agents-at-scale-ark: Command for Claude Code

.claude/commands/ark-create-crd.md

ark-create-crd is a command for Claude Code from mckinsey/agents-at-scale-ark. It costs 0 tokens per session (1,191 once invoked), scanned A, original, Apache-2.0.

A command for creating Kubernetes custom resource definitions for the Ark project. A custom resource definition, or CRD, teaches Kubernetes about a new kind of object that users can configure.

In plain words
What is it for?
Use it to design CRD types, status fields, configuration handling, example YAML, controller scaffolding, webhooks, and related documentation.
Why use it?
It helps new resources follow Ark's established naming, data, validation, and controller patterns. That makes the generated resource fit the rest of the project.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: names the TodoWrite tool.

This is mckinsey/agents-at-scale-ark's own configuration. It tells Claude Code how to work on agents-at-scale-ark itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agents-at-scale-ark configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mckinsey/agents-at-scale-ark. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mckinsey/agents-at-scale-ark/main/.claude/commands/ark-create-crd.md
Clone the repo
git clone --depth 1 https://github.com/mckinsey/agents-at-scale-ark

Made for: Claude Code.

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 ark-create-crd

README.md
[![agentmods](https://agentmods.dev/badge/commands/mckinsey/agents-at-scale-ark/ark-create-crd/github.svg)](https://agentmods.dev/commands/mckinsey/agents-at-scale-ark/ark-create-crd)
Your own site
<a href="https://agentmods.dev/commands/mckinsey/agents-at-scale-ark/ark-create-crd"><img src="https://agentmods.dev/badge/commands/mckinsey/agents-at-scale-ark/ark-create-crd/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 ark-create-crd

Your own site · 80×15
<a href="https://agentmods.dev/commands/mckinsey/agents-at-scale-ark/ark-create-crd"><img src="https://agentmods.dev/badge/commands/mckinsey/agents-at-scale-ark/ark-create-crd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,191 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 $0.00000 $0.01191
Opus 5 $0.00000 $0.00596
Sonnet 5 $0.00000 $0.00238
Haiku 4.5 $0.00000 $0.00119

Measured 5d ago against content hash 11b7d2921edd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ark-create-crd 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 5d 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.

.claude/commands/ark-create-crd.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ARK CRD Generator

You are an expert Kubernetes CRD developer working on the ARK project. Your task is to generate a new Custom Resource Definition following ARK's established patterns and design guidelines.

Pre-Task Checklist

  1. Review CRD Design Guidelines at /docs/content/concepts/crd-design-guide.mdx
  2. Examine existing CRDs in /ark/api/v1alpha1/ for pattern consistency
  3. Check common types in /ark/api/v1alpha1/common_types.go for reusable patterns
  4. Create a todo list using TodoWrite for tracking CRD generation subtasks

CRD Generation Workflow

  • Analyze the requested resource type and requirements
  • Determine appropriate naming following ARK conventions
  • Design the Spec structure using common patterns
  • Design the Status structure with appropriate phases
  • Add proper kubebuilder annotations
  • Generate the complete types file
  • Create sample YAML manifestation
  • Generate basic controller scaffold (if requested)
  • Generate admission webhook scaffold (if requested)
  • Update relevant documentation

ARK CRD Design Principles

Core Patterns to Follow

  1. ValueSource Pattern: Use for all configuration values that may contain secrets
  2. Parameter Pattern: Include []Parameter for template processing
  3. TTL Pattern: Add TTL *metav1.Duration with default "720h"
  4. TokenUsage Pattern: Include TokenUsage *TokenUsage for AI operations
  5. Owner References: Use for parent-child relationships in controller, not as CRD field

Naming Conventions

  • ...Ref: For references to other CRDs (e.g., AgentModelRef)
  • ...Config: For embedded configuration structs (e.g., ModelConfig)
  • ...Spec: For resource desired state (e.g., AgentSpec)
  • ...Status: For resource observed state (e.g., AgentStatus)

Required Kubebuilder Annotations

// +kubebuilder:object:root=true
// +kubebuilder:subresource:status
// +kubebuilder:printcolumn:name="Phase",type=string,JSONPath=`.status.phase`
// +kubebuilder:printcolumn:name="Age",type=date,JSONPath=`.metadata.creationTimestamp`

Read the full file on GitHub · 123 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. 5d ago First seen · 123 lines · 0 tokens per session scan A 11b7d2921edd

Subscribe to this mod's changes

ark-create-crd is a command published in the GitHub repository mckinsey/agents-at-scale-ark (422 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,191 tokens. 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 2026-09-03.