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 atretyak1985/swarmery --skill browser-verificationgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/browser-verification)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/browser-verification"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/browser-verification/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/atretyak1985/swarmery/browser-verification"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/browser-verification.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 | $0.00044 | $0.00708 |
| Opus 5 | $0.00022 | $0.00354 |
| Sonnet 5 | $0.00009 | $0.00142 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
browser-verification 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Canonical procedure for verifying UI behavior in a real browser through the Playwright MCP tools (mcp__plugin_playwright_playwright__browser_*). Extracted from duplicated agent sections — @tech-lead, @ui-developer, @verification-agent, and @code-reviewer reference this skill and keep only their role-specific invariants.
Guardrails (never violate)
- Confirm a live target first:
browser_navigate, then verify the response — never assume a URL is up. - Snapshot before acting — never act on assumed DOM state.
- Use throwaway/seed data; never mutate real records.
browser_run_code_unsafe/browser_evaluaterun arbitrary JS in the page — authorized local/staging targets only, never a production origin.- Always
browser_closewhen finished to release the browser session. - A browser check confirms behavior; it does not replace the automated test suite or the quality gate. Read-only verifiers keep findings supplementary and warning-level — they never flip a deterministic PASS/FAIL verdict.
Resources
- Read
resources/verification-procedure.mdwhen running a verification — target discovery, the core loop, the observation-only variant, domain E2E routing, inputs, and related skills.
How to use
What it does
Gives you one repeatable procedure for checking UI behavior in a real browser: navigate to the page, take an accessibility snapshot, drive the flow, and capture screenshots, console errors, and network failures as evidence. It also fixes the safety rules — snapshot before acting, seed data only, never production.
When to use it
- You changed a component or page and want to see it render and behave live.
- A bug only shows up at runtime — hydration errors, failed API calls, broken responsive layout — that build and type-check never catch.
- You need visual evidence (screenshot, console log, network trace) for a review or verification report.
- You are a read-only verifier and want a supplementary warning-level signal alongside the deterministic test verdict.
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.
- 6d ago First seen · 58 lines · 44 tokens per session scan A b0749cdbdd81
browser-verification is a skill published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 708 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 2026-09-03.
Other skills, from other repositories
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
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.
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
agent-browser
Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.
webapp-selenium-testing
Author and maintain versioned Selenium WebDriver tests with Java and JUnit 5. Use for creating, debugging, or running Selenium specs, implementing Page Objects, handling explicit waits, capturing screenshots, or setting up Maven test projects. Supports Chrome, Firefox, and Edge. Keywords: Selenium WebDriver, Java…
loom-e2e-testing
End-to-end testing for web applications with Playwright, Cypress, Selenium, and Puppeteer.