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 LuizEduPP/Rememb --skill agent-browsergit clone --depth 1 https://github.com/LuizEduPP/RemembWrote 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/luizedupp/rememb/agent-browser)<a href="https://agentmods.dev/skills/luizedupp/rememb/agent-browser"><img src="https://agentmods.dev/badge/skills/luizedupp/rememb/agent-browser/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/luizedupp/rememb/agent-browser"><img src="https://agentmods.dev/badge/skills/luizedupp/rememb/agent-browser.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 | $0.00108 | $0.07659 |
| Opus 5.5 | $0.00043 | $0.03064 |
| Sonnet 5.5 | $0.00022 | $0.01532 |
| Haiku 4.5 | $0.00011 | $0.00766 |
Grade A, and why
agent-browser 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 1mo 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.
This is a copy
91% identical to agent-browser — 136 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 850 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with agent-browser
The CLI uses Chrome/Chromium via CDP directly. Install via npm i -g agent-browser, brew install agent-browser, or cargo install agent-browser. Run agent-browser install to download Chrome. Existing Chrome, Brave, Playwright, and Puppeteer installations are detected automatically. Run agent-browser upgrade to update to the latest version.
Core Workflow
Every browser automation follows this pattern:
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
agent-browser open <form-url>
agent-browser snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"
agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "$APP_PASSWORD"
agent-browser click @e3
agent-browser wait 2000
agent-browser snapshot -i # Check result
Command Chaining
Commands can be chained with && in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls.
# Chain open + snapshot in one call (open already waits for page load)
agent-browser open <page-url> && agent-browser snapshot -i
# Chain multiple interactions
agent-browser fill @e1 "[email protected]" && agent-browser fill @e2 "$APP_PASSWORD" && agent-browser click @e3
# Navigate and capture
agent-browser open <page-url> && agent-browser screenshot
When to chain: Use && when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs).
Handling Authentication
When automating a site that requires login, choose the approach that fits:
Option 1: Import auth from the user's browser (fastest for one-off tasks)
What ships with it
10 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.
- references/authentication.md 8.1 KB
- references/commands.md 11 KB
- references/profiling.md 3.3 KB
- references/proxy-support.md 4.7 KB
- references/session-management.md 4.1 KB
- references/snapshot-refs.md 5.2 KB
- references/video-recording.md 3.4 KB
- templates/authenticated-session.sh 3.6 KB runs code
- templates/capture-workflow.sh 1.8 KB runs code
- templates/form-automation.sh 1.8 KB runs code
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.
- 1mo ago First seen · 850 lines · 108 tokens per session scan A 2ec6d0b0023f
agent-browser is a skill published in the GitHub repository LuizEduPP/Rememb (5 stars, last pushed 11d ago), licensed MIT. It adds 108 tokens to every session and 7,659 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to agent-browser, differing in 136 lines, and is treated as a copy.
Other skills, from other repositories
dev-in-browser
Use your browser to view https://verso.localhost which is tied to livereload dev server which is already running. You can inspect that page (including taking screenshots!) to validate that your changes fixed the issue.
web-scraping
Mass crawl/scrape sites incl. anti-bot (Cloudflare, Akamai, DataDome, PerimeterX). Crawl4AI = scale (arunmany, dispatchers, deep crawl, LLM-ready markdown); Camoufox = fingerprint evasion. For: scrape N pages, crawl a site, extract structured data, 403/challenge/bot-detection, captcha.
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.
pn-smoke-tests
Run smoke or E2E tests, debug failures, and verify fixes. Use for end-to-end verification before or after changes.
web-scraping
Extract clean content from URLs via MCP. Use when the user asks to scrape a URL, read docs/blog/article pages, summarize a link, extract links, search page text, batch-scrape URLs, or get OG/title metadata without Firecrawl.
playwright-human-mode
Visible, supervised, human-mode browser co-working. PRIMARY browser = Playwright MCP run VISIBLY on your local machine (vision, keyboard, mouse, click, screenshot) for real-time round-trip work you watch: program → drive the browser → check → iterate. Logs in with your credentials when it can; on CAPTCHA/2FA it pauses…