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/documentation/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/documentation)<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/documentation"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/documentation/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/documentation"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/documentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 245 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00041 | $0.02369 |
| Opus 5.5 | $0.00016 | $0.00948 |
| Sonnet 5.5 | $0.00008 | $0.00474 |
| Haiku 4.5 | $0.00004 | $0.00237 |
Grade A, and why
ark-documentation 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.
How it starts
The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ark Documentation
Guidance for structuring Ark documentation using Diataxis adapted for Ark's needs.
When to use this skill
- Creating new documentation
- Deciding where content belongs
- Reviewing documentation PRs
- Restructuring existing documentation
Ark's Diataxis structure
docs/content/
├── Introduction
├── Quickstart
├── Tutorials → Linear learning paths
├── How-to Guides → Task-oriented, by persona
├── Core Concepts → Understanding "why" and "how"
├── Reference → Factual lookup material
├── Marketplace → External link
└── Disclaimer
Terminology
| Diataxis | Ark Term | Why |
|---|---|---|
| Explanation | Core Concepts | More accessible |
The four quadrants
1. Tutorials (learning-oriented)
Purpose: Hands-on lessons for newcomers.
Characteristics:
- Linear, numbered paths (1, 2, 3...)
- Single prescribed path - no choices
- Frequent visible results
- Ends with "Next step" → How-to Guides
Writing style:
- Use "we" language
- Don't explain - link to Core Concepts
Content belongs here if:
- It teaches a skill through doing
- Reader is studying, not working
- Success requires following steps in order
Examples: Quickstart, Running the Dashboard, Starting a New Project, Complete Worked Example
2. How-to guides (task-oriented)
Purpose: Help competent users complete specific tasks.
Organized by persona:
Build with Ark (application developers)
- Configure models, create agents, coordinate teams, run queries, add tools.
Extend Ark (contributors)
- Build services locally, implement APIs, build A2A servers, add tests.
Operate Ark (operators / SRE / security)
- Platform operations: Provisioning, deploying
- CI/CD and supply chain: Build pipelines
- Security & assurance: Pen testing, code analysis
Writing style:
- Goal-oriented: "If you want X, do Y"
- Assumes competence
- Don't teach - link to Tutorials or Core Concepts
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 · 260 lines · 41 tokens per session scan A 7d1d002c6d95
ark-documentation is a skill published in the GitHub repository mckinsey/agents-at-scale-ark (434 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 2,369 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.
ark-documentation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ark-documentationmckinsey/agents-at-scale-ark | Skill | 434 | yesterday | Apache-2.0 | A | 41 | Claude Code |
| mirrord-quickstartmetalbear-co/mirrord | Skill | 5.4k | yesterday | MIT | A | 89 | Claude Code, Codex |
| container-manager-kubernetes-operationsKnuckles-Team/container-manager-mcp | Skill | 6 | yesterday | MIT | A | 189 | Claude Code, Codex |
| bdbsaastraininghybridlabor-api/bdb-dev-optimized-agent-skills | Skill | 6 | 5d ago | Apache-2.0 | B | 56 | Claude Code |
| 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 |
| agent-challengesruvnet/ruflo | Skill | 81k | yesterday | MIT | A | 15 | Claude Code |