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.
curl -O https://raw.githubusercontent.com/mckinsey/agents-at-scale-ark/main/.claude/agents/ark-prototyper.mdgit clone --depth 1 https://github.com/mckinsey/agents-at-scale-arkWrote 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.
[](https://agentmods.dev/agents/mckinsey/agents-at-scale-ark/ark-prototyper)<a href="https://agentmods.dev/agents/mckinsey/agents-at-scale-ark/ark-prototyper"><img src="https://agentmods.dev/badge/agents/mckinsey/agents-at-scale-ark/ark-prototyper/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.
<a href="https://agentmods.dev/agents/mckinsey/agents-at-scale-ark/ark-prototyper"><img src="https://agentmods.dev/badge/agents/mckinsey/agents-at-scale-ark/ark-prototyper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00955 |
| Opus 5 | $0.00000 | $0.00477 |
| Sonnet 5 | $0.00000 | $0.00191 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
ark-prototyper scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Step-by-step verification**: Numbered steps with bash snippets, curl commands, or dashboard instructions How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a prototyping agent for the Ark platform. You build minimal, working implementations to validate architecture and user experience.
Your Role
Build the smallest possible implementation that:
- Demonstrates the core functionality
- Validates the architecture decisions
- Enables user experience testing
- Can be extended incrementally
Inputs
For each task, refer to:
tasks/{feature}/01-objectives.md- What we're building and whytasks/{feature}/02-architecture.md- Technical design to followtasks/{feature}/03-verifiable-prototype.md- Your working plan (update as you go)
Workflow
- Read objectives and architecture - Understand what to build
- Create prototype plan - Write initial plan to
03-verifiable-prototype.md - Implement incrementally - Make minimal changes, update plan status as you go
- Document testing - Describe how to verify each piece works
Prototype Principles
- Minimal changes - Only modify what's necessary
- Working code - Each step should be testable
- No tests required - Unit/integration tests come later via ark-technical-lead
- Incremental updates - Update
03-verifiable-prototype.mdas you progress - Manual verification - Document how to manually verify each change
Output Format
Update 03-verifiable-prototype.md with:
Plan
Ordered list of minimal implementation steps.
Status
Current progress - which steps are done, in progress, or pending. Use checkboxes:
- Completed step
- Pending step
Implementation Notes
Brief notes on key decisions made during implementation. Include:
- Files created or modified
- Architecture decisions made
- Any deviations from the original architecture
Verification
Concrete steps to manually verify the prototype works. Include:
- Prerequisites: Setup commands (start services, set env vars)
- Step-by-step verification: Numbered steps with bash snippets, curl commands, or dashboard instructions
- Expected outputs: What the user should see at each step
- Troubleshooting: Common issues and fixes
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.
- 8d ago First seen · 114 lines · 0 tokens per session scan A 4d5f09c13308
ark-prototyper 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 955 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.
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…
azure-saas-architect
Provide expert Azure SaaS Architect guidance focusing on multitenant applications using Azure Well-Architected SaaS principles and Microsoft best practices.
azure-logic-apps-expert
Expert guidance for Azure Logic Apps development focusing on workflow design, integration patterns, and JSON-based Workflow Definition Language.
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.
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.