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/letta-ai/letta-code/browser-usenpx skills add letta-ai/letta-code --skill browser-usegit clone --depth 1 https://github.com/letta-ai/letta-codeWrote 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/letta-ai/letta-code/browser-use)<a href="https://agentmods.dev/skills/letta-ai/letta-code/browser-use"><img src="https://agentmods.dev/badge/skills/letta-ai/letta-code/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 | $0.00097 | $0.03662 |
| Opus 5 | $0.00048 | $0.01831 |
| Sonnet 5 | $0.00019 | $0.00732 |
| Haiku 4.5 | $0.00010 | $0.00366 |
Grade B, and why
browser-use scanned grade B with 1 finding 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Chrome refuses to run as root without `--no-sandbox`, so add that flag when How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Use with CDP
Drive the browser through its native Chrome DevTools Protocol over the
remote-debugging WebSocket. This works with zero dependencies: launch the
browser with --remote-debugging-port, then talk JSON over fetch and the
built-in WebSocket global (available in Bun and Node ≥ 22 — no ws package).
If the project already has Playwright or Puppeteer installed, using it is usually simpler — reach for raw CDP when no automation library is available, when protocol-level control is needed, or when recording a deterministic visual demo.
Protocol reference: https://chromedevtools.github.io/devtools-protocol/.
The running browser's exact schema is at http://127.0.0.1:<port>/json/protocol;
tip-of-tree docs can differ from the installed version.
Managed cloud sandbox default: visible browser
When running in a cloud sandbox, default every browser task to the visible managed desktop, even when the user did not explicitly ask to watch. Most browser tasks exist because plain HTTP is not enough; a headless browser is more likely to trigger bot protection and gives the user no way to observe or take over. This matters especially for clicking or typing, forms, sign-in, checkout/payment, CAPTCHAs or bot protection, and user handoff.
For the first managed-sandbox browser window, use the skill's launcher instead of assembling Chrome, DISPLAY, or Xvfb commands yourself:
/root/.letta/cloud-skills/browser-use/scripts/open-visible-browser.sh 'https://example.com'
It starts the managed desktop and launches Chrome through the persistent Cua
Driver with its required root flag. Then load computer-use for visible
interaction. If protocol-level control is necessary, use Cua Driver's explicit
browser_prepare flow after binding the exact visible window; do not pass
remote-debugging flags through launch_app. The launcher exits zero only
after Cua Driver reports an on-screen browser window. If it exits nonzero, stop
and report the launch failure instead of claiming the browser opened.
What ships with it
1 file 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.
- yesterday First seen · 364 lines · 97 tokens per session scan B 5a098559482f
browser-use is a skill published in the GitHub repository letta-ai/letta-code (3,178 stars, last pushed yesterday), licensed Apache-2.0. It adds 97 tokens to every session and 3,662 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-02.
Other skills, from other repositories
notte
Deploy browser automations as scheduled, API-callable serverless Functions — plus stealth sessions, vault-backed login, captcha solving, and natural-language agent runs via the Notte CLI. Turns any browser flow into a deterministic Bitterbot-callable endpoint, ideal for crystallized skills + dream-engine cron…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
linggen
Linggen — durable cross-host memory plus browser control, over two local MCP servers: ling-mem for memory, the Linggen engine for browser, X and agents. Memory: three-tier model (core + long-term + episodic staging) of who the user is, not a log of what was done; same ling-mem daemon and store in Claude Code, Codex…
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol.
agent-browser
Use Vercel agent-browser for browser automation through a persistent visible Chrome or Chromium CDP session. Trigger when the user asks to use agent-browser, Vercel agent browser, real Chrome, non-headless browser automation, CDP, Hotbox, LinkedIn profile browser work, or authenticated browser workflows.