Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/datit309/supergraphnpx agentmods add skills/datit309/supergraph/browser-agentWrote 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/datit309/supergraph/browser-agent)<a href="https://agentmods.dev/skills/datit309/supergraph/browser-agent"><img src="https://agentmods.dev/badge/skills/datit309/supergraph/browser-agent/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/datit309/supergraph/browser-agent"><img src="https://agentmods.dev/badge/skills/datit309/supergraph/browser-agent.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 | $0.00050 | $0.01609 |
| Opus 5.5 | $0.00020 | $0.00644 |
| Sonnet 5.5 | $0.00010 | $0.00322 |
| Haiku 4.5 | $0.00005 | $0.00161 |
Grade A, and why
browser-agent 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 today.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/supergraph:browser-agent
Autonomous human-like browser control and professional QA/QC testcase execution without Playwright.
Powered by native Rust agent-browser (Chrome DevTools Protocol direct, zero bot-detection footprint).
Announce: "🌐 /supergraph:browser-agent — professional QA testing with real user emulation (Rust CDP)..."
Why Agent-Browser over Playwright?
- Zero Bot Detection Footprint: Native Rust client communicating directly via CDP. Removes
navigator.webdriverand disables Blink automation flags. - Human Input Mode (
--input-mode human): Natural Bezier mouse curves, randomized typing cadence, natural dwell times. - Token Efficiency: Compact Accessibility Tree snapshots with
@refidentifiers (~100-300 tokens vs 20,000 HTML tokens). - Session & Profile Reuse: Effortlessly attaches to your authenticated Chrome profile or
--auto-connectto running Chrome on port 9222.
Available Tools / Commands
Can be invoked via MCP (mcp__supergraph-browser__*) or CLI (agent-browser):
| Action | MCP Tool | CLI Command | Purpose |
|---|---|---|---|
| Open URL | agent_browser_open |
agent-browser open <url> |
Navigate to page |
| Read State | agent_browser_snapshot |
agent-browser snapshot -i |
Accessibility tree with @ref |
| Find Target | agent_browser_find |
agent-browser find role button click |
Locate elements semantically |
| Click | agent_browser_click |
agent-browser click @ref |
Click element by ref |
| Type/Fill | agent_browser_fill |
agent-browser fill @ref <text> |
Fill input with human keystrokes |
| Key Press | agent_browser_press |
agent-browser press Enter |
Send keyboard event |
| Wait | agent_browser_wait_for_text |
agent-browser wait <ms> |
Wait for condition or pause |
| Screenshot | agent_browser_screenshot |
agent-browser screenshot <path> |
Capture visual evidence |
| Console Logs | agent_browser_eval |
agent-browser console |
View browser console errors |
| Page Errors | agent_browser_eval |
agent-browser errors |
Catch unhandled exceptions |
| Network Requests | agent_browser_eval |
agent-browser network requests |
Inspect failed API calls |
| Close | agent_browser_close |
agent-browser close |
Close session |
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.
- today Changed · +14 lines 3962197e1bf1
- yesterday First seen · 118 lines · 50 tokens per session scan A 5e553e935e61
browser-agent is a skill published in the GitHub repository datit309/supergraph (22 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,609 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
playwright-qa
QA engineering workflows on top of Playwright. Use when a QA engineer asks to design test cases from a ticket, PRD or acceptance criteria, decide what to automate, write a bug report from a failing test or trace, convert manual test cases (TestRail, Xray, CSV) into Playwright specs with case-ID traceability, or review…
playwright-skill
Current Playwright (1.64) patterns for writing, debugging, and scaling reliable test suites. Use for any Playwright task, even ones you think you know, because the guides cover APIs and CLI flags newer than most training data. Covers writing or fixing tests, locators, a failing or flaky test, a trace.zip or error…
playwright-migration
Step-by-step migration guides for moving to Playwright from Cypress or Selenium/WebDriver — command mappings, architecture changes, and incremental adoption strategies.
playwright-pom
Page Object Model patterns for Playwright — when to use POM, how to structure page objects, and when fixtures or helpers are a better fit.
website-change-verifier
Verify website changes across source, routes, rendering, metadata, discovery surfaces, and deployment state. Use when a user asks to check a new or edited page, confirm an exact replacement, validate a route, inspect responsive behavior, verify metadata or sitemap changes, compare localhost with production, or…