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.
npx skills add Oriolshhh/runware-image-mcp --skill browser-visual-validationgit clone --depth 1 https://github.com/Oriolshhh/runware-image-mcpWrote 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/oriolshhh/runware-image-mcp/browser-visual-validation)<a href="https://agentmods.dev/skills/oriolshhh/runware-image-mcp/browser-visual-validation"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/browser-visual-validation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/oriolshhh/runware-image-mcp/browser-visual-validation"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/browser-visual-validation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.00524 |
| Opus 5.5 | $0.00009 | $0.00210 |
| Sonnet 5.5 | $0.00004 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
browser-visual-validation 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 1mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Visual Validation
Purpose
Replace code-only confidence with reproducible evidence from the rendered product.
When to use it
- After frontend changes and before completing UI review or improvement workflows.
Instructions
- Discover the repository's documented install and preview commands. Do not invent commands, silently change ports, or install browser tooling without approval.
- Establish a reproducible URL, route, fixture/account, viewport set, and target states. Record authentication or data limitations without exposing secrets.
- Capture a baseline before changes when improving existing UI.
- Use the strongest available browser surface: existing project tests, Playwright, browser-control/MCP, Storybook, or another repository-approved tool.
- Exercise the primary task plus loading, empty, error, success, keyboard/focus, narrow/wide layouts, zoom, reduced motion, and long content as applicable.
- Inspect console errors, failed network requests, runtime exceptions, layout overflow, obscured controls, and focus loss.
- Capture comparable final evidence and run existing unit/component/E2E/visual and accessibility checks. Never update visual baselines merely to make tests pass.
- Write
.agent/evidence/ui/<task>/report.mdwith environment, steps, evidence paths, findings, fixes, remaining risks, and untested coverage. Store binary artifacts only when useful and follow repository policy for committing them.
Output format
A reproducible browser-evidence report with baseline/final comparison, tested viewports/states/interactions, console/network observations, tests, and limitations.
Anti-patterns
- Declaring visual success from source inspection alone.
- Testing only one desktop happy path or using different data for before/after.
- Hiding console errors, blindly accepting screenshot changes, or claiming screen-reader coverage not performed.
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.
- 1mo ago First seen · 48 lines · 22 tokens per session scan A 1ca7111933c1
browser-visual-validation is a skill published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 524 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…