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 video_studiogit 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/video_studio)<a href="https://agentmods.dev/skills/tubecreate/tubecli/video_studio"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/video_studio/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/video_studio"><img src="https://agentmods.dev/badge/skills/tubecreate/tubecli/video_studio.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 | $0.00024 | $0.00962 |
| Opus 5.5 | $0.00010 | $0.00385 |
| Sonnet 5.5 | $0.00005 | $0.00192 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade A, and why
Video Studio 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎬 Video Studio
Adds three things the system doesn't have yet: removing burned-in subtitles, channel analysis, and a reup pipeline. The remaining stages (downloading video, extracting subtitles, translation, TTS) live in other extensions — see the rules below.
🛑 IMPORTANT RULE: when a tool is missing, GUIDE the user, don't say "can't be done"
Most video stages are handled by optional extensions. If the user requests something whose extension isn't installed:
- Do NOT give a generic answer like "I don't have that capability".
- Emit
{"action": "video_capabilities"}to get the exact list. - Hand the result verbatim to the user — it lists exactly which extension to install, describes each one, and reminds them to go to the Market (
/market) then restart the server.
Job → extension needed:
| Job | Extension needed |
|---|---|
| Download video | video_downloader |
| Extract subtitles / translate / burn subtitles | subtitle_extractor |
| Voiceover (TTS) | tts_vibevoice |
| Remove original subtitles · analyze channel · pipeline | video_studio (already installed) |
| Full reup pipeline | all 4 of the above |
📥 video_capabilities — see what can be done
{"action": "video_capabilities"}
Use BEFORE refusing any video request.
📥 analyze_channel — analyze a channel, suggest content
{"action": "analyze_channel", "url": "https://www.youtube.com/@tenkenh"}
Returns: topic, audience, tone, the title formula of hit videos, and 5-8 new video ideas with hooks. Use when the user asks "what is this channel about", "what video should I make next".
📥 remove_hardsub — remove burned-in subtitles
{"action": "remove_hardsub", "video_path": "C:/path/video.mp4", "mode": "delogo"}
mode: delogo (default — interpolates from the surrounding border; on a flat background the text vanishes without leaving a streak), blur, pixel, fill.
📥 reup_video — run the whole chain
{"action": "reup_video", "url": "https://v.douyin.com/xxxx"}
What ships with it
10 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.
- 1mo ago First seen · 91 lines · 24 tokens per session scan A 014f1229aa47
Video Studio is a skill published in the GitHub repository tubecreate/tubecli (174 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 962 once invoked, about $0.0001 per session on Opus 5.5. 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
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.
Browser Automation
Core browser automation features including profile management, fingerprint spoofing, and AI interaction.
ponytail-gain
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".