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/zhiying --skill browsergit clone --depth 1 https://github.com/tubecreate/zhiyingWrote 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/zhiying/browser)<a href="https://agentmods.dev/skills/tubecreate/zhiying/browser"><img src="https://agentmods.dev/badge/skills/tubecreate/zhiying/browser/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/zhiying/browser"><img src="https://agentmods.dev/badge/skills/tubecreate/zhiying/browser.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00018 | $0.00222 |
| Opus 5 | $0.00009 | $0.00111 |
| Sonnet 5 | $0.00004 | $0.00044 |
| Haiku 4.5 | $0.00002 | $0.00022 |
Grade A, and why
Browser Automation 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 11d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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 154 B runs code
- 29.8.1_64.json 172 B
- actions/browse.js 1.8 KB runs code
- actions/captcha_helper.js 2.0 KB runs code
- actions/click.js 8.1 KB runs code
- actions/comment.js 4.1 KB runs code
- actions/extract_content.js 19 KB runs code
- actions/login.js 25 KB runs code
- actions/mouse_helper.js 2.6 KB runs code
- actions/navigate.js 2.1 KB runs code
- actions/read_gmail.js 4.6 KB runs code
- actions/save_image.js 4.9 KB runs code
- actions/search_extract.js 1.3 KB runs code
- actions/search.js 8.0 KB runs code
- actions/type.js 1.8 KB runs code
- actions/visual_scan.js 864 B runs code
- actions/watch.js 5.8 KB runs code
- add_api_endpoints.py 1.6 KB runs code
- add_global_settings_ui.py 2.2 KB runs code
- agent.json 8.9 KB
- ai_engine.js 22 KB runs code
- auth_status.json 17 KB
- browser_manager.js 20 KB runs code
- check_versions.backup.php 1.9 KB
- check_versions.php 6.6 KB
- cleanup_session_manager.py 957 B runs code
- commands.py 6.5 KB runs code
- debug_ai_simple.js 529 B runs code
- debug_ai.js 522 B runs code
- debug_plugin.js 722 B runs code
- dump_fingerprint_keys.js 1005 B runs code
- ev_green_tech_agent.json 9.5 KB
- extension.py 2.4 KB runs code
- financial_analyst.json 6.5 KB
- fix_js_syntax_v2.py 2.0 KB runs code
- fix_js_syntax.py 642 B runs code
- gpu_monitor.js 727 B runs code
- insert_methods.py 2.3 KB runs code
- insurance_agent.json 3.4 KB
- locales/en.json 418 B
- locales/vi.json 456 B
- locales/zh.json 442 B
- open_fix.js 9.5 KB runs code
- open.js 84 KB runs code
- package-lock.json 60 KB
- package.json 639 B
- process_manager.py 13 KB runs code
- profile_manager.py 6.0 KB runs code
- quantum_philosopher.json 3.7 KB
- README_VERSION_SERVER.txt 534 B
- routes.py 18 KB runs code
- scraped_data/profilemoi/history.json 370 B
- scraped_data/testphienban356636546/history.json 381 B
- scraped_data/testprofilemoi/history.json 374 B
- scraped_data/testsock/history.json 1.3 KB
- scraped_data/teststok2/history.json 1.2 KB
- screenshots/error_1774240395542.jpg 70 KB
- screenshots/error_1774240690237.jpg 73 KB
- screenshots/error_1774241202756.jpg 170 KB
- screenshots/error_1774256151574.jpg 97 KB
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.
- 11d ago First seen · 31 lines · 18 tokens per session scan A 4ab2841a0830
Browser Automation is a skill published in the GitHub repository tubecreate/zhiying (71 stars, last pushed 5mo ago), with no licence file. It adds 18 tokens to every session and 222 once invoked, about $0.0001 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
browser_scripts
Visual browser automation script editor & manager for TubeCLI.
Browser Automation
Manage anti-detect browser profiles, open/close browsers, automate the web.
keychain
The user keeps their real social-media logins here (Facebook, TikTok, X, Discord, Telegram, Google). The vault holds the credentials; a browser profile that has an account assigned to it can act as that account.
Video Editor (FFmpeg)
AI-powered Video Editor with trimming, merging, effects, overlays, and export.
Codex
Mission control: create tasks, assign to an agent/team, wait for human approval, worker runs in the background, accept results.
File Manager
Manage files and folders on the computer.