browser-use SKILL.md skillB

browser-use from steipete/agent-scripts is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add steipete/agent-scripts/browser-use@git:20260911.866c26d

Pins git:20260911.866c26d in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
steipete/agent-scripts
Path
skills/browser-use/SKILL.md
Versions recorded
8
Latest version
git:20260911.866c26d, committed Sep 11, 2026
First version recorded
Aug 7, 2026
Size
15,793 bytes
Repository stars
7,386
License
MIT

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.

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

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,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add steipete/agent-scripts/browser-use@sha256:b4c648aa84d66539

The line at the top of this page pins the label git:20260911.866c26d, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2i2ios4yt7fe7anh.svg)](https://markdownregistry.com/a/art_2i2ios4yt7fe7anh)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 8 versions of this file, between Aug 7, 2026 and Sep 11, 2026, about one every 5 days. Its first recorded version is graded A and its latest B.

versioncommittedcommitsizeaudit
git:20260911.866c26d latest2026-09-11 866c26d 15,793 BB view · diff
git:20260911.ec388b92026-09-11 ec388b9 14,959 BB view · diff
git:20260911.6db16aa2026-09-11 6db16aa 14,803 BA view · diff
git:20260812.2e320ff2026-08-12 2e320ff 12,548 BA view · diff
git:20260812.a6902fe2026-08-12 a6902fe 12,025 BA view · diff
git:20260810.587b0dd2026-08-10 587b0dd 10,484 BA view · diff
git:20260809.2cd4d052026-08-09 2cd4d05 9,350 BA view · diff
git:20260807.2469c642026-08-07 2469c64 6,967 BA view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://127.0.0.1:28799)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (15793 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 script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

steipete/agent-scripts · 7,386 stars · license MIT · pushed 2026-10-18 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2i2ios4yt7fe7anh
GET https://markdownregistry.com/api/v1/resolve?ref=steipete/agent-scripts/browser-use
GET https://markdownregistry.com/api/v1/blob/b4c648aa84d66539f4cff8704f50e26760c757d5ae8ad7febb08b98a6e45c343

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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from steipete/agent-scripts

agent-transcript SKILL.md skill
steipete/agent-scripts · skills/agent-transcript/SKILL.md · Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.
git:20260905.1d5ff53 · audit A · 7,386 stars
beeper SKILL.md skill
steipete/agent-scripts · skills/beeper/SKILL.md · Beeper cache: contact hints, room lookup, WhatsApp/iMessage traces, FTS.
git:20260523.0a2d76c · audit A · 7,386 stars
clawsweeper-status SKILL.md skill
steipete/agent-scripts · skills/clawsweeper-status/SKILL.md · ClawSweeper status: URLs, workflow health, active workers, ops snapshot.
git:20260828.8cfe7b9 · audit A · 7,386 stars
clickclack SKILL.md skill
steipete/agent-scripts · skills/clickclack/SKILL.md · ClickClack ops: chat app, Cloudflare Workers deploy, DNS/docs/app, container rollout.
git:20260705.c9a6fb0 · audit A · 7,386 stars
cloudflare-registrar SKILL.md skill
steipete/agent-scripts · skills/cloudflare-registrar/SKILL.md · Cloudflare Registrar: domain availability, prices, registration via mcporter.
git:20260523.0a2d76c · audit A · 7,386 stars
codex-debugging SKILL.md skill
steipete/agent-scripts · skills/codex-debugging/SKILL.md · Codex debugging: codex-rs core/tui/exec/cli/app-server/config.
git:20260523.0a2d76c · audit A · 7,386 stars
codex-first SKILL.md skill
steipete/agent-scripts · skills/codex-first/SKILL.md · Claude Code work routing: delegate hands-on work to Codex under the native-Claude model gate. Keep specification…
git:20261018.6232f9b · audit A · 7,386 stars
codex-huge-context SKILL.md skill
steipete/agent-scripts · skills/codex-huge-context/SKILL.md · Codex 1M context: direct OpenAI Responses API inference, safe Astra/Sol/Terra/Luna input headroom, Keychain delivery…
git:20261012.5a54cf3 · audit B · 7,386 stars
codexbar SKILL.md skill
steipete/agent-scripts · skills/codexbar/SKILL.md · AI service usage/quota via CodexBar CLI: Codex/OpenAI, Claude, Kimi and other provider limits, credits, reset times.
git:20260810.68e90b8 · audit A · 7,386 stars
create-cli SKILL.md skill
steipete/agent-scripts · skills/create-cli/SKILL.md · CLI UX/spec: args, flags, help, output, errors, config, dry-run.
git:20260509.51ee7e5 · audit A · 7,386 stars
discord-clawd SKILL.md skill
steipete/agent-scripts · skills/discord-clawd/SKILL.md · Discord-backed OpenClaw agent/session relay; not archive search.
git:20260523.0a2d76c · audit A · 7,386 stars
domain-dns-ops SKILL.md skill
steipete/agent-scripts · skills/domain-dns-ops/SKILL.md · DNS/domain ops: registrars, zones, redirects, DNS/HTTP verify, manager truth.
git:20260523.0a2d76c · audit A · 7,386 stars

Every file in steipete/agent-scripts

Other files named browser-use

browser-use SKILL.md skill
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.
git:20261010.a182a36 · audit A · 28,586 stars
browser-use SKILL.md skill
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…
v4 · audit A · 11,927 stars
browser-use SKILL.md skill
davidondrej/skills · skills/research-and-web/browser-use/SKILL.md · Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
git:20260925.cb72780 · audit A · 4,161 stars
browser-use SKILL.md skill
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…
git:20260903.d9a1dc2 · audit B · 3,675 stars
browser-use SKILL.md skill
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…
git:20261017.f7fa257 · audit A · 1,049 stars
browser-use SKILL.md skill
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…
git:20251221.f6c90d7 · audit A · 27 stars
browser-use SKILL.md skill
joe-qai/qa-skills · browser-use/SKILL.md · Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
git:20260906.d616bee · audit A · 25 stars
browser-use SKILL.md skill
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…
git:20260828.f7e78f2 · audit B · 7 stars

Browse by kind, by grade B, or by owner.