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 iurysza/android-use --skill audio-transcribegit clone --depth 1 https://github.com/iurysza/android-useWrote 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/iurysza/android-use/audio-transcribe)<a href="https://agentmods.dev/skills/iurysza/android-use/audio-transcribe"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/audio-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/iurysza/android-use/audio-transcribe"><img src="https://agentmods.dev/badge/skills/iurysza/android-use/audio-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 | $0.00043 | $0.00905 |
| Opus 5.5 | $0.00017 | $0.00362 |
| Sonnet 5.5 | $0.00009 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
audio-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 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio Transcription
The bundled CLI normalizes audio, uploads each chunk to Gemini 3.5 Transcribe, and writes one Markdown transcript. Default output uses Gemini's speaker diarization and word-level timestamps.
Setup
Resolve paths relative to this SKILL.md. Do not assume a global skill directory.
bun install --cwd <skill-directory>/scripts --no-save
export GEMINI_API_KEY='...'
GOOGLE_API_KEY and OPENCODE_GOOGLE_API_KEY are fallbacks. Set GEMINI_TRANSCRIBE_MODEL only to select a compatible replacement model. The default is gemini-3.5-transcribe.
Before transcription
- Confirm the input exists and uses a supported format.
- Use
ffprobeto inspect duration. - Agree on an output path when the user does not provide one.
- Warn before an unexpectedly long or costly transcription.
- Ask for language hints and domain terms when they are known and likely to improve recognition.
Do not upload media without the user's explicit transcription request.
Run
bun run <skill-directory>/scripts/transcribe.ts \
./interview.m4a \
--language en-US \
--vocabulary "SumUp" \
--output ./interview-transcript.md
Options:
--chunk-minutes N: chunk duration. The default is30.--language CODE: BCP-47 language hint. Repeat the option for each known language. Omit it for automatic language detection and code-switching.--vocabulary TERM: domain term, acronym, or proper name. Repeat the option for each term. Use it with--smart. Gemini accepts up to 1,000 terms. It normally performs best with a short, targeted list.--smart: return a cleaned transcript. This removes filler words, repetitions, and false starts, but Gemini does not provide speaker labels or timestamps in this mode.--output PATH: exact Markdown output path.--keep: retain normalized audio and chunk files beside the transcript.--help: show usage.
Default verbatim mode requests speaker diarization and word timestamps. Gemini limits those requests to 30 minutes of audio per request, so the CLI splits longer recordings. The live API rejects custom vocabulary with word timestamps, so the CLI fails clearly when --vocabulary is used without --smart. --smart supports chunks up to 60 minutes because it does not request either feature. If Gemini returns a rate-limit delay, the CLI waits for that delay and retries the interaction once.
What ships with it
3 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 · 76 lines · 43 tokens per session scan A 9647cad8cd6f
audio-transcribe is a skill published in the GitHub repository iurysza/android-use (21 stars, last pushed 16d ago), licensed MIT. It adds 43 tokens to every session and 905 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
review-artifact-comments
Only use when the user explicitly invokes this skill by name.
babysit
Use when a user asks to babysit, monitor, keep checking, keep an eye on, or report when a pull request, CI run, ticket, deployment, or other changing target reaches an outcome.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
papyrus-latex-comments
Set up and use a non-destructive COMMENT layer in a LaTeX document — margin/inline notes tagged by type next to the author's text, without rewriting it. Use when asked to comment on, review or annotate a .tex file. For accept/reject replacement text, use papyrus-latex-suggestions.