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/serkan-ozal/browser-devtools-claude/browser-testingnpx skills add serkan-ozal/browser-devtools-claude --skill browser-testinggit clone --depth 1 https://github.com/serkan-ozal/browser-devtools-claudeWrote 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/serkan-ozal/browser-devtools-claude/browser-testing)<a href="https://agentmods.dev/skills/serkan-ozal/browser-devtools-claude/browser-testing"><img src="https://agentmods.dev/badge/skills/serkan-ozal/browser-devtools-claude/browser-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 | $0.00035 | $0.01065 |
| Opus 5 | $0.00017 | $0.00532 |
| Sonnet 5 | $0.00007 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
browser-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 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Testing Skill
Automated browser testing and debugging skill using Browser DevTools MCP.
Page structure: To understand what is on a page, use ARIA snapshot first (a11y_take-aria-snapshot or a11y_take-ax-tree-snapshot), not screenshot. Use screenshot only when you need to verify how something looks visually (e.g. design check, visual bug).
When to Use
This skill activates when:
- User asks to test a web page or application
- User wants to debug frontend issues
- User needs to verify UI behavior
- User asks about page performance or accessibility
- User wants to automate browser interactions
Capabilities
Ref-Based Workflow (Recommended)
- ARIA snapshot first (
a11y_take-aria-snapshot) — Returns refs (e1, e2, …) and a refs map. Options:interactiveOnly,cursorInteractive(for div/span buttons),selector(scope). - Use refs in interactions — Click, fill, hover, etc. accept CSS selector or ref (e.g.
e1,@e1). Refs valid until next snapshot or navigation. - Annotated screenshot —
content_take-screenshotwithannotate: trueoverlays labels [1],[2],… mapping to e1,e2,…
Navigation & Interaction
- Navigate to URLs (
navigation_go-to) — returns ARIA snapshot and refs by default; use response refs for interactions without callinga11y_take-aria-snapshotagain - Same for
navigation_go-back-or-forwardandnavigation_reload(includeSnapshot: true) - Click, fill, hover — selector or ref (e.g.
e1,#submit) - Press keys (
interaction_press-key), scroll (interaction_scroll), drag (interaction_drag)
Content Capture
- Screenshots (
content_take-screenshot) — optionalannotate,annotateContent,cursorInteractive - HTML/text content, PDF
Debugging & Observability
- Get console messages (
o11y_get-console-messages) - Monitor HTTP requests (
o11y_get-http-requests) - Get Web Vitals (
o11y_get-web-vitals) - OpenTelemetry tracing (
o11y_get-trace-id,o11y_set-trace-id)
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 · 72 lines · 35 tokens per session scan A d77498fb09c1
browser-testing is a skill published in the GitHub repository serkan-ozal/browser-devtools-claude (8 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,065 once invoked, about $0.0002 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
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
playwright-dev
Explains how to develop Playwright - add APIs, MCP tools, CLI commands, and vendor dependencies.
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
playwright-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.
playwright-skill
Complete browser automation with Playwright. Auto-detects dev servers, writes reusable test scripts, and supports screenshots, responsive checks, UX validation, login flows, link checks, and arbitrary browser automation. Use when the user wants to test a website, automate browser interactions, validate web…