review-ci

review-ci is a command for Claude Code from lyarwood/kubevirt-ai-helpers. It costs 13 tokens per session (1,363 once invoked), scanned A, original, Apache-2.0.

A command that investigates failed automated checks for a KubeVirt pull request. A pull request is a proposed code change, and CI is the system that builds and tests it automatically.

In plain words
What is it for?
Use it to summarize job status, group failures such as builds or tests, detect possible flaky tests, and suggest fixes.
Why use it?
It gathers scattered job results and logs so developers can identify the likely cause instead of debugging each failure blindly.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the kubevirt plugin — 4 skills, 17 commands shipped together

Good fit Use it to summarize job status, group failures such as builds or tests, detect possible flaky tests, and suggest fixes.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/lyarwood/kubevirt-ai-helpers/review-ci
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/lyarwood/kubevirt-ai-helpers

Made for: Claude Code.

Or install kubevirt, the plugin that ships this one along with the rest of its 4 skills, 17 commands.

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 review-ci

README.md
[![agentmods](https://agentmods.dev/badge/commands/lyarwood/kubevirt-ai-helpers/review-ci/github.svg)](https://agentmods.dev/commands/lyarwood/kubevirt-ai-helpers/review-ci)
Your own site
<a href="https://agentmods.dev/commands/lyarwood/kubevirt-ai-helpers/review-ci"><img src="https://agentmods.dev/badge/commands/lyarwood/kubevirt-ai-helpers/review-ci/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 review-ci

Your own site · 80×15
<a href="https://agentmods.dev/commands/lyarwood/kubevirt-ai-helpers/review-ci"><img src="https://agentmods.dev/badge/commands/lyarwood/kubevirt-ai-helpers/review-ci.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 1,363 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 $0.00013 $0.01363
Opus 5 $0.00006 $0.00681
Sonnet 5 $0.00003 $0.00273
Haiku 4.5 $0.00001 $0.00136

Measured 12d ago against content hash 7cf48cb3df26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-ci 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 12d 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.

plugins/kubevirt/commands/review-ci.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Name

kubevirt:review-ci

Synopsis

/kubevirt:review-ci <pr-number-or-url>

Description

The kubevirt:review-ci command analyzes CI failures for a KubeVirt pull request, providing structured analysis of failed jobs, root cause identification, and remediation suggestions.

This command is designed to help developers quickly understand and address CI failures by:

Analysis Capabilities

  1. Job Status Overview: Summarize all CI jobs and their current status
  2. Failure Categorization: Group failures by type (build, unit test, e2e test, lint, etc.)
  3. Root Cause Analysis: Extract relevant error messages and stack traces from logs
  4. Flaky Test Detection: Identify tests with known flaky behavior patterns
  5. Remediation Suggestions: Provide actionable steps to address each failure type

Failure Categories

The command categorizes failures into these types:

Build Failures
  • Compilation errors
  • Dependency resolution issues
  • Container image build failures
Unit Test Failures
  • Test assertion failures
  • Test timeouts
  • Missing test dependencies
E2E Test Failures
  • Infrastructure issues (cluster provisioning, network)
  • Test timeouts and flaky tests
  • Actual test assertion failures
  • Resource cleanup failures
Lint/Static Analysis Failures
  • golangci-lint violations
  • gofmt/goimports issues
  • shellcheck failures
Other Failures
  • Prow infrastructure issues
  • Quota/resource exhaustion
  • Network connectivity problems

Implementation

Phase 1: Gather CI Status

  1. Parse the PR argument to extract the PR number and repository (defaults to kubevirt/kubevirt)
  2. Use gh pr view <pr-number> --repo <repo> --json statusCheckRollup,commits,headRefName to get:
    • All CI check statuses
    • The head commit SHA for linking to specific job runs
    • The branch name for context
  3. Identify all failed checks from the status check rollup
  4. For each failed check, extract the job name and failure context

Phase 2: Fetch Failure Logs

  1. For GitHub Actions workflows:
    • Use gh run list --repo <repo> --branch <branch> --json databaseId,name,status,conclusion to find failed runs
    • Use gh run view <run-id> --repo <repo> --log-failed to get failure logs
  2. For Prow jobs (detected by check context containing "prow.ci.openshift.org"):
    • Extract the Prow job URL from the check details URL
    • Fetch the build-log.txt from the GCS artifacts bucket
    • Parse the Prow job metadata for job type and parameters
  3. Limit log fetching to the most recent failed run per job type to avoid excessive API calls

Read the full file on GitHub · 151 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. 12d ago First seen · 151 lines · 13 tokens per session scan A 7cf48cb3df26

Subscribe to this mod's changes

review-ci is a command published in the GitHub repository lyarwood/kubevirt-ai-helpers (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 13 tokens to every session and 1,363 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.