Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Browser Use
Direct browser control via CDP. For task-specific edits, use `agent-workspace/agent_helpers.py`. For setup, install, or connection problems, read https://github.com/browser-use/browser-harness/blob/main/install.md.
## When Not to Use
A basic fetch of public information needs no browser. If a plain HTTP request can read it — a public page, an API, docs — use `curl` or your fetch tool, and leave the browser alone. Use browser-use when the task needs interaction (click, type, navigate), the user's logged-in session, JS rendering, or a bot-protected page. If a direct fetch fails or returns a shell page, then escalate to the browser.
Domain skills are off by default. Set `BH_DOMAIN_SKILLS=1` to enable them; see the bottom section.
**If `BH_DOMAIN_SKILLS=1` and the task is site-specific, read every file in the matching `$BH_AGENT_WORKSPACE/domain-skills/<site>/` directory before inventing an approach.**
## Usage
```bash
browser-use <<'PY'
print(page_info())
PY
```
- Invoke as `browser-use`. Use heredocs for multi-line commands.
- Helpers are pre-imported. `run.py` calls `ensure_daemon()` before `exec`.
…
The line at the top of this page pins the label git:20260925.cb72780, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (10526 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
davidondrej/skills · 4,161 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6d42rcmycab5wedx
GET https://markdownregistry.com/api/v1/resolve?ref=davidondrej/skills/browser-use
GET https://markdownregistry.com/api/v1/blob/58d07219a900116242ce948253bf1d6ebd84d9a5b0743e3e1e5609f0f8296a51
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
davidondrej/skills · skills/agent-orchestration/bb-cli/SKILL.md · Use this when controlling bb. The bb CLI inspects and manages threads, environments, projects, machines, providers…
davidondrej/skills · skills/agent-orchestration/bb-plugins/SKILL.md · Build, install, and debug bb plugins. Use when the user wants a bb plugin, a sidebar panel, a bb CLI subcommand, an…
davidondrej/skills · skills/agent-orchestration/codex-subagent/SKILL.md · Launch OpenAI Codex CLI as a subagent (no API key). Use when delegating a self-contained coding task to Codex from…
davidondrej/skills · skills/agent-orchestration/fable-review/SKILL.md · Launch an independent Fable code review and return it verbatim. Use only when the user explicitly invokes /fable-review.
davidondrej/skills · skills/agent-orchestration/fable-safe-prompt/SKILL.md · Make minimal prompt edits to reduce false-positive refusals from Fable. Use only when the user explicitly invokes…
davidondrej/skills · skills/agent-orchestration/git-worktree/SKILL.md · Use Git worktrees to isolate parallel coding tasks. Use when setting up a task checkout, working in a shared repo, or…
davidondrej/skills · skills/agent-orchestration/goal-loop/SKILL.md · Draft /goal prompts and explain persistent agent loops. Use for goal or Ralph loops, autonomous run setup, monitoring…
davidondrej/skills · skills/agent-orchestration/gpt-review/SKILL.md · Launch an independent GPT-6.1-Sol Max code review and return it verbatim. Use only when the user explicitly invokes…
davidondrej/skills · skills/agent-orchestration/herdr/SKILL.md · Operate and coordinate AI agents in Herdr workspaces in Ghostty. Use when the user mentions Herdr or asks to inspect…
qwenlm/qwen-code · packages/core/src/skills/bundled/browser-use/SKILL.md · Control the user's Chrome through the existing persistent Node REPL and the Qwen Browser SDK.
jxxghp/moviepilot · skills/browser-use/SKILL.md · Use this skill when the user asks the agent to open, browse, inspect, extract content from, click through, fill forms…
letta-ai/letta-code · src/skills/builtin/browser-use/SKILL.md · Control a real browser to navigate pages, click, type, fill forms, inspect rendered UI, take screenshots, or record…
xuzhougeng/wisp-science · skills/browser-use/SKILL.md · Use this skill to drive Wisp Browser Runtime sessions (shared daily Chrome or workspace Chrome) — open pages, read…
mjunaidca/mjs-agent-skills · docs/panaversity-ri-vault/skills/browser-use/SKILL.md · Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract…
joe-qai/qa-skills · browser-use/SKILL.md · Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
kripu77/software-factory · skills/browser-use/SKILL.md · Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite…