A visual regression testing workflow checks whether a website or app's appearance has changed by comparing new screenshots with saved reference images.

It finds the repository's existing screenshot-testing setup, runs the visual comparison, and guides review of each difference.

It helps distinguish real visual problems from harmless differences before updating the saved screenshots.

vrt-check — Skill for Claude Code by mgiovani

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add mgiovani/cc-arsenal --skill vrt-check

Clone the repo

git clone --depth 1 https://github.com/mgiovani/cc-arsenal

Made for: Claude Code.

Or install cc-arsenal, the plugin that ships this one along with the rest of its 53 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/vrt-check.svg)](https://agentmods.dev/skills/mgiovani/cc-arsenal/vrt-check)

Your own site

<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/vrt-check"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/vrt-check.svg" alt="Measured on agentmods" height="20"></a>

Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,912 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.

Model	Per session	Once invoked
Fable 5.1	$0.00180	$0.01912
Opus 5	$0.00090	$0.00956
Sonnet 5	$0.00036	$0.00382
Haiku 4.5	$0.00018	$0.00191

Measured 8d ago against content hash 1b2d0d2dff07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

vrt-check 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 8d 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.

skills/vrt-check/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VRT Check

Run visual regression tests, then triage every failure by eye before touching a snapshot. The workflow's only real risk is rubber-stamping --update on a diff nobody looked at: everything below exists to prevent that.

Step 1: Discover the tooling

Never assume a command. Different repos wire VRT through different tools. Look for, in order:

Task runner targets: just --list or grep -E 'visual|screenshot|chromatic|snapshot' justfile Makefile for targets like visual-diff, visual-update, test:visual.
package.json scripts: grep -A2 '"scripts"' package.json for chromatic, test:visual, storybook:test, playwright test.*visual.
Storybook test-runner: presence of .storybook/test-runner.ts or @storybook/test-runner in package.json.
Playwright screenshot tests: toHaveScreenshot( calls in *.spec.ts, or a playwright.config.* with snapshotDir/toMatchSnapshot settings.
Chromatic: chromatic.config.json or a chromatic devDependency; these run in CI and produce a web UI, not local diff images, say so and point the user there instead of trying to fake a local diff.
Loki: .loki config or loki devDependency.

Base each check on the actual output of the command you ran (ls, grep, just --list), never assert a file is absent without having listed the directory. If two of these are present, ask the user which one is authoritative rather than running both. If none are found, stop and say so, do not invent a screenshot workflow.

For an unfamiliar repo, where a subagent/Task tool is available, delegate this discovery to it rather than grepping inline yourself; otherwise run the greps above directly. Either way, keep the discovered commands around for the rest of the run.

Step 2: Run the diff

Run the discovered diff target, not the update target, even if the user asked to "fix the visual tests", you need to see what changed before deciding anything should be updated.

just visual-diff        # or whatever Step 1 found

Read the full file on GitHub · 101 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

8d ago First seen · 101 lines · 180 tokens per session scan A 1b2d0d2dff07

Subscribe to this mod's changes

vrt-check is a skill published in the GitHub repository mgiovani/cc-arsenal (7 stars, last pushed 8d ago), licensed MIT. It adds 180 tokens to every session and 1,912 once invoked, about $0.0009 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.

Claude Code Testing agent-skills agentskills ai-agents automation cli

voiden

Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.

VoidenHQ/voiden · 28 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

safe-extraction

Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.

ZaxbyHub/opencode-swarm · 60 tokens

safe-rename

Workflow for safely renaming symbols (functions, types, classes, interfaces, constants, variables) across a codebase. Uses repomap, batchsymbols, and buildcheck to ensure every consumer is updated and nothing breaks.

ZaxbyHub/opencode-swarm · 48 tokens

test-file-split

Protocol for splitting test files that approach or exceed the FR-006 500-line limit (enforced in CI by scripts/check-test-file-cap.ts as a diff-scoped ratchet). Covers describe-block extraction, shared helper management, pure-function extraction, mock isolation verification, and cascading-split detection. Load when a…

ZaxbyHub/opencode-swarm · 77 tokens

confirm-failures-are-causally-linked-to-the-task-before-reportin

When delegating a task affected by this skill, include.

ZaxbyHub/opencode-swarm · 29 tokens