Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/JansenAnalytics/claudexnpx agentmods add skills/jansenanalytics/claudex/visual-reviewWrote 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/jansenanalytics/claudex/visual-review)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/visual-review"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/visual-review.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00750 |
| Opus 5 | $0.00012 | $0.00375 |
| Sonnet 5 | $0.00005 | $0.00150 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
visual-review 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 4d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
visual-review
Screenshot comparison and visual regression detection: pixel diffing, before/after overlays, threshold-based change detection.
When to Use
- Comparing UI states before and after changes
- Detecting visual regressions in CI or manual review
- Creating before/after diff images for stakeholder review
- Validating that CSS/layout changes didn't break other components
- Generating visual regression reports across multiple pages
Scripts
screenshot-diff.py
Compares two PNG screenshots pixel-by-pixel and generates a diff image.
python3 scripts/screenshot-diff.py \
--before before.png \
--after after.png \
--output diff.png \
--threshold 0.5
Arguments:
--before— Path to the baseline screenshot (required)--after— Path to the new screenshot (required)--output— Path for the diff image output (default:diff.png)--threshold— Maximum allowed change percentage, 0-100 (default:0.5)
Output:
- Diff image with changed pixels highlighted in red on a dimmed background
- Prints change percentage to stdout
- Exit code 0 if change% ≤ threshold, exit code 1 if above
Notes:
- Images must be the same dimensions (script will error if not)
- Uses per-pixel RGB distance comparison (threshold per-pixel: 30/255)
visual-report.py
Generates a Markdown report from a directory of before/after screenshot pairs.
python3 scripts/visual-report.py \
--dir ./screenshots \
--output report.md \
--threshold 0.5
Arguments:
--dir— Directory containing before/after pairs (required)--output— Output report path (default: stdout)--threshold— Pass/fail threshold percentage (default:0.5)
Naming convention: Files must be named <name>-before.png and <name>-after.png.
Report includes:
- Each pair with change percentage and pass/fail status
- Sorted by most changed first
- Summary: total pairs, pass count, fail count
overlay-gen.py
Creates visual comparison images in different modes.
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.
- 4d ago First seen · 110 lines · 24 tokens per session scan A a6699613743f
visual-review is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 750 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.
testing-e2e
End-to-end testing patterns with Playwright — page objects, AI agent testing, visual regression, accessibility testing with axe-core, and CI integration. Use when writing E2E tests, setting up Playwright, implementing visual regression, or testing accessibility.
storybook-testing
Storybook 10 testing patterns with Vitest integration, ESM-only distribution, CSF3 typesafe factories, play() interaction tests, Chromatic TurboSnap visual regression, module automocking, accessibility addon testing, and autodocs generation. Use when writing component stories, setting up visual regression testing…
Espresso Android Testing
Android UI testing with Espresso framework including view matchers, actions, assertions, idling resources, and RecyclerView testing patterns.
hatch3r-browser-verify
Opt-in browser verification skill — spec-run-first Playwright verification (assertions execute in the runner, agent reads only failures), axe-core a11y audits, toHaveScreenshot() regression diffs, E2E test scaffolds, and snapshot-mode exploratory driving. Default ON for UI-affecting agent invocations; disable globally…
playwright-e2e-testing
Production-grade Playwright end-to-end testing skill for AI coding agents. Provides specialized guidance for writing, debugging, and maintaining Playwright tests in TypeScript, JavaScript, and Python. Covers the full testing lifecycle: test structure and architecture (Page Object Model, fixtures, custom matchers)…