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 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tubecreate/tubecli/browser_scripts"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/browser_scripts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 113 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 5.1 | $0.00000 | $0.01043 |
| Opus 5.5 | $0.00000 | $0.00417 |
| Sonnet 5.5 | $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 1mo 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 132 KB runs code
- script_routes.py 70 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.
- 1mo ago First seen · 118 lines · 0 tokens per session scan A 7f28a6d46522
browser_scripts is a skill published in the GitHub repository tubecreate/tubecli (174 stars, last pushed today), 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.
cloud_api
Manages cloud AI provider API keys for Gemini, OpenAI, Claude, DeepSeek, Grok.
multi_agents
Enables multi-agent collaboration through teams, task delegation, and coordinated workflows.
auth_manager
Manage OAuth credentials & tokens for Google, Facebook, TikTok.
ollama_manager
Manages local Ollama AI models for agents to use without cloud API keys.
omk-computeruse
Route OMK computer-use and Neo tasks by verified tool and model capabilities, without a second orchestrator. Use for native desktop apps, WSL-to-Windows experiments, browser sessions, site previews, screenshots, mouse/keyboard input, structured web extraction, or questions about Neo skills and MCP setup availability.