Agent skill

Browser Use

by steipete in steipete/agent-scripts

Control the user's existing signed-in Chrome: callable Codex Chrome plugin first, then OpenClaw extension-backed mcporter, with direct DevTools attachment only as a last fallback.

MITAuto-check passedProductivity & Automation

Install Browser Use

skills CLI
$ npx skills add steipete/agent-scripts --skill browser-use -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install steipete/agent-scripts browser-use --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/steipete/agent-scripts.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/browser-use .claude/skills/browser-use && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
browser-use
GitHub stars
7.3k
Token cost
~3.9k tokens
SKILL.md length
1,991 words
Files
3
Skills in repo
45
Repo updated
First seen
Licence
MIT

At a glance

Control the user's existing signed-in Chrome: callable Codex Chrome plugin first, then OpenClaw extension-backed mcporter, with direct DevTools attachment only as a last fallback.

  • Works in 3 steps: Use the Codex Chrome or Chrome… → Otherwise prefer the OpenClaw… → Use legacy direct DevTools attachment…
  • Tasks that involve Browser automation
  • SKILL.md covers Route, Extension Relay Model, Setup and Repair and Fail-Closed Readiness Proof, plus 5 more sections
  • Runs Python scripts from its folder

What it does

Browser Use is an agent skill from steipete/agent-scripts. Control the user's existing signed-in Chrome: callable Codex Chrome plugin first, then OpenClaw extension-backed mcporter, with direct DevTools attachment only as a last fallback.

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `auto-allow.py` and `mcporter-config.md`).

It sits in Productivity & Automation, covering Browser automation. The repository describes itself as: Scripts for agents, shared between my repositories. The licence is MIT.

When your agent uses it

  • Tasks that involve Browser automation

Example prompts

  • “/browser-use”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Use the Codex Chrome or Chrome [Internal] plugin when it is callable in
  2. Otherwise prefer the OpenClaw extension-backed mcporter route.
  3. Use legacy direct DevTools attachment only as the explicit last fallback.

What it can do on your machine

Read from SKILL.md and the folder at commit 79150cf. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Browser Use loads about 3.9k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 1,991 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~3.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from steipete/agent-scripts at commit 79150cf, republished under its MIT licence (© steipete). 1,991 words, ~3,949 tokens.

Download SKILL.mdSave it as .claude/skills/browser-use/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
browser-use
description
Control the user's existing signed-in Chrome: callable Codex Chrome plugin first, then OpenClaw extension-backed mcporter, with direct DevTools attachment only as a last fallback.

Browser Use

Control the user's existing real Chrome profile, especially for login-dependent work and live UI verification.

Route

  1. Use the Codex Chrome or Chrome [Internal] plugin when it is callable in the active session. Installed on disk is not enough.
  2. Otherwise prefer the OpenClaw extension-backed mcporter route.
  3. Use legacy direct DevTools attachment only as the explicit last fallback.

For mcporter, the MCP call remains the agent-facing control interface. The OpenClaw extension is the transport underneath it, not a separate tool. Set chromeDevtoolsRelay: "require" on the canonical global Chrome server definition to enforce relay-only routing. Keep the caller policy explicit as well:

bash
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.<tool>

Seeing an agent request the chrome-devtools MCP tool is therefore expected. A Chrome Allow remote debugging? prompt or a relay-policy error indicates that the extension transport was not used. The shared daemon retains canonical policy; a shell environment prefix alone cannot change that policy.

Never use isolated Chrome, the Codex in-app browser, Playwright, Puppeteer, AppleScript, osascript, generic GUI scripting, or macOS open as a browser-control substitute unless the user explicitly asks for an isolated or new browser. Peekaboo is allowed only for Chrome or extension setup and visible prompts. Login-heavy sites often depend on the real profile's cookies, SSO, device trust, and extensions.

For a rendered-browser bug, prove behavior through this real profile. Treat curl, source inspection, API checks, and isolated test browsers as supporting evidence, not substitutes for live UI proof.

Extension Relay Model

OpenClaw creates a random per-host relay key in its mode-0600 credentials directory. The extension and same-host clients use nonce-bound mutual HMAC proofs. The reusable key is never sent to an unverified loopback listener, placed in a URL, or passed to the child MCP process. Keep credentials out of configuration, command output, chat, logs, and screenshots.

On a same-host relay, mcporter authenticates /json/version and upgrades the same retained socket to /cdp, then gives chrome-devtools-mcp a protected one-use local handoff. Agents still call the standard MCP tools; successful relay routing is what removes direct DevTools attachment and Chrome's approval prompt.

New pairings default to All tabs: every ordinary eligible tab is exposed except tabs explicitly paused in the popup. Existing pairings keep their stored mode. In Selected tabs mode, membership in the Chrome tab group titled OpenClaw is the sharing boundary. Restricted/internal pages, incognito, other profiles, and tabs without an eligible URL remain excluded in both modes.

Topology Boundary

Direct remote Gateway pairing over wss:// lets OpenClaw's Gateway-side browser tool control local Chrome. It does not create a local relay for a local mcporter process. Do not routinely copy remote secrets or build ad-hoc SSH tunnels around this boundary.

If local mcporter cannot authenticate to a local relay, the extension-backed mcporter route is unavailable. Report that clearly or use the labeled legacy fallback; never represent remote Gateway control or direct attachment as local relay success.

Setup and Repair

  • Run openclaw browser extension install before Load unpacked. It copies the extension to the stable OpenClaw-owned path, pre-registers that path's deterministic Chrome ID, and prints the path to load. The first native call then pairs automatically for local or browser-node topology.
  • Use openclaw browser extension status --json to verify the installed copy, exact origins, and native-host registrations. Status must report no issues and manualSetupRequired: false.
  • Confirm Settings reports automatic setup ready and the popup reports Connected. New installs should show All tabs unless the user changes the access mode; no copied pairing string or popup setup is part of the normal local flow.
  • A previous native-host miss is cached for the Chrome process. If the extension attempted native messaging before installation, restart Chrome once after installing; repeated retries in the same process cannot repair that cache.
  • After pairing or changing the relay route, stop the mcporter daemon before re-running relay-only proof. A Gateway restart can leave the Chrome DevTools child alive with a dead upstream socket; mcporter daemon stop retires it before the next call creates a fresh connection.
  • Direct remote Gateway pairing remains an Advanced manual flow. It serves the Gateway browser path and does not create a local relay for local mcporter.
Discovery Timeout and Daemon Configuration

MCPorter discovers the actual relay through openclaw browser extension cdp --json. Even packaged OpenClaw can take more than five seconds to cold-start. In mcporter 0.13.10, discovery failure falls back to port 18799; a timeout can therefore appear as network-error at the wrong endpoint, or as browser_owner_conflict when a later discovery returns the real endpoint. Do not interpret that sequence as proof that another Chrome owner or credential rotation caused the failure.

For the shared Chrome owner, use the OS account's canonical ~/.mcporter/mcporter.json (or mcporter.jsonc only when the JSON file is absent). Merge these fields into its existing Chrome definition, preserving its command, arguments and other settings:

json
{
  "chromeDevtoolsRelay": "require",
  "env": {
    "MCPORTER_CHROME_DEVTOOLS_RELAY_TIMEOUT_MS": "20000"
  }
}

The relay timeout bounds each discovery or authentication step; it does not extend the client's total operation deadline. Initial Chrome startup can run several discovery checks before MCP initialization and the requested tool call. On older installed clients, pair the canonical 20000 per-step setting with an explicit --timeout 300000 on the initial call or schema listing. For example:

bash
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.list_pages --timeout 300000 --output text

Newer Chrome-specific outer defaults require an upgraded invoking client. Explicit --timeout, MCPORTER_CALL_TIMEOUT, and MCPORTER_LIST_TIMEOUT still override those defaults; a smaller override can cut startup short.

The daemon intentionally strips inherited MCPORTER_CHROME_DEVTOOLS_RELAY_* and OPENCLAW_* controls from the canonical Chrome environment. Shell exports do not update an existing owner and are not a durable fix for a respawn. Put literal values in the canonical definition's env; do not use placeholders that depend on those stripped variables. If an explicit endpoint is necessary, set MCPORTER_CHROME_DEVTOOLS_RELAY_URL there to the verified credential-free HTTP loopback base URL, for example http://127.0.0.1:28799 after verifying that port. This override does not accept a WebSocket CDP URL such as ws://127.0.0.1:28799/cdp. Prefer discovery with a sufficient timeout over a guessed or hardcoded port, especially when several OpenClaw installations coexist.

After changing canonical settings, let active calls drain and run mcporter daemon stop. If stop refuses because calls remain active, wait for them to finish and retry stop; proceed only after it succeeds. The next call starts a daemon with the saved settings, and subsequent respawns use the same configuration. Verify the relay decision with mcporter daemon status --json and repeat the readiness proof below. Check the installed mcporter version before relying on newer timeout defaults or explicit discovery-failure diagnostics; a source fix does not update an already installed binary or running daemon.

Current openclaw browser extension cdp --json emits non-secret metadata by default, but older versions and legacy-bearer options can expose credentials. Prefer mcporter's redacted status for routine diagnostics, never request legacy credentials, and do not dump process arguments. If credential exposure is suspected, rotate the per-host secret and pair again.

Fail-Closed Readiness Proof

Require every condition below before calling the extension route ready:

  1. Extension status reports the stable copy and exact native registrations with no issues; Settings says automatic setup ready.
  2. The popup says Connected and the intended ordinary tab is not paused. In Selected tabs mode, it must also belong to the OpenClaw group.
  3. mcporter has been stopped after pairing, relay-route or canonical-config changes, and the next call has started a fresh daemon.
  4. The canonical Chrome definition uses chromeDevtoolsRelay: "require", and a call with MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require succeeds. The canonical policy forbids direct DevTools fallback, so success is positive relay proof.
  5. Selection and evaluation both succeed in a known eligible disposable tab.
bash
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.list_pages --args '{}' --output text
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.select_page --args '{"pageId":9}' --output text
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.evaluate_script --args '{"function":"() => ({title: document.title, href: location.href})"}' --output json

A relay-policy error means the extension transport is unavailable; report or repair it instead of retrying without require. A blocking Allow remote debugging? prompt proves legacy attachment was attempted.

Show full SKILL.md (728 more words)Show less

Typical Flow

List pages, select only a shared target, snapshot before acting, and use fresh snapshot UIDs. Prefer DOM snapshots over screenshots unless layout matters.

bash
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.list_pages --args '{}' --output text
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.select_page --args '{"pageId":9}' --output text
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.take_snapshot --args '{}' --output text
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.click --args '{"uid":"1_38","includeSnapshot":true}' --output text
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.fill --args '{"uid":"1_13","value":"text","includeSnapshot":true}' --output text
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.evaluate_script --args '{"function":"() => document.title"}' --output json

For live UI proof, capture the current page state before the action, perform the requested interaction, then snapshot or evaluate the rendered result. Keep secrets out of DOM, input, network, console, and screenshot output. For credential checks, return only safe shape such as present/absent, length, status code, or account/organization label.

If automation is unavailable, report the verification gap instead of silently switching to prohibited or isolated tooling.

Argument and Output Mechanics

--args accepts inline JSON only. It does not read @file. Flag-style named arguments do:

bash
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.navigate_page url=@/tmp/target-url.txt --output text
MCPORTER_CHROME_DEVTOOLS_RELAY_POLICY=require mcporter call chrome-devtools.evaluate_script function=@/tmp/probe.js --output json

Treat this as a safety primitive, not just ergonomics. A sign-in URL, magic link, or callback URL is credential-equivalent: write it to a mode-0600 file and pass it by file reference so it never reaches shell history, process arguments, or captured tool output. The same form carries a multi-line JavaScript function without quoting or control-character errors.

Other call mechanics worth knowing before a login flow:

  • Generic client defaults are 60 seconds for calls and 30 seconds for listings, separate from the relay's per-step discovery/authentication timeout. Slow initial Chrome startup on older clients needs --timeout 300000 as described above. Choose an explicit timeout for later interactive work when needed.
  • take_screenshot with filePath is confined to the server's configured workspace roots and refuses arbitrary paths. Omit filePath, read the base64 image from --output json, and decode it locally.
  • new_page can fail with a restricted/unavailable tab when the target is not shared. Navigate an already-shared tab instead of creating one.
  • mcporter list <server> --schema prints the real function signatures. Use it rather than guessing parameter names.

Clicks That Do Not Click

A click by uid can return success and still do nothing: some pages bind their handlers so that a synthetic click is ignored. Silence is not proof of action, so verify state after every activation rather than assuming it worked.

When a click no-ops, drive the control from the keyboard with press_key (Tab, Shift+Tab, Enter) and confirm focus with a screenshot before committing. Focus rings are the only reliable evidence of which control is about to receive Enter, and consent screens routinely put the safe-looking prominent button next to a low-emphasis link that is the one you actually want. Blind Enter on such a page picks the wrong control.

Snapshot uid values are invalidated by any navigation or re-render. Re-run take_snapshot and re-resolve the uid after every step; a stale uid reports that the element no longer exists, which is a cue to re-snapshot rather than to retry the same call.

When the Relay Goes Empty Mid-Task

The relay can stop exposing tabs partway through a task because eligible tabs were closed, the current tab became restricted or paused, Selected tabs mode lost its group members, or the extension disconnected. The failure can be quiet: list_pages may return an empty result and later calls time out.

Treat an empty page list as "the relay has no eligible tabs", not "the browser is gone". Confirm Chrome is running, check the popup connection and current-tab Pause/Allow state, then check the access mode. Only Selected tabs mode requires restoring the OpenClaw group. Restarting mcporter cannot repair extension disconnection, tab eligibility, or access policy.

Do not escalate to a full-profile attachment or an isolated browser to route around it. When the task is a sign-in the user is present for, the faster and more honest move is to hand the URL to the browser the user is already sitting at, and if the flow's callback listens on another host, forward that port to the user's machine first. Otherwise report the access gap.

Legacy Fallback: Full-Profile Direct Attachment

Use this only after the callable plugin and authenticated local extension relay are unavailable. It exposes the full real-profile tab set and can show Chrome's blocking Allow remote debugging? prompt.

When a visible, unambiguous Chrome prompt asks to allow the attachment, approve it once, then rerun list_pages. If the prompt is absent, ambiguous, or the retry fails, stop and ask the user or report that Chrome DevTools MCP is unavailable. Do not loop approvals, repeatedly restart Chrome or mcporter, or kill browser processes.

Verify that list_pages shows the intended real-profile tabs before acting. Always label this path as full-profile direct attachment, never as OpenClaw extension relay success.

© steipete, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in skills/browser-use of steipete/agent-scripts.

  • SKILL.md
  • auto-allow.py
  • mcporter-config.md

Open the folder on GitHubat commit 79150cf

Compare with similar skills

Browser Use next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Browser Use compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Browser Use this skillsteipete/agent-scripts7.3k—~3.9kAutomated safety check: PassMIT
Agent Browserquran/quran.com-frontend-next1.9k41 repos~3.3kAutomated safety check: PassNone
Dev-Browser CLI AutomationSawyerHood/dev-browser6.7k1 repos~455Automated safety check: PassMIT
Camoufox CLIBin-Huang/camoufox-cli3501 repos~4.5kAutomated safety check: PassMIT
BrowserVibiumDev/vibium2.9k—~4.8kAutomated safety check: PassApache-2.0
Use Agent Browser For Airimoeru-ai/airi50k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Agent Browser

    quran/quran.com-frontend-next

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    1.9k GitHub starsUsed in 41 repos~3.3k tokens
    Productivity & AutomationAuto-check passed
  • Dev-Browser CLI Automation

    SawyerHood/dev-browser

    Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web…

    6.7k GitHub starsUsed in 1 repo~455 tokens
    Productivity & AutomationAuto-check passed
  • Camoufox CLI

    Bin-Huang/camoufox-cli

    Anti-detect browser automation CLI & Skills for AI agents. An agent skill from Bin-Huang/camoufox-cli.

    350 GitHub starsUsed in 1 repo~4.5k tokens
    Productivity & AutomationAuto-check passed
  • Browser

    VibiumDev/vibium

    Automate browsers with the Vibium CLI. An agent skill from VibiumDev/vibium.

    2.9k GitHub stars~4.8k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts.

    50k GitHub stars~1.1k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Browser Use Terminal

    browser-use/terminal

    Direct browser control via the Browser Use Terminal CLI. An agent skill from browser-use/terminal.

    651 GitHub stars~2.1k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

More from steipete/agent-scripts

All 45 skills in this repo
  • Mac Fleet Maintenance

    steipete/agent-scripts

    Inventories and maintains a fleet of Macs from a desired-state file: package updates, repo and Xcode sync, and disk, backup and security health reports.

    7.3k GitHub stars~4.8k tokensUpdated 3 days ago
    Auto-check passed
  • Agent Transcript for PRs

    steipete/agent-scripts

    Finds a coding agent's session log, trims and redacts it, and inserts it into a GitHub PR or issue only when the user has asked for a transcript.

    7.3k GitHub starsUsed in 1 repo~698 tokens
    Auto-check passed
  • Parallels macOS VM Lab

    steipete/agent-scripts

    Uses a clean Parallels macOS VM to test GUI automation, TCC permission prompts and screenshot tools like Peekaboo, verifying results from outside the guest.

    7.3k GitHub stars~1.8k tokensUpdated 3 days ago
    Auto-check passed
  • ClawSweeper Status

    steipete/agent-scripts

    Reports ClawSweeper's status with a bundled script: workflow health, active workers, queue health and recently merged, reviewed, commented and closed items.

    7.3k GitHub stars~972 tokensUpdated 3 days ago
    Auto-check passed
  • GitHub Project Triage

    steipete/agent-scripts

    Produces maintainer-facing triage cards for a project's GitHub issues and pull requests, each with its URL, risk, test state, blockers and a next action.

    7.3k GitHub stars~4k tokensUpdated 3 days ago
    Auto-check passed
  • Nano Banana Image Generation

    steipete/agent-scripts

    Generates and edits images with Google's Nano Banana 2 (Gemini 3.1 Flash Image) through a uv script, with a draft-then-final workflow and sizes from 512 to 4K.

    7.3k GitHub stars~1.4k tokensUpdated 3 days ago
    Auto-check passed

Questions about Browser Use

What does Browser Use do?

Control the user's existing signed-in Chrome: callable Codex Chrome plugin first, then OpenClaw extension-backed mcporter, with direct DevTools attachment only as a last fallback. Browser Use is an agent skill from steipete/agent-scripts. Control the user's existing signed-in Chrome: callable Codex Chrome plugin first, then OpenClaw extension-backed mcporter, with direct DevTools attachment only as a last fallback.

When should I use Browser Use?

Browser Use fits situations like: tasks that involve Browser automation.

How do I install Browser Use in Claude Code?

Run `npx skills add steipete/agent-scripts --skill browser-use -a claude-code`. Or copy the skill folder (skills/browser-use in steipete/agent-scripts) into .claude/skills/browser-use in your project. Claude Code loads it when a task matches its description.

How do I install Browser Use in Codex?

Run `npx skills add steipete/agent-scripts --skill browser-use -a codex`. Or copy the skill folder (skills/browser-use in steipete/agent-scripts) into .agents/skills/browser-use in your project. Codex loads it when a task matches its description.

Can I use Browser Use in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add steipete/agent-scripts --skill browser-use -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/browser-use, .gemini/skills/browser-use, .github/skills/browser-use and .opencode/skills/browser-use in your project.

What does Browser Use need to run?

Going by SKILL.md and its folder, Browser Use needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Browser Use access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Browser Use safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Browser Use use?

Browser Use is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Browser Use use?

About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Browser Use?

Skills that share tags, products or a category with Browser Use: Agent Browser (quran/quran.com-frontend-next, 1.9k stars), Dev-Browser CLI Automation (SawyerHood/dev-browser, 6.7k stars), Camoufox CLI (Bin-Huang/camoufox-cli, 350 stars) and Browser (VibiumDev/vibium, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Browser Use?

steipete (a GitHub user) maintains it in steipete/agent-scripts, which has 7,259 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on October 4, 2026.

Source: steipete/agent-scripts on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.