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.
git 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/plugins/lyarwood/kubevirt-ai-helpers/kubevirt)<a href="https://agentmods.dev/plugins/lyarwood/kubevirt-ai-helpers/kubevirt"><img src="https://agentmods.dev/badge/plugins/lyarwood/kubevirt-ai-helpers/kubevirt/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/plugins/lyarwood/kubevirt-ai-helpers/kubevirt"><img src="https://agentmods.dev/badge/plugins/lyarwood/kubevirt-ai-helpers/kubevirt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kubevirt 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 7d 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.
What it actually says
{
"name": "kubevirt",
"description": "KubeVirt development workflows for code review, PR review, linting, CI analysis, and enhancement proposals (VEPs)",
"version": "1.10.0",
"author": {
"name": "KubeVirt Contributors"
}
}
What it installs
The manifest is a name and a version. 4 skills, 17 commands travel with it, and installing the plugin installs all of them — 445 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill create-eval-from-docs A 64 tokens
- Skill review-enhancement A 55 tokens
- Skill review A 38 tokens
- Skill vep-find-reviewers A 50 tokens
- Command review-enhancement A 24 tokens
- Command ci-report A 7 tokens
- Command ci-search A 11 tokens
- Command ci-triage A 13 tokens
- Command create-eval-from-docs A 12 tokens
- Command lint A 16 tokens
- Command review A 11 tokens
- Command review-pr A 16 tokens
- Command vep-find-reviewers A 15 tokens
- Command vep-groom A 11 tokens
- Command vep-review-list A 17 tokens
- Command ci-health A 11 tokens
- Command ci-lane A 12 tokens
- Command review-ci A 13 tokens
- Command review-list A 17 tokens
- Command vep-summary A 15 tokens
- Command vep-list A 17 tokens
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.
- 7d ago Changed 156e64750519
- 11d ago First seen · 9 lines scan A c4e355b9ef28
kubevirt is a plugin published in the GitHub repository lyarwood/kubevirt-ai-helpers (2 stars, last pushed 8d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
han-communication
Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…
peer-review
Cross-model peer review of plans, specs, and the decisions a session has just made: a harness-agnostic deliberation protocol (challenge packet with GIVEN-tagged context, challenger findings that each carry their own falsifier, evidence-backed responses at a stable locator, a verbatim ledger, a certification pass the…
git-pr
Committing, PR creation and review triage, and dependency upgrades.
ai-infra-auto-driven-skills
Agent-ready playbooks for LLM serving benchmarks, SGLang model Day-0 support, capacity planning, profiling, SGLang/vLLM SOTA loops, code review, incidents, and PR-history dossiers.
code-quality
OxLint, Biome, and Prettier configuration, linting skills, and pre-commit hooks for consistent code quality.
coderabbit
CodeRabbit integration for Claude Code - local code review and PR comment management.