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/ramp-public/cursor-plugin/browser-automationnpx skills add ramp-public/cursor-plugin --skill browser-automationgit clone --depth 1 https://github.com/ramp-public/cursor-pluginWrote 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/ramp-public/cursor-plugin/browser-automation)<a href="https://agentmods.dev/skills/ramp-public/cursor-plugin/browser-automation"><img src="https://agentmods.dev/badge/skills/ramp-public/cursor-plugin/browser-automation.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 | $0.00066 | $0.02773 |
| Opus 5 | $0.00033 | $0.01386 |
| Sonnet 5 | $0.00013 | $0.00555 |
| Haiku 4.5 | $0.00007 | $0.00277 |
Grade A, and why
browser-automation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation
Automate Google Chrome via playwright-cli (pw). Maintains a persistent Chrome profile at ~/.pw-agent/.playwright-profile/ so logins and cookies survive across sessions.
Prerequisites
- Node.js installed
playwright-cliinstalled:npm install -g @playwright/cli- Minimum version:
0.1.0(check withplaywright-cli --version) - If
playwright-cliis not found after install, the npm global bin may not be in PATH. Fix with:export PATH="$(npm root -g)/../bin:$PATH"
Setup
~/.pw-agent/ is the runtime home. It holds the pw launcher script and persistent Chrome state.
First-time setup
-
Create runtime directories:
mkdir -p ~/.pw-agent/.playwright-profile ~/.pw-agent/.playwright-cli ~/.pw-agent/.playwright-mcp -
Create a launcher script at
~/.pw-agent/pw:cat > ~/.pw-agent/pw << 'LAUNCHER' #!/usr/bin/env bash cd "$(dirname "$0")" # Ensure npm global bin is in PATH NPM_BIN="$(npm root -g 2>/dev/null)/../bin" [ -d "$NPM_BIN" ] && export PATH="$NPM_BIN:$PATH" exec playwright-cli "$@" LAUNCHER chmod +x ~/.pw-agent/pw -
Seed the profile by opening a site:
cd ~/.pw-agent && ./pw open https://example.comLog in to any services you need. Close the browser when done. The profile persists for future sessions.
CRITICAL: Never delete ~/.pw-agent/.playwright-profile/ — it contains saved logins and cookies. Re-setup should only recreate the launcher script and mkdir -p missing directories.
Usage
All commands run from ~/.pw-agent/:
cd ~/.pw-agent && ./pw open https://example.com
./pw snapshot # Capture full DOM as YAML accessibility tree
./pw screenshot # Capture viewport as PNG
./pw click e42 # Click element by ref ID
./pw fill e42 "text" # Fill form field
./pw press Enter # Press keyboard key
./pw stop # Close browser
Headed by default — do not pass --headless
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 · 288 lines · 66 tokens per session scan A 3ae096fde98a
browser-automation is a skill published in the GitHub repository ramp-public/cursor-plugin (1 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 2,773 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
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…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.