Menu
Always use browser-harness for any web interaction: automation, scraping, testing, or site/app work.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Find the ghost tokens. Audit Claude Code or Codex setup, see where context goes, fix it. Use when context feels tight.
Set up hierarchical Intent Layer (AGENTS.md files) for codebases. Use when initializing a new project, adding context infrastructure to an existing repo, user asks to set up AGENTS.md, add intent layer, make agents understand the codebase, or scaffolding AI-friendly project documentation.
Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open Computer Use through its native CLI, stdio MCP server, or direct Computer Use tool calls.
any input (code, docs, papers, images, video) → knowledge graph → clustered communities → HTML + JSON + GRAPH_REPORT.md. Use when user asks any question about a codebase, project content, architecture, or file relationships — especially if graphify-out/ exists. Provides persistent graph with god nodes, community detection, and BFS/DFS query tools.
This skill helps users get started with existing (brownfield) projects by scanning the codebase, documenting structure and purpose, analyzing architecture and technical stack, identifying design flaws, suggesting improvements for testing and CI/CD pipelines, and generating AI agent constitution files (AGENTS.md) with project-specific context, coding principles, and UI/UX guidelines.
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
| name | browser-harness |
| description | Always use browser-harness for any web interaction: automation, scraping, testing, or site/app work. |
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.
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 $BH_AGENT_WORKSPACE/domain-skills/<site>/ directory before inventing an approach.
browser-harness <<'PY'
print(page_info())
PY
browser-harness. Use heredocs for multi-line commands.run.py calls ensure_daemon() before exec.new_tab(url), not goto_url(url).If the daemon cannot connect, run diagnostics:
browser-harness --doctor
If Chrome remote debugging is not enabled, the harness opens:
chrome://inspect/#remote-debugging
Ask the user to tick "Allow remote debugging for this browser instance" and click Allow if Chrome shows a permission popup. Then retry the same browser-harness command.
Use Browser Use cloud for headless servers, parallel sub-agents, or isolated work. Authenticate once:
browser-harness auth login
Or import a key safely:
browser-harness auth login --api-key-stdin
Pick a short made-up name; r7k2 below is just a placeholder:
browser-harness <<'PY'
start_remote_daemon("r7k2")
PY
BU_NAME=r7k2 browser-harness <<'PY'
new_tab("https://example.com")
print(page_info())
PY
When the task is done and a cloud browser is still running, ask directly: "Should I close this browser now?" If yes, run stop_remote_daemon(name). Remote daemons bill until they stop or time out.
Do not start a remote daemon and then keep using the default daemon. Use the same name for BU_NAME.
Cloud profile cookie sync reference: https://github.com/browser-use/browser-harness/blob/main/interaction-skills/profile-sync.md.
capture_screenshot() to understand visible state.click_at_xy(x, y) -> screenshot again.wait_for_load().ensure_real_tab().js(...) for DOM inspection or extraction when coordinates are the wrong tool.cdp("Domain.method", ...).If you get stuck on a browser mechanic, check https://github.com/browser-use/browser-harness/tree/main/interaction-skills.
BU_NAME, BU_CDP_URL, BU_CDP_WS, or start_remote_daemon(...).$BH_AGENT_WORKSPACE/agent_helpers.py.chrome://inspect/#remote-debugging must be enabled for local Chrome control.BU_CDP_URL is an HTTP DevTools endpoint; the daemon resolves it to WebSocket.stop_remote_daemon(name) or PATCH /browsers/{id} {"action":"stop"}.Only applies when BH_DOMAIN_SKILLS=1. Otherwise ignore domain skills.
When enabled, search $BH_AGENT_WORKSPACE/domain-skills/<host>/ before inventing an approach. goto_url(...) returns up to 10 skill filenames for the navigated host.