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 agentmods add skills/nweii/agent-stuff/transcribe-audionpx skills add nweii/agent-stuff --skill transcribe-audiogit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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/nweii/agent-stuff/transcribe-audio)<a href="https://agentmods.dev/skills/nweii/agent-stuff/transcribe-audio"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/transcribe-audio.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.00849 |
| Opus 5 | $0.00030 | $0.00425 |
| Sonnet 5 | $0.00012 | $0.00170 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
transcribe-audio 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 5d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transcribe audio
Produce a transcript from an audio or video file using the model configured on this machine.
Check for a config first
Settings live in ~/.config/transcribe-audio/config.json.
- Missing — the machine isn't set up. Read
references/setup.mdand run setup (staging area, then model choice) before transcribing. Don't pick a model unprompted: the right one depends on the user's hardware, languages, and whether they want speed or accuracy, and a wrong guess wastes a large download. - Present — go straight to transcribing.
When the user asks to change or upgrade their model, route to references/setup.md as well.
Transcribe
Run the bundled script on the file:
python3 <skill-dir>/scripts/transcribe.py /path/to/recording.mp4
The script extracts a 16kHz mono WAV (so audio and video files are handled the same way), runs the configured model, and writes the transcript to the staging area.
--outdir DIR— write the WAV and transcript somewhere other than the staging area.--format srt— timestamped captions instead of prose;txt(default),vtt, andjsonalso work.
Run it in the foreground and let its output stream. Throughput is high, but a multi-hour file still takes real time, and a silent run reads as stalled.
Offer to fix errors when accuracy matters
Auto-transcripts fail in predictable spots: proper nouns — names, products, jargon — get misheard, and audio over music or crosstalk garbles. Whether to fix this depends on use. A transcript the user skims once needs nothing; one they'll quote, publish, or keep as a record is worth a pass.
Flag, don't silently correct: you're inferring what was said, and a confident wrong fix buries the error where the user won't catch it. Read the whole transcript first, and ground proper nouns in whatever context exists — project notes, a glossary, the surrounding conversation — rather than substituting a similar-sounding name from your own knowledge. Then triage what you find:
What ships with it
2 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.
- 5d ago First seen · 57 lines · 59 tokens per session scan A e2d7dc47f26e
transcribe-audio is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 17d ago), licensed MIT. It adds 59 tokens to every session and 849 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…