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 agentmods add skills/ironbee-ai/ironbee-devtools-skills/visual-testingnpx skills add ironbee-ai/ironbee-devtools-skills --skill visual-testinggit clone --depth 1 https://github.com/ironbee-ai/ironbee-devtools-skillsWrote 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/ironbee-ai/ironbee-devtools-skills/visual-testing)<a href="https://agentmods.dev/skills/ironbee-ai/ironbee-devtools-skills/visual-testing"><img src="https://agentmods.dev/badge/skills/ironbee-ai/ironbee-devtools-skills/visual-testing.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 | $0.00050 | $0.01783 |
| Opus 5 | $0.00025 | $0.00892 |
| Sonnet 5 | $0.00010 | $0.00357 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
visual-testing 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 6d 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Testing Skill
Perform visual testing, UI verification, and design comparison using screenshots, responsive testing, and Figma integration.
When to Use
This skill activates when:
- User wants to verify UI appearance
- User asks to compare page with design or Figma
- User needs responsive design testing
- User wants to check for visual regressions
- User mentions UI bugs or styling issues
- User asks about design parity
- User wants to validate implementation against design
Capabilities
Screenshot Capture
ironbee-browser-devtools-cli content take-screenshot --name "homepage"
ironbee-browser-devtools-cli content take-screenshot --name "element" --selector ".hero"
ironbee-browser-devtools-cli content take-screenshot --name "fullpage" --full-page
ironbee-browser-devtools-cli content take-screenshot --name "photo" --type jpeg --quality 80
ironbee-browser-devtools-cli content save-as-pdf --name "page" --format A4
Annotated Screenshot (ref labels)
Overlay numbered labels [1],[2] on interactive elements. Call a11y take-aria-snapshot first.
ironbee-browser-devtools-cli a11y take-aria-snapshot
ironbee-browser-devtools-cli content take-screenshot --annotate --name "annotated"
ironbee-browser-devtools-cli content take-screenshot --annotate --annotate-content --name "with-headings"
Responsive Testing
ironbee-browser-devtools-cli interaction resize-viewport --width 375 --height 667 # Mobile
ironbee-browser-devtools-cli interaction resize-viewport --width 768 --height 1024 # Tablet
ironbee-browser-devtools-cli interaction resize-viewport --width 1920 --height 1080 # Desktop
Figma Design Comparison
ironbee-browser-devtools-cli figma compare-page-with-design \
--figma-file-key "ABC123xyz" \
--figma-node-id "12:34"
ironbee-browser-devtools-cli figma compare-page-with-design \
--figma-file-key "ABC123xyz" \
--figma-node-id "12:34" \
--selector ".hero-section"
ironbee-browser-devtools-cli figma compare-page-with-design \
--figma-file-key "ABC123xyz" \
--figma-node-id "12:34" \
--mssim-mode semantic
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.
- 6d ago First seen · 226 lines · 50 tokens per session scan A 3363c1aafef8
visual-testing is a skill published in the GitHub repository ironbee-ai/ironbee-devtools-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,783 once invoked, about $0.0003 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.
Other skills, from other repositories
Author and Run Regression Tests with Agent QA
Use Agent QA's CLI and MCP server to author, validate, run, debug, and triage natural-language web and mobile regression tests with persistent test memory and reviewable run evidence.
run-ux-validation
Validate a user journey by running Stunt Double workflows or checklists and reporting the results.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -…
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)…
playwright-tabbed-orchestration
Parent Agent uses playwright-tabbed to allocate browser tabs and partition tasks, then spawns child agents in parallel — each operating on its assigned tabid — for browser acceptance testing or automation, with a final aggregated summary. Suitable for multi-page validation, parallel module checks, and…
alethia
Drive a real browser with plain English via Alethia — the patent-pending zero-IPC agent-driven testing runtime. Use when the user asks to smoke-test a local app, run an accessibility (WCAG) or security (NIST SP 800-53) audit, prove the EA1 safety gate works, bootstrap test coverage on an unknown page, run parallel…