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 InternLM/WildClawBench --skill bilibili-youtube-watchergit clone --depth 1 https://github.com/InternLM/WildClawBenchWrote 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/internlm/wildclawbench/bilibili-youtube-watcher)<a href="https://agentmods.dev/skills/internlm/wildclawbench/bilibili-youtube-watcher"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/bilibili-youtube-watcher/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/internlm/wildclawbench/bilibili-youtube-watcher"><img src="https://agentmods.dev/badge/skills/internlm/wildclawbench/bilibili-youtube-watcher.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 | $0.00038 | $0.00678 |
| Opus 5 | $0.00019 | $0.00339 |
| Sonnet 5 | $0.00008 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
video-watcher 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 12d 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
1 near-identical copy found in the catalogue:
- video-watcher — 100% identical, 0 lines differ
What it actually says
Video Watcher
Fetch transcripts from YouTube and Bilibili videos to enable summarization, QA, and content extraction.
Supported Platforms
- ✅ YouTube (youtube.com, youtu.be)
- ✅ Bilibili (bilibili.com, b23.tv)
Usage
Get Transcript (Auto-detect Platform)
python3 {baseDir}/scripts/get_transcript.py "VIDEO_URL"
Specify Language
python3 {baseDir}/scripts/get_transcript.py "VIDEO_URL" --lang zh-CN
Examples
YouTube Video
python3 {baseDir}/scripts/get_transcript.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
Bilibili Video
python3 {baseDir}/scripts/get_transcript.py "https://www.bilibili.com/video/BV1xx411c7mD"
With Custom Language
# Get English subtitles for a Bilibili video
python3 {baseDir}/scripts/get_transcript.py "https://bilibili.com/video/..." --lang en
# Get Chinese subtitles for a YouTube video
python3 {baseDir}/scripts/get_transcript.py "https://youtube.com/watch?v=..." --lang zh-CN
Default Languages
| Platform | Default Language |
|---|---|
| YouTube | en (English) |
| Bilibili | zh-CN (Chinese) |
Common Language Codes
en- Englishzh-CN- Simplified Chinese (简体中文)zh-TW- Traditional Chinese (繁體中文)ja- Japaneseko- Koreanes- Spanishfr- Frenchde- German
Notes
- Requires
yt-dlpto be installed and available in PATH - Works with videos that have closed captions (CC) or auto-generated subtitles
- Automatically detects platform from URL
- If no subtitles available, the script will fail with an error message
- yt-dlp natively supports both YouTube and Bilibili
What ships with it
3 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.
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.
- 12d ago First seen · 85 lines · 38 tokens per session scan A 6bf8e0a81277
video-watcher is a skill published in the GitHub repository InternLM/WildClawBench (520 stars, last pushed 26d ago), licensed MIT. It adds 38 tokens to every session and 678 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
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
naga-config
A configuration-management skill for Naga, including its settings, connected tools, and imported skills.
naga_control
A control interface for changing Naga’s own running state and settings through a specific agent type.
live2d_controller
// 读取：system.characterbundle.loadcharacterskillsections -> system.config.buildtier1variables.characterbuiltinskillsprompt.
file-manager
A file and folder management helper for organizing files on a computer.
openclaw-control
A control interface for the OpenClaw AI assistant, covering messages, status checks, settings, and skill installation.