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 bhaumikmaan/claude-code-master-skills --skill browser-testinggit clone --depth 1 https://github.com/bhaumikmaan/claude-code-master-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/bhaumikmaan/claude-code-master-skills/browser-testing)<a href="https://agentmods.dev/skills/bhaumikmaan/claude-code-master-skills/browser-testing"><img src="https://agentmods.dev/badge/skills/bhaumikmaan/claude-code-master-skills/browser-testing/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/bhaumikmaan/claude-code-master-skills/browser-testing"><img src="https://agentmods.dev/badge/skills/bhaumikmaan/claude-code-master-skills/browser-testing.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 | $0.00052 | $0.01055 |
| Opus 5 | $0.00026 | $0.00528 |
| Sonnet 5 | $0.00010 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
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 9d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Testing
CRITICAL: Always snapshot browser state before interacting. Never assume tabs or elements from a previous session still exist.
Before Any Interaction
- Check for browser tools: Verify that browser automation MCP tools are available. If not, tell the user and stop — don't attempt workarounds.
- Get tab context: Call the tabs/context tool to see what's currently open. Never assume a tab exists from a prior session.
- Snapshot the page: Capture the page structure and element references before clicking, typing, or hovering. Element refs are ephemeral — re-snapshot after any navigation or significant DOM change.
Core Interaction Patterns
Navigation
- Open new pages in new tabs within the user's existing browser session.
- After navigation, wait for the page to load before snapshotting. Use short incremental waits (1-2 seconds) with snapshot checks, not a single long wait.
- Track tab IDs during the session. Never reuse tab IDs from a previous session — they're invalid after the browser restarts.
Element Interaction
- Always snapshot before clicking, typing, or selecting. Use the element ref from the most recent snapshot.
- For elements inside scroll containers, scroll the element into view before clicking.
- Use
fillto replace input contents (clears first),typeto append text. - For contenteditable elements, use
fillas well.
Forms
- Use
fill_formfor multi-field forms — it's more reliable than filling fields one at a time. - After submitting a form, wait for the response and snapshot to verify the result.
Screenshots
- Take screenshots to verify visual state, capture bugs, or document behavior.
- Use element-scoped screenshots for focused verification (e.g., a specific component).
- Use full-page screenshots sparingly — they're large and often not necessary.
Console Log Monitoring
- Check console messages after page loads and interactions to catch JavaScript errors.
- Filter console output for relevant patterns — don't dump the entire console.
- Common patterns to watch for:
Error,TypeError,ReferenceError— runtime JS failuresFailed to load resource— missing assets, broken API callsCORS— cross-origin issuesWarning— React/framework warnings that may indicate bugs
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 98 lines · 52 tokens per session scan A 60258a82bdf5
browser-testing is a skill published in the GitHub repository bhaumikmaan/claude-code-master-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 1,055 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
control-ui
Drive and inspect a local web, IDE, or Electron UI with browser or CDP automation and evidence. Use for UI regressions, screenshots, accessibility snapshots, visual diffs, focus, keyboard, scrolling, resize, console, network, performance, or heap checks. Do not use for backend-only changes or for a screenshot without…
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. Use when testing or debugging a local web app, verifying frontend behavior, or capturing browser screenshots and…
browser-use-agentcore
An AWS AgentCore Browser tool for automated website testing and screenshot capture. Automated web testing checks a site through a browser without requiring every check to be performed by hand.
browser-automation
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping…
ui-test-guard
A Stop hook that catches Claude when it claims a UI change is "done", "deployed", or "verified" without showing evidence that a real-browser UI test actually passed. Stops the curl + grep illusion of testing.
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.