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/commands/lyarwood/kubevirt-ai-helpers/review-list)<a href="https://agentmods.dev/commands/lyarwood/kubevirt-ai-helpers/review-list"><img src="https://agentmods.dev/badge/commands/lyarwood/kubevirt-ai-helpers/review-list/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/commands/lyarwood/kubevirt-ai-helpers/review-list"><img src="https://agentmods.dev/badge/commands/lyarwood/kubevirt-ai-helpers/review-list.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 | $0.00017 | $0.01726 |
| Opus 5 | $0.00009 | $0.00863 |
| Sonnet 5 | $0.00003 | $0.00345 |
| Haiku 4.5 | $0.00002 | $0.00173 |
Grade A, and why
review-list 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
kubevirt:review-list
Synopsis
/kubevirt:review-list [username] [--sig <sig>] [--repo <repo>] [--limit <n>] [--order-by <field>]
Description
The kubevirt:review-list command lists open pull requests where a user has been requested as a reviewer or is assigned, across KubeVirt organization repositories. It helps reviewers see their pending review queue at a glance.
If no username is provided, the command defaults to the current user's GitHub handle (via gh api user).
What it Shows
For each PR pending review:
- PR Number: With repository prefix
- Title: Brief description of the change
- Author: Who opened the PR
- SIG: SIG labels on the PR (sig/compute, sig/network, sig/storage, etc.)
- Size: Lines added/deleted and files changed
- Age: How long the PR has been open
- Draft: Whether the PR is a draft
- Labels: All labels on the PR
- Link: URL to the PR
Filtering Options
[username]: GitHub username to look up (defaults to current user)--sig: Filter by SIG label (compute, network, storage, etc.)--repo: Filter by repository (defaults tokubevirt/kubevirt; useallfor all kubevirt org repos, or specify e.g.kubevirt/containerized-data-importer)--limit: Maximum number of PRs to display (defaults to 10)--order-by: Sort order for results (defaults toupdated; also acceptscreated,age)
Implementation
-
Resolve GitHub Username: Determine the reviewer's GitHub handle:
# If no username argument provided, get the current user gh api user --jq '.login' -
Determine Target Repositories: Based on
--repoflag:- Default (no flag):
kubevirt/kubevirt --repo all: Query all major kubevirt org repos:kubevirt/kubevirt,kubevirt/containerized-data-importer,kubevirt/kubevirt.github.io,kubevirt/enhancements,kubevirt/community--repo <owner/repo>: Use the specified repository
- Default (no flag):
-
Fetch PRs Pending Review: For each target repository, use
ghto find open PRs where the user is a requested reviewer:gh pr list --repo <repo> --search "review-requested:<username>" --state open \ --json number,title,author,labels,additions,deletions,changedFiles,createdAt,updatedAt,isDraft,url,headRefName \ --limit 100Also fetch PRs where the user is an assignee but not yet reviewed:
gh pr list --repo <repo> --assignee <username> --state open \ --json number,title,author,labels,additions,deletions,changedFiles,createdAt,updatedAt,isDraft,url,headRefName \ --limit 100Merge and deduplicate the two result sets by PR number.
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.
- 12d ago First seen · 149 lines · 17 tokens per session scan A d8e2eded9841
review-list is a command published in the GitHub repository lyarwood/kubevirt-ai-helpers (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,726 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
argos
A command for checking whether an implementation matches its design deliverables. Its Korean description compares the work to the design as part of a completion inspection.