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/marchatton/agent-skills/browser-usenpx skills add marchatton/agent-skills --skill browser-usegit clone --depth 1 https://github.com/marchatton/agent-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/marchatton/agent-skills/browser-use)<a href="https://agentmods.dev/skills/marchatton/agent-skills/browser-use"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/browser-use.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 | $0.00053 | $0.00579 |
| Opus 5 | $0.00026 | $0.00290 |
| Sonnet 5 | $0.00011 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
browser-use 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browser-use
Purpose
- Persistent browser session across commands.
- Element index workflow:
state-> act by index.
When
- Need quick multi-step browser automation without writing Playwright.
- Need reuse logged-in Chrome session (real browser mode).
- Need parallel sessions (
--session).
Install
# one-off
uvx "browser-use[cli]" open https://example.com
# permanent
uv pip install "browser-use[cli]"
browser-use install # downloads Chromium/deps
Core Loop
browser-use open https://example.com
browser-use state # list elements w/ indices
browser-use click 5
browser-use input 3 "hello"
browser-use screenshot
browser-use state # verify + get next indices
browser-use close
Modes
browser-use --browser chromium open <url> # default (headless)
browser-use --browser chromium --headed open <url> # visible window
browser-use --browser real open <url> # your Chrome (cookies/login)
browser-use --browser remote open <url> # cloud browser (API key)
Common Commands
browser-use open <url>
browser-use state [--json]
browser-use click <idx> | dblclick <idx> | rightclick <idx> | hover <idx>
browser-use input <idx> "text" | type "text"
browser-use scroll up|down [n]
browser-use screenshot
browser-use get <what> # read page/element info
browser-use back | switch | close-tab
browser-use cookies export <path> | cookies import <path>
browser-use profile list|create|update|delete
browser-use sessions
browser-use server status|logs|stop
browser-use close [--all]
Sessions
browser-use --session work open https://work.example.com
browser-use --session personal open https://personal.example.com
browser-use --session work state
browser-use close --all
Rules (agent-friendly)
- Always run
browser-use statebefore acting; indices change after navigation. - After each navigation/submit: re-run
state(don’t reuse stale indices). - Prefer
--headedwhile debugging. - Cleanup:
browser-use close(orclose --all) when done.
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 · 79 lines · 53 tokens per session scan A 4d7d7cf8dc86
browser-use is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 579 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.
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.
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…