visual-diff SKILL.md skillA

visual-diff from zwolf25/tokenminning is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add zwolf25/tokenminning/visual-diff@git:20260914.7766564

Pins git:20260914.7766564 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
zwolf25/tokenminning
Path
tools/visual-diff/SKILL.md
Versions recorded
1
Latest version
git:20260914.7766564, committed Sep 14, 2026
Size
4,341 bytes
Repository stars
33
License
MIT

Run this BEFORE viewing (Read-ing) any screenshot, slide export, or UI mockup image to check whether an AI-made edit worked — not after. This is default behavior, not opt-in: pipe the screenshot through visual-diff.js as part of the same step that produces or locates the image, rather than viewing it first and diffing later — a post-hoc PostToolUse rewrite doesn't reliably work for this in current Claude Code (see the still-open bug anthropics/claude-code#68951, where output-rewriting hooks…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# visual-diff

Pixel-diff pre-filter for screenshot validation. Compares a new screenshot against a cached
baseline of the same artifact: if nothing meaningfully changed, you never view the image at
all (near-zero vision tokens); if something did change, you view a small crop of just the
changed region instead of the full screenshot.

**Token rule (do not break):** on a `skip` decision, do not `Read` the screenshot — the JSON
result is the answer ("no visual change, X% diff"). On a `crop` decision, `Read` only
`cropPath`, never the original full screenshot. On a `full` decision (first time seeing this
artifact), there's no baseline yet to compare against — view the original if you need to,
that only happens once per artifact.

## Step 1 — Prereq gate

Needs `node` on PATH plus the global `pixelmatch`/`pngjs` packages (`npm install -g pixelmatch
pngjs`, one-time). If missing, install first — don't fall back to viewing the raw screenshot
just to avoid the install step, that's the exact token cost this skill exists to avoid.

## Step 2 — Run it

```
node visual-diff.js "<screenshot-path>" --key "<stable-artifact-key>"
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add zwolf25/tokenminning/visual-diff@sha256:96a6ffba92ed939d

The line at the top of this page pins the label git:20260914.7766564, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_istrfjwdchgwaesg.svg)](https://markdownregistry.com/a/art_istrfjwdchgwaesg)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 14, 2026.

versioncommittedcommitsizeaudit
git:20260914.7766564 latest2026-09-14 7766564 4,341 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4341 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

zwolf25/tokenminning · 33 stars · license MIT · pushed 2026-10-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_istrfjwdchgwaesg
GET https://markdownregistry.com/api/v1/resolve?ref=zwolf25/tokenminning/visual-diff
GET https://markdownregistry.com/api/v1/blob/96a6ffba92ed939d72a36eb75665d07553fb1280b425d73eabebb39db65ba351

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from zwolf25/tokenminning

doc-convert SKILL.md skill
zwolf25/tokenminning · tools/doc-convert/SKILL.md · Convert documents locally, without spending model tokens — PDF/DOCX/PPTX/XLSX → Markdown, and Markdown → styled DOCX…
git:20260907.723b1fa · audit A · 33 stars

Every file in zwolf25/tokenminning

Browse by kind, by grade A, or by owner.