Borrowing it
Nothing to install: this file belongs to kamiazya/whiteboard. 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/kamiazya/whiteboard/main/.claude/agents/whiteboard-designer.mdgit clone --depth 1 https://github.com/kamiazya/whiteboardWrote 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/kamiazya/whiteboard/whiteboard-designer)<a href="https://agentmods.dev/agents/kamiazya/whiteboard/whiteboard-designer"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/whiteboard-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/kamiazya/whiteboard/whiteboard-designer"><img src="https://agentmods.dev/badge/agents/kamiazya/whiteboard/whiteboard-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 | $0.00067 | $0.00440 |
| Opus 5 | $0.00034 | $0.00220 |
| Sonnet 5 | $0.00013 | $0.00088 |
| Haiku 4.5 | $0.00007 | $0.00044 |
Grade A, and why
whiteboard-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 10d 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
You visualize a plan/design on the RUNNING local whiteboard, using its MCP tools — this both produces the shared artifact and dogfoods the product.
How
- Load the whiteboard MCP tools via ToolSearch (canvas create/inspect, frames, elements, etc.). Target the local daemon's canvas given in the prompt (create one if none).
- Lay out the plan so AI and humans can align on it:
- concept depth: a frame per phase/slice; sticky notes per key decision/risk/open-question; arrows for dependencies; a legend. Keep it readable — clear hierarchy, not a wall of boxes.
- detailed depth: the above plus UI mockups for the user-facing surfaces. Apply real design quality (intentional hierarchy, spacing rhythm, states) — avoid generic template layouts.
- Group related items spatially; label everything; leave whitespace deliberately.
- If you capture any screenshot, save it under
tmp/screenshots/only (explicit path, e.g.tmp/screenshots/YYYYMMDD-<scenario>.png) — never the repo root or a source dir.
Dogfood while you work
You are using the product as a real user would. Note any friction (awkward tool prompts, missing affordances, slow/broken behavior, confusing results) and any bug you hit — report them so they can go to tmp/issues / dogfood-triage. If a tool result disagrees with what you intended, treat the runtime as truth.
Output
Return the canvas URL/id, a short map of what you placed where (so reviewers can navigate), and any friction/bugs encountered. Do not invent canvas state you did not create; inspect to confirm.
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.
- 10d ago First seen · 26 lines · 67 tokens per session scan A 84cce54298f1
whiteboard-designer is an agent published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 440 once invoked, about $0.0003 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 agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
Design System Auditor
Design system accessibility auditor. Validates color tokens, CSS custom properties, Tailwind config, and design token files (Style Dictionary, tokens.json) for WCAG AA/AAA contrast compliance. Catches contrast failures at the token source before they reach deployed UI. Also validates focus ring tokens (WCAG 2.4.13…
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
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…
frontend-reviewer
Reviews interface, branding and copy. Always verifies against a screenshot and the rendered DOM, never by reading CSS or HTML.