visual-verifier

visual-verifier is a skill for Claude Code, Codex from aleksbuss/orchestra. It costs 75 tokens per session (558 once invoked), scanned A, original, MIT.

A quality-checking helper for web pages that uses browser tools to inspect how an application loads and looks.

In plain words
What is it for?
Use it to test local or remote pages, take screenshots, inspect page structure, compare changes, and investigate frontend errors.
Why use it?
It helps catch broken pages, missing elements, and layout problems instead of relying on assumptions about the interface.

Skill for Claude CodeCodex

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 skills/aleksbuss/orchestra/visual-verifier
Any agent
npx skills add aleksbuss/orchestra --skill visual-verifier
Clone the repo
git clone --depth 1 https://github.com/aleksbuss/orchestra

Made for: Claude Code, Codex.

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.

agentmods badge for visual-verifier

README.md
[![agentmods](https://agentmods.dev/badge/skills/aleksbuss/orchestra/visual-verifier.svg)](https://agentmods.dev/skills/aleksbuss/orchestra/visual-verifier)
Your own site
<a href="https://agentmods.dev/skills/aleksbuss/orchestra/visual-verifier"><img src="https://agentmods.dev/badge/skills/aleksbuss/orchestra/visual-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 558 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00075 $0.00558
Opus 5 $0.00037 $0.00279
Sonnet 5 $0.00015 $0.00112
Haiku 4.5 $0.00007 $0.00056

Measured 4d ago against content hash e5d2d3066f5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

visual-verifier scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **Deployment Check**: Verify the dev server is running (e.g., `curl -s http://localhost:3000`).
bundled-skills/visual-verifier/SKILL.md · 44 lines

What it actually says

Visual Verifier

You are a Senior QA Engineer specializing in Automated Testing and Computer Vision. Your job is to be the "eyes" of the development team.

Capabilities

  1. Functional Testing: Navigate to local or remote URLs to verify that the app doesn't crash (e.g., check for 404 or white screens).
  2. Visual QA: Use take_screenshot or the browser subagent to capture the UI state.
  3. Layout Debugging: Analyze raw DOM/CSS to identify why elements are misaligned.

Workflow: The "Self-Healing UI" Loop

When a user or another agent claims they have "finished" a UI task:

  1. Deployment Check: Verify the dev server is running (e.g., curl -s http://localhost:3000).
  2. First Look: Navigate to the page using npx agent-browser open http://localhost:3000.
  3. Analyze: Take a DOM snapshot using npx agent-browser snapshot -i.
  4. Correction:
    • If the page has an error: Fix the code.
    • If elements are missing from the Accessibility Tree, adjust the JSX/CSS.
  5. Verify: Use npx agent-browser diff snapshot after applying a patch to ensure it actually changed.

Guidelines

  • Never guess what the UI looks like. Always take a fresh screenshot after changes.
  • Check Mobile and Desktop. Don't assume responsive design "just works."
  • Verify Accessibility. Look for missing ARIA labels or poor contrast.
  • Console is King. Always check the developer console for hidden JavaScript errors that don't manifest visually.

Tools of the Trade

  • Core command: npx agent-browser snapshot -i (Extracts an Accessibility Tree mapping DOM elements to interactive refs).
  • Assertion: Use the Accessibility Tree output instead of raw images. Modifying layout/styles reflects in the semantic output of the snapshot.
  • Diffing: npx agent-browser diff snapshot (Compare current structure with the previous state).
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. 4d ago First seen · 44 lines · 75 tokens per session scan A e5d2d3066f5b

Subscribe to this mod's changes

visual-verifier is a skill published in the GitHub repository aleksbuss/orchestra (2 stars, last pushed 8d ago), licensed MIT. It adds 75 tokens to every session and 558 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

tui-smoke-test-with-tmux

Verify and debug this project's ratatui/crossterm TUI by running the ACN agent CLI inside tmux, capturing terminal screens as text, sending scripted keys, checking stderr, and writing focused tmux regressions for requested TUI flows. Use after changes to src/sessiontui, src/bin/acn.rs interactive mode, terminal…

FTShare-Lab/agent-claim-network · 108 tokens

tdd-workflow

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

affaan-m/ECC · 43 tokens

e2e-testing

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Use when writing Playwright tests, structuring page objects, or fixing flaky E2E runs in CI.

affaan-m/ECC · 53 tokens

testing

Testing workflow and quality standards for writing and running tests. Use when: (1) Writing new tests, (2) Adding a new feature that needs tests, (3) Modifying logic that has existing tests, (4) Before claiming a task is complete.

iOfficeAI/AionUi · 55 tokens

playwright-cli

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

VoltAgent/voltagent · 52 tokens

connect-agent

Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…

langwatch/langwatch · 102 tokens