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/skills/architecture/SKILL.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/skills/mckinsey/agents-at-scale-ark/architecture)<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/architecture"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/architecture/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/skills/mckinsey/agents-at-scale-ark/architecture"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00029 | $0.00323 |
| Opus 5.5 | $0.00012 | $0.00129 |
| Sonnet 5.5 | $0.00006 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
ark-architecture 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.
What it actually says
Ark Architecture Skill
Design architecture for Ark features following existing patterns and principles.
Process
- Analyze Current Solution - Use the ark-analysis skill to examine relevant parts of the codebase
- Identify Patterns - Find existing idioms, data models, and service structures to reuse
- Design for Reuse - Extend existing components rather than creating new ones
- Enable Incremental Updates - Break changes into small, independent pieces
- Flag One-Way Decisions - Raise questions on choices that are hard to reverse
Principles
- Reuse over creation - Extend existing services, models, and patterns
- Follow existing idioms - Match current code style, naming, and structure
- Incremental delivery - Design so features can be shipped in stages
- Reversibility - Identify and question decisions that lock in future options
Conventions
- Watch endpoints: Use
?watch=truequery param for SSE streaming (Kubernetes-style) - Service ports: Use named ports (e.g.,
port: mcp) rather than port numbers
Output
Architecture documents should include:
- Component diagram showing how new pieces fit with existing ones
- Data model extending current schemas
- API design following existing conventions
- List of one-way decisions requiring team input
- Implementation phases for incremental delivery
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.
- 2mo ago First seen · 38 lines · 29 tokens per session scan A f75e749d6eb5
ark-architecture is a skill published in the GitHub repository mckinsey/agents-at-scale-ark (434 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 323 once invoked, about $0.0001 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.
ark-architecture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ark-architecturemckinsey/agents-at-scale-ark | Skill | 434 | yesterday | Apache-2.0 | A | 29 | Claude Code |
| container-manager-kubernetes-operationsKnuckles-Team/container-manager-mcp | Skill | 6 | yesterday | MIT | A | 189 | Claude Code, Codex |
| kubernetes-mesh-provisionerKnuckles-Team/container-manager-mcp | Skill | 6 | yesterday | MIT | C | 60 | Claude Code, Codex |
| k8s-opsjingyanjiang/k8s-mcp | Skill | 3 | 5mo ago | MIT | A | 77 | Claude Code |
| linkerd-patternswshobson/agents | Skill | 42k | yesterday | MIT | A | 41 | Claude Code |
| cost-optimizationwshobson/agents | Skill | 42k | yesterday | MIT | A | 48 | Claude Code |
| istio-traffic-managementwshobson/agents | Skill | 42k | yesterday | MIT | A | 40 | Claude Code |