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.
npx skills add lyarwood/kubevirt-ai-helpers --skill review-enhancementgit clone --depth 1 https://github.com/lyarwood/kubevirt-ai-helpersWrote 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.
[](https://agentmods.dev/skills/lyarwood/kubevirt-ai-helpers/review-enhancement)<a href="https://agentmods.dev/skills/lyarwood/kubevirt-ai-helpers/review-enhancement"><img src="https://agentmods.dev/badge/skills/lyarwood/kubevirt-ai-helpers/review-enhancement/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.
<a href="https://agentmods.dev/skills/lyarwood/kubevirt-ai-helpers/review-enhancement"><img src="https://agentmods.dev/badge/skills/lyarwood/kubevirt-ai-helpers/review-enhancement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00055 | $0.05529 |
| Opus 5.5 | $0.00022 | $0.02212 |
| Sonnet 5.5 | $0.00011 | $0.01106 |
| Haiku 4.5 | $0.00006 | $0.00553 |
Grade A, and why
review-enhancement 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Enhancement
This skill provides the detailed implementation logic for the /kubevirt:review-enhancement command. It covers how to resolve the input (an enhancements PR or a VEP number), read best practices live from the enhancements repo, gather all VEP data sources, perform process compliance checks, execute a multi-pass technical review, verify that updates to existing VEPs stay accurate against their implementation, and produce a structured review report.
When to Use This Skill
- When executing the
/kubevirt:review-enhancementcommand - When a user asks for a comprehensive review of a VEP proposal or an enhancements PR
- When reviewing a VEP graduation / stage-bump PR and needing to confirm the implementation backs it
- When preparing review feedback for a VEP before a SIG meeting or approval decision
Prerequisites
- gh CLI: Must be installed and authenticated (
gh auth status) - Network access: Requires access to the GitHub API for fetching best-practice docs, VEP content, tracking issues, project data, and implementation PRs
Guiding Principle: Best Practices Come From the Repo
Do not rely solely on the checklists baked into this skill. At review time, read the current best practices live from the kubevirt/enhancements repository so the review reflects the process as it stands today. The checks below encode the process as understood when this skill was written; the live docs are authoritative when they differ. See Step 0 for how to load them.
Implementation Steps
Step 0: Resolve Input and Load Best Practices
The command primarily takes an enhancements PR (number or URL), but also accepts a VEP number. Resolve which one was given, then load the live best-practice docs.
0a: Resolve the Input
If the argument is a PR URL or a number that resolves to an open enhancements PR:
gh pr view <pr-number> --repo kubevirt/enhancements --json number,title,body,labels,state,files,url,headRefName,commits
From the PR's changed files, determine the VEP and the kind of change:
- New VEP: the PR adds a
veps/sig-*/NNNN-*/vep.mdfile. - Update to an existing VEP: the PR modifies an existing
veps/sig-*/NNNN-*/vep.md(e.g. a graduation/stage bump or a design change).
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.
- 1mo ago Changed · +120 lines · +15 tokens per session d8f6b6e2da23
- 1mo ago First seen · 382 lines · 40 tokens per session scan A d72ac608e7c8
review-enhancement is a skill published in the GitHub repository lyarwood/kubevirt-ai-helpers (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 5,529 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…