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

.claude/skills/analysis/SKILL.md

Ark Analysis is a skill for Claude Code from mckinsey/agents-at-scale-ark. It costs 45 tokens per session (816 once invoked), scanned C, original, Apache-2.0.

A codebase-analysis guide for examining Ark's source code, Kubernetes resources, controllers, APIs, and software development kits.

In plain words
What is it for?
It is for investigating Ark's architecture, implementation details, custom resources, and controllers.
Why use it?
It gives developers a structured way to answer how Ark works without guessing from scattered files.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

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/skills/analysis/SKILL.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 Analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/analysis.svg)](https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/analysis)
Your own site
<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/analysis"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/analysis.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 81
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 81
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 81
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
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 $0.00045 $0.00816
Opus 5 $0.00023 $0.00408
Sonnet 5 $0.00009 $0.00163
Haiku 4.5 $0.00005 $0.00082

Measured 4d ago against content hash 3338cf031fbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

Ark Analysis scanned grade C with 1 finding 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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

5. **Clean up**: Optionally remove the temp directory when done: `rm -rf /tmp/ark-analysis`
.claude/skills/analysis/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ark Analysis

This skill helps you analyze the Ark codebase by cloning the repository and examining its contents.

When to use this skill

Use this skill when:

  • User asks "how does X work in Ark?"
  • User wants to understand Ark's architecture or implementation
  • User needs to examine Ark source code, CRDs, or controllers
  • User mentions analyzing the Ark repository

Quick start

Clone the Ark repository to a temporary location:

git clone [email protected]:mckinsey/agents-at-scale-ark.git /tmp/ark-analysis
cd /tmp/ark-analysis

Codebase structure

The Ark repository is organized as follows:

  • ark/ - Kubernetes operator and default executor (Go)

    • Controller dispatches queries to executors via A2A protocol
    • CRDs: Agent, Model, Query, Team, MCPServer, ExecutionEngine, A2AServer
    • executors/completions/ - Built-in default execution engine
  • lib/ark-sdk/ - Python SDK (generated + overlay)

    • BaseExecutor ABC and ExecutorApp for pluggable executor interface
  • services/ - Component services

    • ark-api/ - REST API gateway (Python/FastAPI)
    • ark-broker/ - In-memory event bus (Node.js/Express)
    • ark-dashboard/ - Web UI (Next.js/React)
  • samples/ - Example YAML configurations

  • docs/ - Documentation site (Next.js/MDX)

Common analysis tasks

Find controllers

ls ark/internal/controller/
grep -r "Reconcile" ark/internal/controller/

Find CRDs

ls ark/config/crd/bases/
grep -r "kind: Agent" samples/

Find A2A implementations

find . -path "*/a2a*" -type f
grep -r "A2AServer" .

Search for specific features

# Use ripgrep or grep to search
rg "query controller" --type go
grep -r "team coordination" --include="*.go"

Best practices

  1. Clone to /tmp: Always clone to /tmp/ark-analysis to avoid cluttering the workspace
  2. Navigate first: cd /tmp/ark-analysis before running analysis commands
  3. Use search tools: Prefer rg (ripgrep) or grep for code searches
  4. Check CLAUDE.md: Look for project-specific guidance in CLAUDE.md files
  5. Clean up: Optionally remove the temp directory when done: rm -rf /tmp/ark-analysis

Read the full file on GitHub · 107 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. 4d ago First seen · 107 lines · 45 tokens per session scan C 3338cf031fbf

Subscribe to this mod's changes

Ark Analysis is a skill published in the GitHub repository mckinsey/agents-at-scale-ark (422 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 816 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

container-manager-kubernetes-operations

Full operational Kubernetes surface via the container-manager-mcp MCP server — workloads (pods/rollouts/StatefulSets/DaemonSets/ReplicaSets/Jobs/CronJobs), config (ConfigMaps/Secrets/Namespaces/CRDs/patch), networking (Ingress/native Services/NetworkPolicy/DNS), storage (PV/PVC/StorageClass/snapshots/CSI), RBAC…

Knuckles-Team/container-manager-mcp · 189 tokens

k8s-ops

Opinionated multi-step Kubernetes workflows on top of the k8s-mcp server. Encodes tool-sequencing logic and failure-mode decision trees for deploying from a repo, debugging pods/rollouts, performing safe restarts, and auditing cluster posture. Use when the user asks to deploy, diagnose, restart, roll out, or audit…

jingyanjiang/k8s-mcp · 77 tokens

kubernetes-mesh-provisioner

Kubernetes Mesh Provisioner atomic skill. Stands up an RKE2 cluster (server + agents) with Cilium CNI and the NVIDIA GPU device plugin, the Kubernetes parallel of swarm-mesh-provisioner. Idempotent — re-runnable.

Knuckles-Team/container-manager-mcp · 60 tokens

cost-optimization

Optimize cloud costs across AWS, Azure, GCP, and OCI through resource rightsizing, tagging strategies, reserved instances, and spending analysis. Use when reducing cloud expenses, analyzing infrastructure costs, or implementing cost governance policies.

wshobson/agents · 48 tokens

linkerd-patterns

Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.

wshobson/agents · 41 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens