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 nhatvu148/video-transcriber-mcp-rs --skill transcribegit clone --depth 1 https://github.com/nhatvu148/video-transcriber-mcp-rsWrote 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/nhatvu148/video-transcriber-mcp-rs/transcribe)<a href="https://agentmods.dev/skills/nhatvu148/video-transcriber-mcp-rs/transcribe"><img src="https://agentmods.dev/badge/skills/nhatvu148/video-transcriber-mcp-rs/transcribe/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/nhatvu148/video-transcriber-mcp-rs/transcribe"><img src="https://agentmods.dev/badge/skills/nhatvu148/video-transcriber-mcp-rs/transcribe.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 | $0.00079 | $0.01150 |
| Opus 5 | $0.00039 | $0.00575 |
| Sonnet 5 | $0.00016 | $0.00230 |
| Haiku 4.5 | $0.00008 | $0.00115 |
Grade A, and why
transcribe 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transcribe the given video and answer the user's question about it — or summarize it if no question was asked.
Transcription is local and offline: whisper.cpp runs on this machine, and nothing but the video download leaves it.
Pick the right tool
The video-transcriber MCP server is auto-registered by this plugin. Route by what the user actually wants:
| Situation | Tool |
|---|---|
| A URL or file path, needs transcribing | transcribe_video |
| "What did that video say about X" across past videos | search_transcripts |
| "The one I just did" / no URL given | get_latest_transcript |
| "What have I transcribed?" | list_transcripts |
| Something failed and the cause is unclear | check_dependencies |
| "Does it support ?" | list_supported_sites |
Do not re-transcribe. Before calling transcribe_video on a URL, check list_transcripts — transcription is minutes of compute, and the transcript may already be on disk. Transcripts are saved to ~/Downloads/video-transcripts/ by default.
Transcribing
transcribe_video takes url (required), plus model, language, and output_dir.
Model choice matters more than anything else here:
| Model | Use when |
|---|---|
tiny / base |
Default. Clear speech, English, you want an answer now. base is the default. |
small / medium |
Accented speech, domain jargon, multiple speakers, or the base pass came back garbled. |
large |
Accuracy actually matters — quotes, names, numbers you'll act on. Slowest by a wide margin. |
Set language to an ISO 639-1 code (en, vi, es, ja) when you know it. auto is the default and it does misdetect on short or music-heavy clips — an explicit code is both faster and more accurate.
The response carries the transcript inline, truncated for long videos, along with the paths to the saved .txt, .json, and .md. When the transcript is truncated and the question needs the whole thing, Read the .txt path rather than transcribing again.
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 · 73 lines · 79 tokens per session scan A 73236edbd39d
transcribe is a skill published in the GitHub repository nhatvu148/video-transcriber-mcp-rs (17 stars, last pushed 8d ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,150 once invoked, about $0.0004 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.