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

.claude/agents/ark-security-patcher.md

ark-security-patcher is an agent for Claude Code from mckinsey/agents-at-scale-ark. It costs 0 tokens per session (6,028 once invoked), scanned B, original, Apache-2.0.

A security-remediation agent for Ark, a Kubernetes operator for managing AI workloads. It researches vulnerabilities such as CVEs, assesses their impact, proposes mitigations, applies approved fixes, tests them, and prepares a pull request.

In plain words
What is it for?
Use it to investigate CVEs, penetration-test findings, and other Ark security issues, then implement and document approved fixes.
Why use it?
It organizes the work needed to move from a reported vulnerability to a reviewed code change. It also separates different kinds of security findings and uses the matching workflow for each.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the AskUserQuestion tool; mentions Claude Code.

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-security-patcher.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-security-patcher

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/mckinsey/agents-at-scale-ark/ark-security-patcher"><img src="https://agentmods.dev/badge/agents/mckinsey/agents-at-scale-ark/ark-security-patcher.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 6,028 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.06028
Opus 5 $0.00000 $0.03014
Sonnet 5 $0.00000 $0.01206
Haiku 4.5 $0.00000 $0.00603

Measured 8d ago against content hash 77536afcab1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

ark-security-patcher scanned grade B with 2 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 8d 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 deletemediumDestructive command

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

rm -rf /tmp/ark-security-fix

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://cve.circl.lu/api/cve/CVE-2024-12345"
.claude/agents/ark-security-patcher.md · 790 lines

How it starts

The opening of the file, as written. The whole thing — 790 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security specialist agent for the Ark platform. You identify, analyze, and fix security vulnerabilities through a systematic research and remediation process.

Your Mission

When the user reports a security vulnerability, complete the full workflow:

  1. Check for existing GitHub issues (leverage issues skill)
  2. Identify the vulnerability type:
    • CVE vulnerability: Use vulnerability-fixer skill
    • Penetration test finding: Use pentest-issue-resolver skill
    • Generic security issue: Use research skill to identify specifics
  3. Research and understand the vulnerability thoroughly
  4. Analyze the impact on the Ark codebase (leverage analysis skill)
  5. Present clear mitigation options to the user
  6. Wait for user approval
  7. Clone the Ark repository for development
  8. Implement the approved fix
  9. Test the changes (optionally use setup skill for integration testing)
  10. Create a detailed pull request (link to issue if found in step 1)

Core Principles

  • End-to-end workflow: From issue tracking to PR creation
  • Leverage existing skills: Use issues, vulnerability-fixer, pentest-issue-resolver, research, analysis, and setup skills
  • Identify vulnerability type: CVE, pentest finding, or generic issue - use the appropriate skill
  • Check for existing work: Always search for existing GitHub issues before starting
  • User approval required: Present options and wait for confirmation before making changes
  • Clear communication: Explain technical details in accessible language
  • Comprehensive documentation: Document every aspect of the vulnerability and fix
  • Test thoroughly: Verify fixes don't break existing functionality

Workflow

Step 1: Check for Existing GitHub Issues

ALWAYS check for existing issues first using the issues skill:

# Search for CVE-related issues
gh search issues --repo mckinsey/agents-at-scale-ark "CVE-2025-55183"

# Or search more broadly for security issues
gh search issues --repo mckinsey/agents-at-scale-ark "security vulnerability"

Read the full file on GitHub · 790 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. 8d ago First seen · 790 lines · 0 tokens per session scan B 77536afcab1f

Subscribe to this mod's changes

ark-security-patcher is an agent published in the GitHub repository mckinsey/agents-at-scale-ark (423 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,028 tokens. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). 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

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

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

01-Orchestrator

Master orchestrator for the multi-step Azure platform engineering workflow. Coordinates Requirements, Architect, Design, IaC Plan, IaC Code, Deploy agents with mandatory human approval gates. Routes Bicep or Terraform tracks via decisions.iactool.

jonathan-vella/apex-accelerator · 53 tokens

04g-Governance

Azure governance discovery agent. Queries Azure Policy assignments via REST API (incl. management-group-inherited policies), classifies effects, produces governance constraint artifacts, and runs adversarial review. Step 3.5: after Architecture, before IaC Planning.

jonathan-vella/apex-accelerator · 56 tokens

03-Architect

Expert Architect providing guidance using Azure Well-Architected Framework principles and Microsoft best practices. Evaluates decisions against WAF pillars and generates ARM MCP-verified cost estimates.

jonathan-vella/apex-accelerator · 37 tokens