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/billy-enrizky/openbrowser-ai/e2e-testingnpx skills add billy-enrizky/openbrowser-ai --skill e2e-testinggit clone --depth 1 https://github.com/billy-enrizky/openbrowser-aiWrote 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/billy-enrizky/openbrowser-ai/e2e-testing)<a href="https://agentmods.dev/skills/billy-enrizky/openbrowser-ai/e2e-testing"><img src="https://agentmods.dev/badge/skills/billy-enrizky/openbrowser-ai/e2e-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 | $0.00064 | $0.01841 |
| Opus 5 | $0.00032 | $0.00920 |
| Sonnet 5 | $0.00013 | $0.00368 |
| Haiku 4.5 | $0.00006 | $0.00184 |
Grade C, and why
e2e-testing scanned grade C with 2 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 5d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(openbrowser-ai:*) Bash(curl:*) Bash(uv:*) Bash(irm:*) Read Write How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-to-End Testing
Simulate real user interactions and verify web application behavior using Python code execution. Covers navigation, form interaction, content assertions, and multi-page flows.
All code runs via openbrowser-ai -c. The daemon starts automatically and persists variables across calls. All browser functions are async -- use await.
The CLI daemon also persists cookies and login state in ~/.config/openbrowser/profiles/daemon/storage_state.json, so authenticated sessions can be reused across later runs.
Setup
Before running, verify openbrowser-ai is installed:
openbrowser-ai --help
If not found, install:
# macOS/Linux
curl -fsSL https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.sh | sh
# Windows (PowerShell)
irm https://raw.githubusercontent.com/billy-enrizky/openbrowser-ai/main/install.ps1 | iex
Workflow
Step 1 -- Navigate and verify page load
openbrowser-ai -c - <<'EOF'
await navigate("https://staging.example.com")
state = await browser.get_browser_state_summary()
assert "example" in state.url.lower(), f"Unexpected URL: {state.url}"
assert state.title, "Page title is empty"
print(f"Page loaded: {state.title} ({state.url})")
EOF
Step 2 -- Content assertions
openbrowser-ai -c - <<'EOF'
# Check for expected text using JS
has_welcome = await evaluate("""
(function(){ return !!document.body.textContent.match(/Welcome to Example App/i) })()
""")
assert has_welcome, "Welcome message not found"
# Check specific element content
h1_text = await evaluate("document.querySelector('h1')?.textContent?.trim()")
assert h1_text == "Example App", f'Expected "Example App", got "{h1_text}"'
# Check no error messages
error_count = await evaluate("document.querySelectorAll('.error-message').length")
assert error_count == 0, f"Found {error_count} error messages on page"
print("All content assertions passed")
EOF
Step 3 -- Test user interactions (login flow)
openbrowser-ai -c - <<'EOF'
# Get form fields
state = await browser.get_browser_state_summary()
for idx, el in state.dom_state.selector_map.items():
if el.attributes.get("type") in ("email", "text", "password") or el.tag_name == "button":
etype = el.attributes.get("type", "")
placeholder = el.attributes.get("placeholder", "")
print(f"[{idx}] <{el.tag_name}> type={etype} placeholder=\"{placeholder}\"")
# Fill and submit
await input_text(index=3, text="[email protected]")
await input_text(index=4, text="test-password")
await click(index=5) # Login button
await wait(2)
# Assert logged in
state = await browser.get_browser_state_summary()
assert "dashboard" in state.url.lower() or "welcome" in state.title.lower(), \
f"Login may have failed. URL: {state.url}, Title: {state.title}"
print("Login test passed")
EOF
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.
- 5d ago First seen · 236 lines · 64 tokens per session scan C 79f0323bdb9f
e2e-testing is a skill published in the GitHub repository billy-enrizky/openbrowser-ai (241 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 1,841 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browser4-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.
test-production
Runs bin/test-production.ps1 to acceptance-test a production (or prerelease) release of browser4-cli. Use when asked to run production tests, acceptance-test a release, or verify the published CLI.
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…
pr-test
E2E manual testing of PRs/branches using docker compose, agent-browser, and API calls. TRIGGER when user asks to manually test a PR, test a feature end-to-end, or run integration tests against a running system.
browser-viz-verify
Verifies that a NetClaw-generated visualization HTML file (three.js, canvas, drawio, UML, markmap) actually renders correctly — screenshot, console-error check, and an optional Lighthouse audit. Use immediately after generating any browser-based visualization output, to close the QA gap that otherwise requires a human…
write-frontend-tests
Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write them. TRIGGER when user asks to write frontend tests, add test coverage, or 'write tests for my changes'.