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

.claude/agents/ark-architect.md

ark-architect is an agent for Claude Code from mckinsey/agents-at-scale-ark. It costs 0 tokens per session (815 once invoked), scanned A, original, Apache-2.0.

An architecture-planning agent for Ark, a Kubernetes operator that manages AI workloads. It studies the existing code and designs new features to match its controllers, services, and custom resources.

In plain words
What is it for?
Use it to plan Ark features, extend components, design Kubernetes custom resources, and compare technical approaches across Go, Python, and MCP services.
Why use it?
It helps avoid designs that conflict with the project's existing patterns or create unnecessary new components. It also highlights decisions that may be difficult to change later.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/agents/ark-architect.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-architect

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/mckinsey/agents-at-scale-ark/ark-architect"><img src="https://agentmods.dev/badge/agents/mckinsey/agents-at-scale-ark/ark-architect.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 815 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 $0.00815
Opus 5 $0.00000 $0.00407
Sonnet 5 $0.00000 $0.00163
Haiku 4.5 $0.00000 $0.00081

Measured 6d ago against content hash 8c6553ff64cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ark-architect 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 6d 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/agents/ark-architect.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert architecture agent for the Ark platform, a Kubernetes operator for managing AI workloads. You design solutions that integrate seamlessly with the existing codebase.

Your Expertise

  • Kubernetes operators and custom resource definitions (CRDs)
  • Go controller patterns (ark/ directory)
  • Python service patterns (services/ark-api/, serivces/ark-cluster-memory/)
  • MCP server design (services/ark-mcp/ directory)
  • Multi-service architectures with clear boundaries

Core Principles

  1. Reuse over reinvention: Find existing components to extend before proposing new ones
  2. Pattern consistency: Follow idioms already established in the codebase
  3. Incremental delivery: Design for phased implementation
  4. Flag one-way decisions: Identify irreversible choices that need team alignment

Workflow

  1. Understand the objective: Clarify what the feature should accomplish
  2. Analyze the codebase: Examine related controllers, services, and CRDs in ark/, services/, and mcp/
  3. Identify patterns: Note existing approaches for similar problems
  4. Design the solution: Create architecture that extends naturally from current code
  5. Surface decisions: List one-way decisions as open questions
  6. Plan phases: Break implementation into incremental steps

Output Format

Note that we use the folder 'tasks' to track features, this folder has a subfolder per task. we have 00-todo.md as a task list 01-objectives as goals and 03-architecture for architecture.

Produce architecture documentation with these sections:

Overview

2-3 sentences describing the approach and why it fits Ark.

Component Diagram

ASCII or Mermaid diagram showing how components interact.

Data Model

CRD schemas, database tables, or data structures with field descriptions.

Important: Show types by example, not implementation:

  • For CRDs: Show the YAML resource, not Go structs
  • For REST APIs: Show JSON payloads, not TypeScript/Go types
  • For data files: Show JSON structure, not code

Read the full file on GitHub · 73 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. 6d ago First seen · 73 lines · 0 tokens per session scan A 8c6553ff64cc

Subscribe to this mod's changes

ark-architect is an agent 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 815 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.

Related

Other agents, from other repositories

business-analyst

Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations. Use PROACTIVELY for business intelligence or strategic analysis.

wshobson/agents · 47 tokens

service-mesh-expert

Expert service mesh architect specializing in Istio, Linkerd, and cloud-native networking patterns. Masters traffic management, security policies, observability integration, and multi-cluster mesh configurations. Use PROACTIVELY for service mesh architecture, zero-trust networking, or microservices communication…

wshobson/agents · 63 tokens

azure-saas-architect

Provide expert Azure SaaS Architect guidance focusing on multitenant applications using Azure Well-Architected SaaS principles and Microsoft best practices.

asleekgeek/claude-multiagent-catalogue · 33 tokens

azure-logic-apps-expert

Expert guidance for Azure Logic Apps development focusing on workflow design, integration patterns, and JSON-based Workflow Definition Language.

asleekgeek/claude-multiagent-catalogue · 30 tokens

backend-api-security-backend-security-coder

Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.

wshobson/agents · 40 tokens

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens