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/srstomp/pokayokay/browser-verificationnpx skills add srstomp/pokayokay --skill browser-verificationgit clone --depth 1 https://github.com/srstomp/pokayokayWrote 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/srstomp/pokayokay/browser-verification)<a href="https://agentmods.dev/skills/srstomp/pokayokay/browser-verification"><img src="https://agentmods.dev/badge/skills/srstomp/pokayokay/browser-verification.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 | $0.00046 | $0.00790 |
| Opus 5 | $0.00023 | $0.00395 |
| Sonnet 5 | $0.00009 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
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 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Verification Skill
Automatically verify UI changes in a real browser after implementation.
When This Skill Is Used
This skill is triggered during the /work workflow after the implementer completes a task that modifies UI-related files. It is NOT a standalone skill - it's integrated into the work loop.
Purpose
Catch visual and functional issues before code review by testing in a real browser. This prevents:
- CSS issues that look fine in code but break in browser
- JavaScript errors that only appear at runtime
- Responsive/layout issues
- Missing visual elements
Testability Checks
Browser verification only runs when ALL three conditions are met:
1. Browser Tools Available
Must have either:
- Playwright MCP tools (
mcp__plugin_playwright_*) - Chrome Extension tools (
mcp__claude-in-chrome__*)
2. Server Running
Must have an HTTP server on a dev port (3000-9999) or ability to start one via package.json scripts.
3. Renderable Files Changed
Task must have modified files that affect browser output:
.html,.css,.scss,.less.tsx,.jsx,.vue,.svelte- Template files (
.hbs,.ejs,.pug) - Files in
components/,views/,ui/,pages/
If any condition fails, verification is silently skipped.
Verification Process
- Navigate to the development server
- Screenshot the initial state
- Analyze the page snapshot for expected elements
- Test interactions if the task involves interactive behavior
- Check console for JavaScript errors
- Report pass/fail with evidence
Advisory Behavior
This is NOT a hard gate. If verification suggests issues but the user believes the implementation is correct:
- User can provide a reason for skipping
- Skip reason is logged in task notes
- Work continues to spec review with warning flag
Configuration
Projects can customize in .pokayokay.json:
{
"browserVerification": {
"enabled": true,
"portRange": [3000, 9999],
"additionalPaths": ["src/templates/"],
"excludePaths": ["src/email-templates/"]
}
}
What ships with it
3 files 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.
- 4d ago First seen · 102 lines · 46 tokens per session scan A 4250a633390c
browser-verification is a skill published in the GitHub repository srstomp/pokayokay (9 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 790 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
browse
Fast headless browser for QA testing and site dogfooding. (gstack).
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
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.
playwright-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.
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.