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/tubecreate/tubecli/browser_scriptsnpx skills add tubecreate/tubecli --skill browser_scriptsgit clone --depth 1 https://github.com/tubecreate/tubecliWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tubecreate/tubecli/browser_scripts)<a href="https://agentmods.dev/skills/tubecreate/tubecli/browser_scripts"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/browser_scripts.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00000 | $0.01043 |
| Opus 5 | $0.00000 | $0.00522 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00104 |
Grade A, and why
browser_scripts 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Script Studio
Visual browser automation script editor & manager for TubeCLI.
Features
- Create and manage browser automation scripts
- Visual step editor with drag-drop reordering
- Element picker with live browser preview
- Variable interpolation ({{variable_name}})
- Functions — reusable scripts callable from other scripts
- Execution history and real-time logging
- Import/Export scripts as JSON
Storage
Scripts are stored as individual JSON files in scripts/ directory. Each file = one script.
Step Types
- navigate: Go to a URL
- click: Click an element by CSS selector
- type: Enter text into an input field
- wait: Wait for element to appear
- wait_hidden: Wait for element to disappear
- sleep: Pause for N milliseconds
- evaluate: Run JavaScript code in page context
- extract: Get text/attribute from element, save to variable
- screenshot: Capture page screenshot
- download: Wait for and save downloads
- condition: If/else branching
- loop: Repeat steps N times
- keyboard: Press keyboard keys (Enter, Tab, etc.)
- scroll: Scroll page up/down
- hover: Hover over element
- mouse_move: Move mouse to coordinates
- ai_generate: Use AI to generate text, save to variable
- call_function: Call a reusable function (see below)
Functions
Functions are scripts marked with is_function: true. They define inputs and outputs, and can be called from any script via the call_function step.
Available Functions
gmail_login_with_2fa — Google/Gmail Login
Đăng nhập Google/Gmail với email, password và tự xử lý 2FA.
Inputs:
| Name | Type | Required | Description |
|---|---|---|---|
email |
string | ✅ | Gmail/Google email |
password |
string | ✅ | Account password |
totp_secret |
string | ❌ | TOTP 2FA secret (base32) |
Outputs:
| Name | Type | Description |
|---|---|---|
login_status |
string | "success" or "failed" |
What ships with it
27 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- __init__.py 95 B runs code
- .gitignore 76 B
- db/__init__.py 27 B runs code
- db/database.py 17 KB runs code
- db/script_store.py 9.0 KB runs code
- extension.py 8.7 KB runs code
- google_login_success.png 22 KB
- group_scripts.py 54 KB runs code
- locales/en.json 7.4 KB
- locales/vi.json 8.1 KB
- package-lock.json 764 B
- package.json 48 B
- parser/__init__.py 31 B runs code
- parser/ai_parser.py 16 KB runs code
- runner/preview_server.js 12 KB runs code
- runner/script_runner.js 130 KB runs code
- script_routes.py 72 KB runs code
- scripts/gmail_active_farming.json 1.3 KB
- scripts/google_drive_farming.json 1.1 KB
- scripts/google_maps_farming.json 2.1 KB
- scripts/google_policy_reading.json 1.4 KB
- scripts/google_trends_browsing.json 1.4 KB
- scripts/youtube_search_watch.json 2.3 KB
- static/app.js 103 KB runs code
- static/index.html 43 KB
- static/styles.css 32 KB
- tubecli-extension.json 720 B
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.
- 5d ago First seen · 118 lines · 0 tokens per session scan A 7f28a6d46522
browser_scripts is a skill published in the GitHub repository tubecreate/tubecli (167 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,043 tokens. 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
Browser Automation
Core browser automation features including profile management, fingerprint spoofing, and AI interaction.
ZhiYing System Guide
Complete guide for AI agents to understand, install, and operate ZhiYing.
multi_agents
Enables multi-agent collaboration through teams, task delegation, and coordinated workflows.
auth_manager
Manage OAuth credentials & tokens for Google, Facebook, TikTok.
cloud_api
Manages cloud AI provider API keys for Gemini, OpenAI, Claude, DeepSeek, Grok.
ollama_manager
Manages local Ollama AI models for agents to use without cloud API keys.