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 douyin_downloadergit 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/douyin_downloader)<a href="https://agentmods.dev/skills/tubecreate/tubecli/douyin_downloader"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/douyin_downloader/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/douyin_downloader"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/douyin_downloader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00508 |
| Opus 5 | $0.00000 | $0.00254 |
| Sonnet 5 | $0.00000 | $0.00102 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
douyin_downloader 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 13d 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.
What it actually says
SKILL.md — Video Downloader Extension
Description
The Downloader extension allows downloading videos from TikTok and Douyin (DouYin).
When to use
- User sends a TikTok or Douyin link along with a download request
- User requests "tải video", "download video", "lấy video" AND INCLUDES A URL
⛔ DO NOT USE when: the message contains no video URL, the message is just a greeting/casual chat.
How to trigger (AI OUTPUT JSON)
Download video from URL:
{"action": "download_video", "url": "https://www.douyin.com/video/XXXXXXX"}
Supported URL formats:
https://www.douyin.com/video/<VIDEO_ID>— Douyin direct videohttps://www.tiktok.com/@<user>/video/<ID>— TikTok videohttps://vm.tiktok.com/<SHORT_CODE>— TikTok short URLhttps://v.douyin.com/<SHORT_CODE>— Douyin short URLhttps://www.iesdouyin.com/share/video/<ID>— Douyin share link
API Endpoints
| Method | Path | Description |
|---|---|---|
| POST | /api/v1/douyin_downloader/parse |
Parse video info: {"url": "..."} |
| POST | /api/v1/douyin_downloader/download |
Download video: {"url": "..."} |
| GET | /api/v1/douyin_downloader/status/{task_id} |
Check progress |
| GET | /api/v1/douyin_downloader/history |
Download history |
| GET | /api/v1/douyin_downloader/file/{filename} |
Serve file |
Automated workflow (AI autonomous)
- AI receives the URL from the user
- AI outputs JSON
{"action": "download_video", "url": "..."} - The system calls
/parse→ gets the download URL - The system calls
/download→ downloads the file - The Telegram bot sends the file directly to the user (sendDocument)
IMPORTANT
- NEVER instruct the user to go to the Dashboard to download
- ALWAYS output the JSON action so the system downloads automatically
- After downloading, the file is sent directly to Telegram
What ships with it
24 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 172 B runs code
- api_client.py 25 KB runs code
- encrypt/__init__.py 412 B runs code
- encrypt/aBogus.py 15 KB runs code
- encrypt/device_id.py 1.8 KB runs code
- encrypt/msToken.py 14 KB runs code
- encrypt/ttWid.py 3.0 KB runs code
- encrypt/verifyFp.py 1.9 KB runs code
- encrypt/webID.py 1.4 KB runs code
- encrypt/xBogus.py 5.7 KB runs code
- encrypt/xGnarly.py 10 KB runs code
- extension.py 1.8 KB runs code
- file_downloader.py 5.7 KB runs code
- link_parser.py 11 KB runs code
- locales/en.json 2 B
- locales/es.json 2 B
- locales/ja.json 2 B
- locales/ko.json 2 B
- locales/ru.json 2 B
- locales/tr.json 2 B
- locales/vi.json 2 B
- locales/zh-TW.json 2 B
- locales/zh.json 2 B
- routes.py 13 KB runs code
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.
- 13d ago First seen · 47 lines · 0 tokens per session scan A ec0f8dd07869
douyin_downloader 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 508 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
auth_manager
Manage OAuth credentials & tokens for Google, Facebook, TikTok.
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.
ollama_manager
Manages local Ollama AI models for agents to use without cloud API keys.
Browser Automation
Core browser automation features including profile management, fingerprint spoofing, and AI interaction.
My Skill
Content here.