Browser Harness

Control a real browser via CDP: clicking, typing, navigation, logged-in sessions, JS-rendered or bot-protected pages. Not for plain HTTP fetches of public content - use curl for those.

18,774 stars 1,851 forksWriting & Content

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add browser-use/browser-harness --skill browser-harness

Manual install

git clone --depth 1 https://github.com/browser-use/browser-harness.git /tmp/browser-harness
mkdir -p ~/.claude/skills
cp -r /tmp/browser-harness/. ~/.claude/skills/browser-harness

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# browser-harness

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-harness 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-harness <<'PY'
print(page_info())
PY
```

- Invoke as `browser-harness`. Use heredocs for multi-line commands.
- Helpers are pre-imported. `run.py` calls `ensure_daemon()` before `exec`.
- First navigation for a task is `new_tab(url)`, not `goto_url(url)`. The daemon
  preserves the attached tab across separate CLI invocations, so do not call
  `new_tab()` again in every script.
- Keep one working tab per task/site. Before opening another, inspect
  `current_tab()` and `list_tabs()` and use `switch_tab()` to reuse a matching

Read the full skill on GitHub

Details

Skill name: browser-harness
Repository: browser-use/browser-harness
License: MIT
Repo updated: 30 October 2026

FAQ

What does the Browser Harness skill do?

Control a real browser via CDP: clicking, typing, navigation, logged-in sessions, JS-rendered or bot-protected pages. Not for plain HTTP fetches of public content - use curl for those.

How do I install the Browser Harness skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add browser-use/browser-harness --skill browser-harness. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Browser Harness popular?

It lives in browser-use/browser-harness, which has 18,774 GitHub stars and 1,851 forks.

Related skills

Linkedin Marketing

5.4k

sergebulaev/linkedin-skills

Plan, draft, audit, and publish LinkedIn posts and comments. Use when the user wants to write a viral LinkedIn post, draft a comment or reply on any LinkedIn post URL, audit a draft against 2026 algorithm heuristics, remove AI tells, extract hook formulas from viral posts, or plan a week of content. Powered by the Publora API for publishing. User provides post/comment URLs, skill drafts content, user approves, then publishes.

Writing & ContentIn 4 lists879

Anatomy

23k

wheresryan22/anatomy

Build crafted, highly detailed, interactive isometric SVG figures that explain a technical idea as a real physical object (a test rig, a dial gauge, a cabinet of drawers, a plotter, a lock), with many small precise solid parts, four-tone shading, correct painter's order, a framed card with title, hint and live readout, and calm eased motion. Use this whenever someone wants an isometric illustration, an explanatory diagram or figure for docs, a blog post, a landing page or an article, a "Linear-style" or "premium" technical drawing, an interactive explainer, or an SVG that shows how a system, a

Writing & Content1.9k

Avoid AI Writing

5.3k

conorbronsdon/avoid-ai-writing

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.

Writing & ContentIn 2 lists472

Wwas

28k

phuryn/pm-skills

Create product backlog items in Why-What-Acceptance format — independent, valuable, testable items with strategic context. Use when writing structured backlog items, breaking features into work items, or using the WWA format.

Writing & ContentIn 3 lists2.9k

Cheat on Content

7.4k

XBuilderLAB/cheat-on-content

给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化（播放 / 阅读 / 收听 / 点击）的内容。**rubric 是循环的内容，不是循环本身**——当前内置一份观点视频 rubric（参考博主 25+ 视频拟合），其他形态可借这套起步并 bump 调权重。**强烈建议导入对标账号**作为初始信号源（/cheat-learn-from）。触发词："初始化"/"打分这篇"/"启动预测"/"已发布"/"复盘"/"升级 rubric"/"推荐选题"/"抓热点"/"状态"/"找对标"/"learn from"。**首次使用必须先跑 /cheat-init。**

Writing & Content975

Sprint Plan

28k

phuryn/pm-skills

Plan a sprint with capacity estimation, story selection, dependency mapping, and risk identification. Use when preparing for sprint planning, estimating team capacity, selecting stories, or balancing sprint scope against velocity.

Writing & ContentIn 3 lists2.9k

Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.