Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cacity/videohub/browser-usenpx skills add cacity/VideoHub --skill browser-usegit clone --depth 1 https://github.com/cacity/VideoHubWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00047 | $0.01956 |
| Opus 5 | $0.00023 | $0.00978 |
| Sonnet 5 | $0.00009 | $0.00391 |
| Haiku 4.5 | $0.00005 | $0.00196 |
Grade A, and why
browser-use scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- browser-use — 100% identical, 1 lines differ
- browser-use — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation with browser-use CLI
The browser-use command provides fast, persistent browser automation. A background daemon keeps the browser open across commands, giving ~50ms latency per call.
Prerequisites
browser-use doctor # Verify installation
For setup details, see https://github.com/browser-use/browser-use/blob/main/browser_use/skill_cli/README.md
Core Workflow
- Navigate:
browser-use open <url>— starts browser if needed - Inspect:
browser-use state— returns clickable elements with indices - Interact: use indices from state (
browser-use click 5,browser-use input 3 "text") - Verify:
browser-use stateorbrowser-use screenshotto confirm - Repeat: browser stays open between commands
- Cleanup:
browser-use closewhen done
Browser Modes
browser-use open <url> # Default: headless Chromium
browser-use --headed open <url> # Visible window
browser-use --profile "Default" open <url> # Real Chrome with Default profile (existing logins/cookies)
browser-use --profile "Profile 1" open <url> # Real Chrome with named profile
browser-use --connect open <url> # Auto-discover running Chrome via CDP
browser-use --cdp-url ws://localhost:9222/... open <url> # Connect via CDP URL
--connect, --cdp-url, and --profile are mutually exclusive.
Commands
# Navigation
browser-use open <url> # Navigate to URL
browser-use back # Go back in history
browser-use scroll down # Scroll down (--amount N for pixels)
browser-use scroll up # Scroll up
browser-use switch <tab> # Switch to tab by index
browser-use close-tab [tab] # Close tab (current if no index)
# Page State — always run state first to get element indices
browser-use state # URL, title, clickable elements with indices
browser-use screenshot [path.png] # Screenshot (base64 if no path, --full for full page)
# Interactions — use indices from state
browser-use click <index> # Click element by index
browser-use click <x> <y> # Click at pixel coordinates
browser-use type "text" # Type into focused element
browser-use input <index> "text" # Click element, then type
browser-use keys "Enter" # Send keyboard keys (also "Control+a", etc.)
browser-use select <index> "option" # Select dropdown option
browser-use upload <index> <path> # Upload file to file input
browser-use hover <index> # Hover over element
browser-use dblclick <index> # Double-click element
browser-use rightclick <index> # Right-click element
# Data Extraction
browser-use eval "js code" # Execute JavaScript, return result
browser-use get title # Page title
browser-use get html [--selector "h1"] # Page HTML (or scoped to selector)
browser-use get text <index> # Element text content
browser-use get value <index> # Input/textarea value
browser-use get attributes <index> # Element attributes
browser-use get bbox <index> # Bounding box (x, y, width, height)
# Wait
browser-use wait selector "css" # Wait for element (--state visible|hidden|attached|detached, --timeout ms)
browser-use wait text "text" # Wait for text to appear
# Cookies
browser-use cookies get [--url <url>] # Get cookies (optionally filtered)
browser-use cookies set <name> <value> # Set cookie (--domain, --secure, --http-only, --same-site, --expires)
browser-use cookies clear [--url <url>] # Clear cookies
browser-use cookies export <file> # Export to JSON
browser-use cookies import <file> # Import from JSON
# Python — persistent session with browser access
browser-use python "code" # Execute Python (variables persist across calls)
browser-use python --file script.py # Run file
browser-use python --vars # Show defined variables
browser-use python --reset # Clear namespace
# Session
browser-use close # Close browser and stop daemon
browser-use sessions # List active sessions
browser-use close --all # Close all sessions
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 203 lines · 47 tokens per session scan A 67ead9e22037
browser-use is a skill published in the GitHub repository cacity/VideoHub (130 stars, last pushed 6d ago), licensed MIT. It adds 47 tokens to every session and 1,956 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
qiaomu-cut
把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video; build English-learning movie mixes, person profiles, explainers, product launch videos, cinematic shorts, social clips, course/PPT videos, AI…
stage-compose
Authoring knowledge for Orkas/OVS HTML video compositions -- write an index.html, drive animation from a paused timeline, declare canvas + duration, then run the VideoStudio draft gate to render an mp4. Trigger for explainer / animation / motion-graphics / caption / lower-third / title-card work, or to build a compose…
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.
stage-plan
The "ingest + plan" half of end-to-end video orchestration — ingest the user's material from evidence, then decompose intent into ONE cross-modal EDL (plan.json: edit/generate/compose/provided segments + narration/music/caption tracks + a delivery promise), validate it with ovs plan validate. Trigger when the…
orchestration
The master program for producing or editing a video end to end — read this at the START of any video task (after video-router), then follow the gates and the per-line steps. Trigger for "make / edit / cut / caption / dub / animate a video"; it sequences the compose / generate / edit lines and the approval gates. Do…
stage-assemble
Deterministically assemble an approved cross-modal EDL (plan.json) into a finished video — produce each segment (edit/compose/generate/provided, delegated to its line), then assemble in ffmpeg tiers: concat primaries → overlay composed layers → mix narration once (coverage check) → burn captions → verify loudness…