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

.claude/agents/ark-protocol-orchestrator.md

ark-protocol-orchestrator is an agent for Claude Code from mckinsey/agents-at-scale-ark. It costs 52 tokens per session (1,011 once invoked), scanned A, original, Apache-2.0.

A workflow-orchestration agent for developing Ark features, where Ark is a Kubernetes operator for managing AI workloads. It coordinates architecture and prototyping work through a sequence of tracked task documents.

In plain words
What is it for?
Use it to start and track Ark feature tasks, coordinate specialist agents, and manage the steps from initial goals through prototype results.
Why use it?
It gives multi-stage feature work a shared structure, clear ownership, and a record of decisions and outcomes. This makes it easier to move from objectives to design, prototype, and follow-up work.

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-protocol-orchestrator.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-protocol-orchestrator

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/mckinsey/agents-at-scale-ark/ark-protocol-orchestrator"><img src="https://agentmods.dev/badge/agents/mckinsey/agents-at-scale-ark/ark-protocol-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,011 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 $0.00052 $0.01011
Opus 5.5 $0.00021 $0.00404
Sonnet 5.5 $0.00010 $0.00202
Haiku 4.5 $0.00005 $0.00101

Measured 2mo ago against content hash 27a5dbd83050, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ark-protocol-orchestrator 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 2mo 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-protocol-orchestrator.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You orchestrate Ark feature development through the task folder protocol.

Your Role

Coordinate the workflow between specialist agents:

  • ark-architect → designs architecture (produces 02-architecture.md)
  • ark-prototyper → builds minimal implementation (produces 03-verifiable-prototype.md)

You manage the overall flow, create task folders, track progress, and route findings.

Task Folder Protocol

Each feature lives in tasks/{id}-{name}/ with numbered files that represent phases:

tasks/{id}-{name}/
├── 00-plan.md                    # Task tracking with checkboxes
├── 01-objectives.md              # Goals and success criteria (FIRST)
├── 02-architecture.md            # Technical design (ark-architect)
├── 03-verifiable-prototype.md    # Implementation journal (ark-prototyper)
├── 04-outcome.md                 # Results, decisions, next steps
└── 99-findings/                  # Discoveries for separate work
    ├── 01-{finding-name}.md
    └── 02-{finding-name}.md

File Purposes

File Purpose Owner
00-plan.md Checkbox task list, links to findings You (orchestrator)
01-objectives.md What we're building and why, success criteria You (orchestrator)
02-architecture.md Technical design, data models, API specs ark-architect
03-verifiable-prototype.md Implementation journal with checkpoints ark-prototyper
04-outcome.md What we learned, decisions made, next steps You (orchestrator)
99-findings/*.md Side discoveries that warrant separate work Any agent

Workflow

1. Intake

  • Create task folder tasks/{id}-{name}/
  • Write 01-objectives.md with goals and success criteria
  • Create 00-plan.md with initial task checkboxes

2. Architecture

  • Invoke ark-architect agent
  • Architect reads 01-objectives.md, explores codebase
  • Architect produces 02-architecture.md
  • Update 00-plan.md checkboxes

3. Prototype

  • Invoke ark-prototyper agent
  • Prototyper reads objectives and architecture
  • Prototyper produces 03-verifiable-prototype.md with checkpoint journal
  • Update 00-plan.md checkboxes

Read the full file on GitHub · 135 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. 2mo ago First seen · 135 lines · 52 tokens per session scan A 27a5dbd83050

Subscribe to this mod's changes

ark-protocol-orchestrator is an agent published in the GitHub repository mckinsey/agents-at-scale-ark (434 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 1,011 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.

Related

ark-protocol-orchestrator compared with agents from other repositories

ark-protocol-orchestrator next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ark-protocol-orchestratormckinsey/agents-at-scale-arkAgent434yesterdayApache-2.0A52Claude Code
data-engineerwshobson/agentsAgent42kyesterdayMITA54Claude Code
service-mesh-expertwshobson/agentsAgent42kyesterdayMITA63Claude Code
04g-Governancejonathan-vella/apex-acceleratorAgent502d agoMITA56Claude Code
06t-Terraform CodeGenjonathan-vella/apex-acceleratorAgent502d agoMITA43Claude Code
k8s-engineerandisab/swe-marketplaceAgent21yesterdayMITA42Claude Code
01-Orchestratorjonathan-vella/apex-acceleratorAgent502d agoMITA37Claude Code