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/dashboard/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/dashboard)<a href="https://agentmods.dev/skills/mckinsey/agents-at-scale-ark/dashboard"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/dashboard/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/dashboard"><img src="https://agentmods.dev/badge/skills/mckinsey/agents-at-scale-ark/dashboard.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 | $0.00041 | $0.00511 |
| Opus 5.5 | $0.00016 | $0.00204 |
| Sonnet 5.5 | $0.00008 | $0.00102 |
| Haiku 4.5 | $0.00004 | $0.00051 |
Grade A, and why
Ark Dashboard and UI Testing 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:3000 What it actually says
Ark Dashboard and UI
Test Ark Dashboard UI with Playwright and attach screenshots to PRs.
When to use this skill
Use this skill when:
- User wants to test the Ark dashboard
- User needs screenshots for a PR
- User asks to validate dashboard UI changes
Prerequisites
CRITICAL: Before proceeding, verify Kubernetes is available:
kubectl cluster-info
If this fails, STOP and inform the user:
Cannot continue without a Kubernetes environment. Please ensure Kind or another Kubernetes cluster is running and kubectl is configured.
Ark must be deployed first. Use the ark-setup skill if needed.
Setup
Port forward the dashboard and warm up:
kubectl port-forward svc/ark-dashboard 3000:3000 -n default &
curl http://localhost:3000
Test with Playwright
Use Playwright MCP tools to navigate and screenshot:
browser_navigate- Open pagesbrowser_wait_for- Wait for elementsbrowser_click- Click elementsbrowser_take_screenshot- Capture screenshots
Screenshots save to .playwright-mcp/screenshots/. Move to ./screenshots/ for organization.
Upload Screenshots for PRs
Check if user has a scratch repo:
gh repo view <USERNAME>/scratch
If not, suggest creating: scratch/pull-request-attachments/<org>_<repo>/
Upload screenshots:
cd /tmp && git clone [email protected]:<USERNAME>/scratch.git
mkdir -p scratch/pull-request-attachments/<org>_<repo>
cp ./screenshots/*.png scratch/pull-request-attachments/<org>_<repo>/
cd scratch && git add . && git commit -m "chore: screenshots for <org>/<repo> PR" && git push
Reference in PR body:
Update PR:
gh api repos/<org>/<repo>/pulls/<NUMBER> -X PATCH -f body="..."
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 · 75 lines · 41 tokens per session scan A 2577273f7ce0
Ark Dashboard and UI Testing 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 511 once invoked, about $0.0002 per session on Opus 5.5. 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.
Ark Dashboard and UI Testing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Ark Dashboard and UI Testingmckinsey/agents-at-scale-ark | Skill | 434 | yesterday | Apache-2.0 | A | 41 | Claude Code |
| e2e-testing-patternswshobson/agents | Skill | 42k | yesterday | MIT | A | 51 | Claude Code |
| mirrord-chaosmetalbear-co/mirrord | Skill | 5.4k | yesterday | MIT | A | 119 | Claude Code, Codex |
| browser-testing-with-screenshotsAgentWorkforce/relay | Skill | 1.1k | today | Apache-2.0 | A | 32 | Claude Code |
| test-productionplatonai/Browser4 | Skill | 1.2k | yesterday | Apache-2.0 | A | 44 | Claude Code |
| run-dashboard-e2e-local-changesBlackBeltTechnology/pi-agent-dashboard | Skill | 341 | 2d ago | MIT | A | 42 | Claude Code, Codex |
| mirrord-cimetalbear-co/mirrord | Skill | 5.4k | yesterday | MIT | C | 52 | Claude Code, Codex |