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/skills/visual-evidence/SKILL.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/skills/kamiazya/whiteboard/visual-evidence)<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.
<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>- 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 | $0.00070 | $0.02495 |
| Opus 5 | $0.00035 | $0.01247 |
| Sonnet 5 | $0.00014 | $0.00499 |
| Haiku 4.5 | $0.00007 | $0.00249 |
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.
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))
})
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.
- 5d ago Changed · +20 lines 60b19303cdd5
- 9d ago First seen · 198 lines · 70 tokens per session scan A 12f7608756ba
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…