A command that checks changes on your current local Git branch against a base branch using KubeVirt’s review rules. If the branch has an open GitHub pull request, it also examines the request and existing discussion.

Use it to review local work, find issues across several review areas, and optionally prepare inline comments for an open GitHub pull request.

It provides a structured check for design, code, project conventions, commits, and—when available—pull-request details before changes are submitted or merged.

review — Command for Claude Code by lyarwood

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/lyarwood/kubevirt-ai-helpers/review/github.svg)](https://agentmods.dev/commands/lyarwood/kubevirt-ai-helpers/review)

Your own site

<a href="https://agentmods.dev/commands/lyarwood/kubevirt-ai-helpers/review"><img src="https://agentmods.dev/badge/commands/lyarwood/kubevirt-ai-helpers/review/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/lyarwood/kubevirt-ai-helpers/review"><img src="https://agentmods.dev/badge/commands/lyarwood/kubevirt-ai-helpers/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,500 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	$0.00011	$0.01500
Opus 5	$0.00005	$0.00750
Sonnet 5	$0.00002	$0.00300
Haiku 4.5	$0.00001	$0.00150

Measured 11d ago against content hash e1ee222e9167, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review 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.

plugins/kubevirt/commands/review.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Name

kubevirt:review

Synopsis

/kubevirt:review [base-branch]

Description

The kubevirt:review command performs a comprehensive code review of changes on the current local branch compared to a base branch, applying KubeVirt project coding conventions and reviewer guidelines.

If the current branch has an open pull request on GitHub, the command also evaluates PR metadata (title, description, labels, size), reads existing review discussion to avoid duplicating points, and offers to post inline review comments as a PENDING GitHub review.

This command simulates a thorough code review following the KubeVirt multi-pass review approach. Read the shared review checklist at plugins/kubevirt/skills/review/SKILL.md for the full list of review areas, conventions, and output formatting rules.

Review Passes

General Design Pass: Verify the overall design makes sense and code structure is consistent with the project
Detailed Code Pass: In-depth analysis of the implementation
Standards Compliance Pass: Check adherence to KubeVirt coding conventions
Commit History Pass: Review commit structure and messages
PR Metadata Pass (when PR detected): Evaluate PR title, description, labels, and overall scope

Implementation

Phase 1: Gather Changes

Determine the base branch (defaults to main, falls back to master)
Run git diff <base-branch>...HEAD to get all changes on the current branch
Run git log <base-branch>...HEAD to understand commit history and structure
Prioritize files for review using the file priority order from the shared review checklist

Phase 1b: Detect Associated PR

Check if the current branch has an open pull request:

gh pr list --head $(git branch --show-current) \
  --json number,title,body,labels,state,isDraft,additions,deletions,changedFiles,comments,reviews \
  --jq '.[0]'

If a PR exists:
- Record the PR number and metadata for use in later phases
- Evaluate PR metadata (title, description, labels, size, draft status) using the PR Metadata checklist from the shared skill
- Flag PRs that are too large (>500 lines changed across many files) and suggest splitting
- Fetch existing discussion:
  - Use gh api repos/<owner>/<repo>/pulls/<number>/comments to read all inline review comments with file paths, line numbers, and body text
  - Read and understand the substance of each comment - do not just note that comments exist
  - When generating the review report, do NOT duplicate points already raised in existing comments
  - Note which existing comments have been addressed by subsequent commits and which remain unresolved
If no PR exists:
- Skip PR metadata evaluation
- Note in the report that PR metadata could not be evaluated (no open PR found for this branch)

Read the full file on GitHub · 130 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 · 130 lines · 11 tokens per session scan A e1ee222e9167

Subscribe to this mod's changes

review is a command published in the GitHub repository lyarwood/kubevirt-ai-helpers (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,500 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.

Code review Git and workflow

review

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Name

Synopsis

Description

Review Passes

Implementation

Phase 1: Gather Changes

Phase 1b: Detect Associated PR

What this file has done since we first saw it

Other commands, from other repositories

devkit.github.review-pr

speckit.spex.submit

git

merge-conflict-analysis

code-review

advanced-code-review-context