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 arozumenko/sdlc-skills --skill browser-verifygit clone --depth 1 https://github.com/arozumenko/sdlc-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/arozumenko/sdlc-skills/browser-verify)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/browser-verify"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/browser-verify/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/arozumenko/sdlc-skills/browser-verify"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/browser-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
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 | $0.00047 | $0.02421 |
| Opus 5 | $0.00023 | $0.01210 |
| Sonnet 5 | $0.00009 | $0.00484 |
| Haiku 4.5 | $0.00005 | $0.00242 |
Grade A, and why
browser-verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Verify
Testing-grade browser automation using Chrome controlled through the Chrome DevTools
Protocol. All interactions use real CDP Input domain events (mouse coordinates,
key events) — not synthetic JS .click(). Zero external dependencies beyond
Node 22's built-in WebSocket.
Architecture
Scripts live in the scripts/ directory alongside this SKILL.md:
chrome-launcher.sh— Start/stop/status Chrome with remote debuggingcdp.mjs— Full CDP client with 50+ commands
No npm install required. Uses Node 22 built-in WebSocket.
Resolving Script Paths
The scripts are in the scripts/ subdirectory of this skill. Resolve the path
from your .claude/skills/browser-verify/ install location:
SCRIPTS=".claude/skills/browser-verify/scripts"
bash "$SCRIPTS/chrome-launcher.sh" start --headless
node "$SCRIPTS/cdp.mjs" navigate "https://example.com"
Workflow
1. Start Chrome
bash "$SCRIPTS/chrome-launcher.sh" start
# Headless (no window, faster):
bash "$SCRIPTS/chrome-launcher.sh" start --headless
2. Run Commands
node "$SCRIPTS/cdp.mjs" <command> [args] [--flags]
3. Stop Chrome
bash "$SCRIPTS/chrome-launcher.sh" stop
Command Reference
Navigation
| Command | Example | Purpose |
|---|---|---|
navigate <url> |
navigate "https://example.com" |
Open URL, wait for load |
reload |
reload |
Reload current page |
back |
back |
Browser back |
forward |
forward |
Browser forward |
page-info |
page-info |
Title, URL, counts, viewport, meta |
list-targets |
list-targets |
List open tabs |
new-tab [url] |
new-tab "https://example.com/about" |
Open new tab |
close-tab [id] |
close-tab |
Close tab |
Visual
| Command | Example | Purpose |
|---|---|---|
screenshot |
screenshot --output /tmp/page.png |
Full page capture |
screenshot --selector <s> |
screenshot --selector ".card" |
Element capture |
screenshot --full |
screenshot --full --output /tmp/full.png |
Beyond viewport |
viewport <w> <h> |
viewport 375 812 |
Set viewport size |
pdf |
pdf --output /tmp/page.pdf |
Save as PDF |
emulate <device> |
emulate mobile |
Device emulation |
What ships with it
5 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.
- 9d ago First seen · 231 lines · 47 tokens per session scan A 831c84221784
browser-verify is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 2,421 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 2026-08-30.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
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.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…