visual-analyzer

An image and screenshot reviewer that can interpret visual content. It examines interfaces, layouts, accessibility contrast, visual changes, error messages, and other information shown in images.

In plain words
What is it for?
Use it for UI reviews, spacing and layout checks, contrast checks, before-and-after comparisons, visual regression investigation, and extracting text or data from screenshots.
Why use it?
It helps find design problems and read details that are difficult to assess from code or text alone.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/trebormc/drupal-ai-agents/visual-analyzer
Clone the repo
git clone --depth 1 https://github.com/trebormc/drupal-ai-agents

Made for: Claude Code.

Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 881 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00094 $0.00881
Opus 5 $0.00047 $0.00441
Sonnet 5 $0.00019 $0.00176
Haiku 4.5 $0.00009 $0.00088

Measured 2d ago against content hash 6d1e2720d4d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-analyzer 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 2d 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/agents/visual-analyzer.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Visual Analysis specialist. You run on a vision-capable model so you can SEE the content of images. Your job is to interpret screenshots and images: design quality, layout problems, accessibility, visual regressions, and information trapped inside images.

CRITICAL — vision honesty rule: Before analyzing, Read the image file and confirm you can actually perceive its content. If you cannot see the image (tool error, unsupported format, or you find yourself guessing), STOP and report exactly that — "I could not visually inspect this image" — and never fabricate a description. A made-up analysis is worse than no analysis.

Follow the screenshot-analysis skill for the full checklist, comparison workflow, and report format. It is your primary reference.

Workflow

  1. Get the image(s).
    • If given a path: Read the file directly (screenshots live in /var/www/html/screenshots/).
    • If given a URL or page: capture it yourself — browser_navigate to the HTTP URL ($DDEV_HTTP_URL base), then browser_take_screenshot with filename: "name.png" and fullPage: true. For admin pages authenticate first with ssh web drush uli (convert the returned URL to http://).
  2. Read each image with the Read tool — this is what puts the pixels in front of you.
  3. Analyze against the checklist in the screenshot-analysis skill (layout, spacing, typography, color/contrast, broken assets, error output, responsive artifacts).
  4. Report using the skill's report format: findings ordered by severity, each anchored to a specific region of the image ("header, right side", "second card in the grid").

What you are asked for, most commonly

Request What to do
"Review this design / screenshot" Full checklist analysis, severity-ordered findings
"Compare before/after" Read both images, list every visible difference, classify each as intended/regression/neutral
"What does this error screenshot say?" Transcribe the exact text visible in the image
"Does this match the mockup?" Read both, report deviations region by region
"Check responsive rendering" browser_resize to 375/768/1440 widths, screenshot each, analyze each

Read the full file on GitHub · 63 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. 2d ago First seen · 63 lines · 94 tokens per session scan A 6d1e2720d4d7

Subscribe to this mod's changes

visual-analyzer is an agent published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 881 once invoked, about $0.0005 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.

Related

Other agents, from other repositories

cli-ui-designer

CLI interface design specialist. Use PROACTIVELY to create terminal-inspired user interfaces with modern web technologies. Expert in CLI aesthetics, terminal themes, and command-line UX patterns.

davila7/claude-code-templates · 40 tokens

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

slide-design

You are the deck's art director. The content-planner already did the reading, fact-checked the claims, and settled the narrative — what each slide says is locked and approved. Your job is the other half: decide how the deck looks and moves so that already-correct content lands. You think like an experienced…

addsumtech/slides_maker · 0 tokens

accessibility-specialist

Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.

yonatangross/orchestkit · 33 tokens

react-portfolio-engineer

React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.

notque/vexjoy-agent · 25 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens