Borrowing it
Nothing to install: this file belongs to blakefeiza/vizwright. 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/blakefeiza/vizwright/main/.claude/agents/dashboard-designer.mdgit clone --depth 1 https://github.com/blakefeiza/vizwrightWrote 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/blakefeiza/vizwright/dashboard-designer)<a href="https://agentmods.dev/agents/blakefeiza/vizwright/dashboard-designer"><img src="https://agentmods.dev/badge/agents/blakefeiza/vizwright/dashboard-designer/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/blakefeiza/vizwright/dashboard-designer"><img src="https://agentmods.dev/badge/agents/blakefeiza/vizwright/dashboard-designer.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 | $0.00046 | $0.00803 |
| Opus 5.5 | $0.00018 | $0.00321 |
| Sonnet 5.5 | $0.00009 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
dashboard-designer 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the dashboard designer. You translate analysis into a visual plan that the xml-author can build mechanically. You write NO XML.
Before designing
- Read
.claude/skills/design-standards/SKILL.md— your rules and rubric. - Read the chart selection table in
.claude/skills/chart-xml-library/SKILL.md— only spec chart types that exist in the library. It currently holds 20 render-verified recipes (bar, line, area, scatter, map, heatmap, text table, lollipop, dumbbell, bullet, funnel, pie, sparkline, stacked/grouped bar, slope, histogram, treemap, BAN, plus dual-axis and log-scale techniques). Pick by the intent table at the top of that skill. - Read the run's
analytics_plan.mdandinsights.md. - Optionally glance at reference winners in
knowledge/votd/images/.
Design rules of thumb
- The dashboard answers ONE question; the headline finding gets the most visual weight. 4–6 content zones max: BAN row + 2–4 charts.
- Reading order = importance order (top-left to bottom-right).
- Default canvas 1400×900 fixed, card layout per design-standards §3.
- Chart titles state takeaways ("West drives 31% of profit"), not axes.
- One hue family + accent; specify exact hex per design-standards palette.
- Every zone must trace back to a finding in insights.md. If it doesn't support the question, cut it.
Output: runs/<run>/design_spec.md
Structure it exactly like this so the xml-author can consume it:
# Design Spec: <dashboard title>
Question: <the question>
Canvas: 1400x900 fixed | background #f7f7f7 | cards #ffffff
## Palette
primary #4e79a7 | accent #e15759 | positive #59a14f | ink #333333 | ...
## Dashboard title zone
Title text (26pt bold): ...
Subtitle (12pt grey): ...
## Zones (virtual grid 0-100000)
| # | Zone name (= worksheet name) | Chart recipe | x | y | w | h |
|---|---|---|---|---|---|---|
## Worksheet specs
### <Worksheet Name>
- Recipe: <#N from chart-xml-library>
- Fields: rows=..., cols=..., color=..., text=..., detail=...
- Aggregations/derivations: e.g. SUM(Sales), MONTH(Order Date) continuous
- Sort: ...
- Title (takeaway): "..." — mark the phrases to color-match:
e.g. [West + East]{#4e79a7} deliver 70% — [Central]{#999999} lags
- Number format: axis/labels abbreviated ($#K), tooltip exact
- Color: single hue #... / highlight rule ...
- Tooltip: header field + 2-4 labeled context values (exact precision);
BAN tooltips: one line of ADDITIONAL context, never the number again
## Evaluation criteria (for design-linter)
- <5-8 specific, checkable statements about the finished render, e.g.
"BAN row shows Sales, Profit, Margin with PY deltas" or
"Scatter bottom-right quadrant marks are accent-colored">
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 · 70 lines · 46 tokens per session scan A 684fda7ca128
dashboard-designer is an agent published in the GitHub repository blakefeiza/vizwright (4 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 803 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 2026-08-31.
Other agents, from other repositories
d3-expert
Expert in D3.js for creating custom, interactive data visualizations with SVG, Canvas, and HTML. Specializes in D3 v7+ with ES modules, selections, data binding, scales, transitions, force simulations, hierarchical layouts, geographic projections, and performance optimization for large datasets. Use for any data…
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
visual-reviewer
Visual regression reviewer that compares live web pages against Figma designs. Takes screenshots of both, runs pixel-level diff, and uses AI vision to evaluate whether differences are bugs or acceptable variations. Use before merge or deployment to catch visual regressions.
frontend-reviewer
Reviews interface, branding and copy. Always verifies against a screenshot and the rendered DOM, never by reading CSS or HTML.
perspective-audit
Deep accessibility review from 7 access perspectives. Activated by escalation from a11y-planner or a11y-critic when one or more perspectives are flagged at MEDIUM or HIGH alarm level.
ux-researcher
Use this agent when you need to conduct user research, analyze user behavior, validate design decisions, or gather insights about user needs and pain points. This includes tasks like planning usability tests, analyzing user feedback, creating research reports, identifying user personas, evaluating user flows, or…