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 mrobinson2/AzureAgentForge --skill video-transcriptgit clone --depth 1 https://github.com/mrobinson2/AzureAgentForgeWrote 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/mrobinson2/azureagentforge/video-transcript)<a href="https://agentmods.dev/skills/mrobinson2/azureagentforge/video-transcript"><img src="https://agentmods.dev/badge/skills/mrobinson2/azureagentforge/video-transcript/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/mrobinson2/azureagentforge/video-transcript"><img src="https://agentmods.dev/badge/skills/mrobinson2/azureagentforge/video-transcript.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 | $0.00119 | $0.00771 |
| Opus 5.5 | $0.00048 | $0.00308 |
| Sonnet 5.5 | $0.00024 | $0.00154 |
| Haiku 4.5 | $0.00012 | $0.00077 |
Grade A, and why
video-transcript 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get a video's transcript with video-transcript
video-transcript is a CLI on $PATH that extracts a clean, plain-text
transcript from a video URL using yt-dlp.
It fetches subtitles/captions (human or auto-generated), strips the timing markup,
and de-duplicates the rolling caption lines into readable prose.
Usage
# Print the transcript — capture it so you can grep/quote/summarize it:
video-transcript "https://www.youtube.com/watch?v=VIDEO_ID" > /tmp/page.md
head -c 4000 /tmp/page.md
# Prefer a subtitle language (falls back to English):
video-transcript --lang es "https://www.youtube.com/watch?v=VIDEO_ID"
Only http(s) URLs are accepted. Output (and errors) follow the same convention
as web-read: transcript on stdout, errors on stderr.
How it gets the text
- Captions (default, no key) — human subs first, then auto-generated. Covers most YouTube videos.
- Whisper fallback (optional) — if a video has no captions and
GROQ_API_KEYis set, it downloads the audio and transcribes it with Groq Whisper (needsffmpeg). Without the key, a caption-less video returns exit4.
Behavior and exit codes
| Exit | Meaning |
|---|---|
0 |
Success — transcript on stdout. |
2 |
Usage / validation error (no URL, bad scheme, bad flag). |
3 |
Fetch or transcription failed (clear error on stderr). |
4 |
No captions and no Whisper fallback (GROQ_API_KEY unset). Try a different source. |
5 |
A required tool (yt-dlp, or ffmpeg for the fallback) is missing. |
Environment
| Variable | Purpose |
|---|---|
VIDEO_TRANSCRIPT_MAX_CHARS |
Cap on transcript length (default 100000; long videos are truncated with a marker). |
VIDEO_TRANSCRIPT_LANG |
Default subtitle language (default en). |
VIDEO_TRANSCRIPT_YT_CLIENT |
yt-dlp YouTube player_client (default android,web). YouTube gates captions behind a PO token for the web client from datacenter IPs; the android client bypasses it. Override if YouTube extraction breaks. |
GROQ_API_KEY |
Optional. Enables the Whisper fallback for caption-less videos. |
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 · 66 lines · 119 tokens per session scan A 978f683c639c
video-transcript is a skill published in the GitHub repository mrobinson2/AzureAgentForge (24 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 771 once invoked, about $0.0005 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
tomllm-format
.tomllm / .tomllmd = valid TOML + enriched # comment conventions for LLM context.
pptagent
Create and revise editable PowerPoint presentations from a brief using HTML slide sources, rendering, and visual review. Use when the requested deliverable is a PPTX deck. The host authors the slides; text-only hosts can use an external visual reviewer.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
penguin-plugin
Use for workbenches — the tabs and pages beside the chat, with server code behind them, that an Agent keeps in its own workbenches/ folder inside PenguinHarness — building one, changing it, showing it as the whole app, restoring an earlier version, and removing a tab or a whole workbench when the user wants the custom…
agent-initialization
Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt, before tool calls, or after a task). For an Agent with an in-app workbench, pair with penguin-plugin; for a standalone…
awm-rsi-toolkit
Run AWM (Agent Workflow Memory, Wang et al. 2024) on an agent - induce reusable workflows from its successful trajectories, online over a training stream or offline from supplied experiences, then freeze the workflow memory and measure it on a published Benchmark.