Stagehand is a software development kit for browser agents that automate websites through Playwright-style APIs and natural-language actions. It is for building browser automation in TypeScript, Python, and Go, and the catalogue entries support its use as a skill, MCP integration, and instruction.
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 browserbase/stagehand --skill browsegit clone --depth 1 https://github.com/browserbase/stagehandWrote 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/browserbase/stagehand/browse)<a href="https://agentmods.dev/skills/browserbase/stagehand/browse"><img src="https://agentmods.dev/badge/skills/browserbase/stagehand/browse/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/browserbase/stagehand/browse"><img src="https://agentmods.dev/badge/skills/browserbase/stagehand/browse.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 | $0.00109 | $0.04168 |
| Opus 5.5 | $0.00044 | $0.01667 |
| Sonnet 5.5 | $0.00022 | $0.00834 |
| Haiku 4.5 | $0.00011 | $0.00417 |
Grade A, and why
browse 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 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.
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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browse CLI
Use browse as the primary Browserbase command-line interface.
It can:
- drive a local or Browserbase-hosted browser session
- inspect pages through accessibility snapshots, screenshots, DOM/text reads, and network capture
- interact with pages by refs, selectors, XPath, keyboard, mouse, files, and viewport controls
- manage Browserbase projects, sessions, contexts, extensions, fetch, and search APIs
- develop, publish, and invoke Browserbase Functions
- browse and scaffold Browserbase templates
- diagnose local or remote browser setup issues
- discover and install Browse.sh catalog skills
- install or refresh this Browse CLI skill
Setup Check
Verify the CLI exists before relying on it:
which browse || npm install -g browse
browse --help
Install or refresh this skill with:
browse skills install
Use browse <topic> --help for exact flags before running unfamiliar commands.
Browser Target Selection
Browser driver commands auto-start the browse daemon when needed. Choose the browser target per command with flags:
browse open https://example.com --local
browse open https://example.com --local --headed
browse open https://example.com --remote
browse open https://example.com --remote --verified --proxies
browse open https://example.com --auto-connect
browse open https://example.com --cdp 9222
browse open https://example.com --cdp ws://127.0.0.1:9222/devtools/browser/<id>
Use local mode for development, localhost, trusted sites, and fast iteration. Use --auto-connect only when the user explicitly wants to attach to an already-running debuggable Chrome session with existing cookies or login state; use --local when no debuggable Chrome is available. Use remote mode when Browserbase credentials are available and the site needs hosted browser infrastructure, Verified browser mode, CAPTCHA solving, proxies, or session persistence.
--local requires Chrome or Chromium already installed on the machine. In containers, CI, and sandboxes with no browser installed, use --remote instead of --local. If --local fails with "No Chrome or Chromium found" and BROWSERBASE_API_KEY is set, switch to --remote — do not retry --local.
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 Changed · +5 lines 6c4d6e0ae477
- 1mo ago First seen · 378 lines · 109 tokens per session scan A 9954bcd2ecfb
browse is a skill published in the GitHub repository browserbase/stagehand (25,690 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 4,168 once invoked, about $0.0004 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 2026-09-16.
Other skills, from other repositories
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
moli-websearch
Search the web by keyword or reverse-search images with Moli to find subjects, sources, exact matches, or similar images—even when Moli is not named. For fetching a known URL, use moli-webfetch.
moli-cdp-server
Start Moli's CDP server and connect Playwright, Puppeteer, or raw CDP clients. Use to run a headless-browser CDP endpoint, replace a Chromium process, attach over CDP, enable real layout and screenshot surfaces, or diagnose CDP discovery, connection, and target startup—even when Moli is not named.
webcmd-browser
Use when a live browser task requires Playwright interaction, authenticated handoff, visible UI verification, or ad-hoc page inspection.
browser_harness
../../SKILL.md.
compatibility-testing
Cross-browser, cross-platform, and cross-device compatibility testing ensuring consistent experience across environments. Use when validating browser support, testing responsive design, or ensuring platform compatibility.