examining installer logs, log bundles, and sosreports (for metal jobs). This command is specifically designed to debug failures in the "install should succeed: overall" test, which indicates that the installation process failed at some stage.

Important: All "install should succeed" tests have a specific suffix indicating the failure stage (configuration, infrastructure, cluster bootstrap, cluster creation, cluster operator stability, or other). The JUnit XML contains both the specific failure reason test (which fails) and the overall test (which also fails when any stage fails). This command analyzes the specific failure stage to provide targeted diagnostics.

The command accepts:

  • Prow job URL (required): URL to the failed CI job from prow.ci.openshift.org

It downloads relevant artifacts from Google Cloud Storage, analyzes them, and generates a comprehensive report with findings and recommended next steps.

Recognized Failure Modes

The command identifies the failure mode from junit_install.xml and tailors its analysis:

  • "install should succeed: configuration" - Extremely rare failure where install-config.yaml validation failed. Focus on installer log only.
  • "install should succeed: infrastructure" - Failed to create cloud resources. Usually due to cloud quota, rate limiting, or outages. Log bundle may not exist.
  • "install should succeed: cluster bootstrap" - Bootstrap node failed to start temporary control plane. Check bootkube logs in the bundle.
  • "install should succeed: cluster creation" - One or more operators unable to deploy. Check operator logs in gather-must-gather.
  • "install should succeed: cluster operator stability" - Operators never stabilized (stuck progressing/degraded). Check operator status and logs.
  • "install should succeed: other" - Unknown failure requiring comprehensive analysis of all available logs.

Read the full file on GitHub · 146 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. 11d ago First seen · 146 lines · 10 tokens per session scan A 61519a50601b

Subscribe to this mod's changes

analyze-prow-job-install-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 10 tokens to every session and 1,788 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.