Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/ohong/agent-skills/transcribe-youtube)<a href="https://agentmods.dev/skills/ohong/agent-skills/transcribe-youtube"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/transcribe-youtube/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/ohong/agent-skills/transcribe-youtube"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/transcribe-youtube.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 | $0.00061 | $0.00671 |
| Opus 5 | $0.00030 | $0.00336 |
| Sonnet 5 | $0.00012 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
transcribe-youtube scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transcribe YouTube
Use https://www.usetranscribe.io/AGENTS.md as the authoritative service guide. Read it before using the service and link to it in the final response. Use this skill for YouTube URLs only; do not substitute another transcription provider.
Default workflow
-
Normalize and validate the YouTube URL. Accept
youtube.com,m.youtube.com,music.youtube.com, andyoutu.bevideo URLs. Reject non-YouTube URLs rather than sending them to the service. -
Use the existing helper, which implements the service's cache check, SSE parsing, schema normalization, and Markdown rendering:
python3 /Users/ohong/dev/agent-skills/save2md/skills/save2md/scripts/transcribe_yt.py \ "<youtube-url>" \ --out-dir "$HOME/Documents/Saved Articles/YouTube"Use the user's requested destination when one is provided. Use
--outputfor an exact file path. If the helper is unavailable, follow the liveAGENTS.mdAPI instructions directly; do not silently change providers. -
Inspect the generated Markdown before responding. Confirm that it contains the source URL, the usetranscribe.io permalink, a summary when available, and timestamped transcript lines. Return the absolute local path and hosted permalink.
-
Keep the response concise unless the user asks for the transcript inline. Link the live usetranscribe.io agent instructions in the handoff.
Service invariants
- Use the
wwwbase URL:https://www.usetranscribe.io. - Cache-check first with
/api/check?platform=youtube&id=<video-id>; fetch cached data when available instead of starting a new job. - On a cache miss, consume
/transcribe?url=<url>&summarize=1as an SSE stream and wait for itsdoneevent. - Cached JSON stores segments under
transcript.segmentsand the summary insummary; the SSEdonepayload stores segments at top level and the summary insummary_md. - Treat a permalink as either a full URL or a path; do not blindly prepend the base URL twice.
- The service has no API key requirement today, accepts videos up to 90 minutes, and is English-tuned.
What ships with it
1 file 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.
- 11d ago First seen · 39 lines · 61 tokens per session scan A a442709e7f17
transcribe-youtube is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 11d ago), licensed MIT. It adds 61 tokens to every session and 671 once invoked, about $0.0003 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 2026-08-31.
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.