create-eval-from-docs

create-eval-from-docs is a command for Claude Code from lyarwood/kubevirt-ai-helpers. It costs 12 tokens per session (1,591 once invoked), scanned A, original, Apache-2.0.

A command that turns KubeVirt user guides into evaluation tasks for Kubernetes tools. KubeVirt is software for running virtual machines inside Kubernetes, a system for managing containers and related workloads.

In plain words
What is it for?
Finding actionable workflows in a document, matching them to available tools, and generating task files with setup, prompts, verification, cleanup, and a summary.
Why use it?
It converts human documentation into repeatable checks, making it easier to see whether an AI agent can complete the documented workflows.

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 Finding actionable workflows in a document, matching them to available tools, and generating task files with setup, prompts, verification, cleanup, and a summary.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/lyarwood/kubevirt-ai-helpers/create-eval-from-docs
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 create-eval-from-docs

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/lyarwood/kubevirt-ai-helpers/create-eval-from-docs"><img src="https://agentmods.dev/badge/commands/lyarwood/kubevirt-ai-helpers/create-eval-from-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,591 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 $0.00012 $0.01591
Opus 5 $0.00006 $0.00796
Sonnet 5 $0.00002 $0.00318
Haiku 4.5 $0.00001 $0.00159

Measured 10d ago against content hash 2fdeaf890a88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

create-eval-from-docs 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 10d 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/create-eval-from-docs.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Name

kubevirt:create-eval-from-docs

Synopsis

/kubevirt:create-eval-from-docs <doc-path-or-feature>

Description

The kubevirt:create-eval-from-docs command reads KubeVirt user-guide documentation and generates MCPChecker evaluation tasks for the kubernetes-mcp-server project. It extracts actionable workflows from documentation, maps them to available MCP tools, and produces v1alpha2 task YAML files with setup, prompt, verify, and cleanup phases.

This command bridges the gap between user-facing documentation and automated evaluation coverage. Each generated task validates that an AI agent can complete a real user workflow using the kubernetes-mcp-server's KubeVirt and core toolsets.

Workflow

Input                  Analysis                 Generation             Output
-----                  --------                 ----------             ------
Doc path/feature  -->  Read & classify doc  --> Map to MCP tools  --> Task YAML files
                       Extract workflows        Assess difficulty      Verify helpers
                       Identify prereqs         Detect tool gaps       Summary report

What It Generates

For each viable workflow found in the documentation:

  • A v1alpha2 MCPChecker task YAML file with all four phases (setup, prompt, verify, cleanup)
  • New verify helper functions if existing helpers do not cover the workflow
  • A summary report with tier classification, MCP tool mapping, and gap analysis

MCP Tool Coverage

The generated tasks test agent use of these MCP tools:

Toolset Tools Use Cases
kubevirt vm_create, vm_clone, vm_lifecycle VM creation, cloning, start/stop/restart
core resources_create_or_update, resources_get, resources_list, resources_delete Any K8s/KubeVirt resource CRUD
core pods_log, pods_exec, events_list Debugging, inspection
prompts vm-troubleshoot Structured VM diagnostics

Implementation

Refer to the detailed implementation guide in plugins/kubevirt/skills/create-eval-from-docs/SKILL.md for step-by-step instructions.

Read the full file on GitHub · 148 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. 10d ago First seen · 148 lines · 12 tokens per session scan A 2fdeaf890a88

Subscribe to this mod's changes

create-eval-from-docs is a command published in the GitHub repository lyarwood/kubevirt-ai-helpers (2 stars, last pushed 8d ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,591 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.