whiteboard: Skill for Claude Code

.claude/skills/visual-evidence/SKILL.md

visual-evidence is a skill for Claude Code from kamiazya/whiteboard. It costs 70 tokens per session (2,495 once invoked), scanned A, original, Apache-2.0.

Instructions for producing a before-and-after image when a code change affects how a canvas is rendered. Rendering means turning the diagram data into the pixels a user sees.

In plain words
What is it for?
It is for visual evidence in pull requests involving edge routing, layout, themes, or the SVG rendering system.
Why use it?
It helps reviewers see whether the change fixed the intended visual defect, rather than relying only on code or descriptions. The process compares the same example before and after the change.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is kamiazya/whiteboard's own configuration. It tells Claude Code how to work on whiteboard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything whiteboard configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { renderSceneToSvg } from '../svg/backend.js'.

Part of the whiteboard plugin — 21 skills, 18 agents, 3 hooks shipped together

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/kamiazya/whiteboard/main/.claude/skills/visual-evidence/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kamiazya/whiteboard

Made for: Claude Code.

Or install whiteboard, the plugin that ships this one along with the rest of its 21 skills, 18 agents, 3 hooks.

Wrote 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.

agentmods badge for visual-evidence

README.md
[![agentmods](https://agentmods.dev/badge/skills/kamiazya/whiteboard/visual-evidence/github.svg)](https://agentmods.dev/skills/kamiazya/whiteboard/visual-evidence)
Your own site
<a href="https://agentmods.dev/skills/kamiazya/whiteboard/visual-evidence"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/visual-evidence/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.

agentmods 80×15 button for visual-evidence

Your own site · 80×15
<a href="https://agentmods.dev/skills/kamiazya/whiteboard/visual-evidence"><img src="https://agentmods.dev/badge/skills/kamiazya/whiteboard/visual-evidence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,495 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.02495
Opus 5 $0.00035 $0.01247
Sonnet 5 $0.00014 $0.00499
Haiku 4.5 $0.00007 $0.00249

Measured 5d ago against content hash 60b19303cdd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

visual-evidence 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 5d 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.

.claude/skills/visual-evidence/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Before/after figures for a rendering change

AGENTS.md requires visual evidence on a PR whose change has a user-visible effect. For a routing or layout change that means: the same canvas, rendered by the code before and after, side by side. A reviewer should see the defect and the fix without cloning anything.

The whole thing is four steps and about five minutes. The traps below are the ones that actually cost time — every one of them has produced a wrong or misleading figure at least once.

1. Pick a case the change actually fixes

Do not eyeball this. A canvas can look wrong for several reasons at once, and the biggest offender is usually not the one you fixed — twice, a case picked by "worst total ink" turned out to be dominated by a defect class the change did not touch, and the figure showed the same flaw on both sides.

Select by the metric the change targets, and require it to go to zero:

// throwaway test: score every corpus case before and after, keep the ones
// this change actually repaired
const fixed = Object.keys(before).filter((name) => before[name] > 0 && after[name] === 0)

Run it once with the change, once with it stashed, and diff the two maps. Prefer the smallest case in the list — three nodes reads; eight does not.

2. Render both versions through the real pipeline

A throwaway test, because the pipeline needs a measurer and a body parser that only the test-utils have. Write to a path from the environment so one file serves both runs:

// packages/canvas-render/src/layout/__render.test.ts  (delete when done)
import { writeFileSync } from 'node:fs'
import { it } from 'vitest'
import { renderSceneToSvg } from '../svg/backend.js'
import { createFakeMeasure } from '../test-utils/fake-measure.js'
import { layoutSpatialCanvas } from './spatial-canvas.js'

it('render', () => {
  const scene = layoutSpatialCanvas(canvas, {
    measure: createFakeMeasure(),
    parseBody: (text) => ({ type: 'root', children: [{ type: 'paragraph', children: [{ type: 'text', value: text }] }] }),
    appearance: {
      resolveNode: () => ({ fill: '#ffffff', stroke: '#404040' }),
      resolveEdge: () => ({ stroke: '#d04040' }),
      resolveLabel: () => ({ fill: '#303030', fontFamily: 'sans-serif' }),
    },
    geometry: { paddingPx: 8, labelFontSizePx: 12, minContentWidthPx: 1 },
  })
  writeFileSync(process.env.OUT as string, renderSceneToSvg(scene))
})

Read the full file on GitHub · 218 lines

Changes

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.

  1. 5d ago Changed · +20 lines 60b19303cdd5
  2. 9d ago First seen · 198 lines · 70 tokens per session scan A 12f7608756ba

Subscribe to this mod's changes

visual-evidence is a skill published in the GitHub repository kamiazya/whiteboard (6 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 2,495 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.