Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/aiocean/claude-plugins/aio-dashboard-designnpx skills add aiocean/claude-plugins --skill aio-dashboard-designgit clone --depth 1 https://github.com/aiocean/claude-pluginsWrote 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/aiocean/claude-plugins/aio-dashboard-design)<a href="https://agentmods.dev/skills/aiocean/claude-plugins/aio-dashboard-design"><img src="https://agentmods.dev/badge/skills/aiocean/claude-plugins/aio-dashboard-design.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.04220 |
| Opus 5 | $0.00017 | $0.02110 |
| Sonnet 5 | $0.00007 | $0.00844 |
| Haiku 4.5 | $0.00003 | $0.00422 |
Grade A, and why
aio-dashboard-design 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 6d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SaaS Dashboard Design Advisor
"Above all else show the data. Maximize the data-ink ratio." — Edward Tufte, The Visual Display of Quantitative Information (1983, p. 105)
"The annotation layer is the most important thing we do… otherwise it's a case of here it is, you go figure it out." — Amanda Cox, NYT Upshot (2012)
Skill này tổng hợp ~60 năm nghiên cứu visualization (Bertin 1967, Tufte 1983, Cleveland–McGill 1984, Few 2006, Munzner 2014, Shneiderman 1996, Knaflic 2015, Cairo 2016, Segel–Heer 2010), UX thực nghiệm của Nielsen Norman Group, accessibility theo WCAG 2.2 + Chartability (Elavsky 2022), hướng dẫn từ IBM Carbon / Shopify Polaris / Atlassian / Material / Fluent, và pattern sản phẩm của Stripe, Linear, Vercel, Datadog, Shopify Admin, Plausible, GitHub.
Dùng nó như cả design reference (để làm dashboard tốt) lẫn review standard (để chặn dashboard tệ trước khi ship).
Workflow: 5-Step Review / Design Loop
Khi skill này trigger, KHÔNG dump toàn bộ principle. Luôn apply vào surface cụ thể của user. Tuân thủ 5 bước.
Step 1 — UNDERSTAND: Audience & Surface
Hỏi chỉ những gì còn thiếu:
- Ai đọc cái này? Executive (strategic), Analyst (exploratory), Front-line/NOC (operational), hoặc mixed audience?
- Big Idea là gì? Một câu hoàn chỉnh: viewpoint + so what + implied action. Nếu user không viết được câu đó → redesign, đừng debate pixel. (Knaflic/Duarte.)
- Surface type? Strategic / Analytical / Operational (Few taxonomy). Chi tiết:
references/design-guidelines.md§3.1. - Mode? Explanatory (home, exec summary, email digest — author-driven) hay exploratory (analyst workbench, segment explorer — reader-driven). Nếu mixed → đề xuất Martini Glass (Segel–Heer 2010).
- Constraint check: mobile? real-time? WCAG AA bắt buộc? dark mode? locale Đông Á?
Nếu user đã cung cấp đủ context, skip sang Step 2.
Step 2 — SELECT: Pick Principles & Chart Types
Map problem của user vào:
- Principles (§ 10 Core Principles bên dưới).
- Chart types (§ Chart Selection Matrix).
- Routing table (§ Routing Table).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 211 lines · 35 tokens per session scan A 0df3d22c338e
aio-dashboard-design is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 4,220 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…
source-command-methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.
canary
Post-deploy monitoring: watch production after a deploy and alert on regressions.
investigate
Systematic root-cause debugging: find the cause before writing any fix.