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 Lingtai-AI/lingtai --skill listengit clone --depth 1 https://github.com/Lingtai-AI/lingtaiWrote 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/lingtai-ai/lingtai/listen)<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/listen"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/listen/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/lingtai-ai/lingtai/listen"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/listen.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 | $0.00104 | $0.01567 |
| Opus 5 | $0.00052 | $0.00783 |
| Sonnet 5 | $0.00021 | $0.00313 |
| Haiku 4.5 | $0.00010 | $0.00157 |
Grade A, and why
listen 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 7d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
listen
Nested swiss-knife reference for local-only audio analysis. No API key, no network. Two actions: transcribe (speech → text) or appreciate (music → numerical critique).
Two Actions
| Action | Backend | When |
|---|---|---|
| transcribe | faster-whisper (local Whisper) |
Spoken word, voice notes, podcasts, lectures. Works on singing too but lyrics may be inaccurate. |
| appreciate | librosa (signal processing) |
Music — tempo, key, frequency bands, dynamics. Returns numerical measurements, not subjective descriptions. |
Both actions are wrappers around the bundled scripts. Run them with bash like any other command-line tool:
python3 <skill-path>/scripts/transcribe.py <audio-file>
python3 <skill-path>/scripts/appreciate.py <audio-file>
The scripts auto-install their dependencies via lingtai.venv_resolve.ensure_package on first run, so the first invocation may take ~30 s.
transcribe — speech to text
python3 <skill-path>/scripts/transcribe.py <audio-path> [--model base] [--device cpu]
| Flag | Default | Notes |
|---|---|---|
--model |
base |
Whisper model size: tiny, base, small, medium, large-v2, large-v3. Larger = more accurate, slower, more RAM. |
--device |
cpu |
Use cuda if you have a GPU. |
--compute-type |
int8 |
CTranslate2 compute type. int8 is the fastest CPU mode. Use float16 on GPU. |
Output: a JSON document on stdout with:
{
"text": "<full transcript>",
"language": "en",
"language_probability": 0.99,
"duration": 42.3,
"segments": [
{"start": 0.0, "end": 4.2, "text": "..."},
...
]
}
Best for: Clear spoken word in any of Whisper's supported languages.
Caveats: Singing lyrics often mistranscribed — Whisper is trained on speech, not singing. Background music degrades accuracy. For very noisy input, try --model medium or large-v3.
appreciate — music analysis
python3 <skill-path>/scripts/appreciate.py <audio-path>
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.
- 7d ago First seen · 124 lines · 104 tokens per session scan A 0fdf5c0f1472
listen is a skill published in the GitHub repository Lingtai-AI/lingtai (670 stars, last pushed yesterday), licensed Apache-2.0. It adds 104 tokens to every session and 1,567 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
transcribe
Transcribe audio/video files to text using mlx-whisper (Apple Silicon, runs 100% local, no cloud, PHI-safe). Accepts any audio/video format ffmpeg can handle. Outputs: plain text, SRT subtitles, or timestamped JSON. Use when: (1) meeting recordings, (2) voice notes, (3) video subtitles, (4) PHI-safe medical dictation…
transcribe-tool
Audio transcription tool. Converts audio files to text with Whisper and optional LLM post-processing. Use when: transcribing meetings, podcasts, or extracting text from recorded audio files.
voice-chatterbox-tts
Use when free local TTS with voice cloning using Chatterbox. Zero API costs, word-level timing, whisper integration. Clone any voice with 10-60s reference audio. Use when generating narration, voiceovers, or custom AI voices.
audio-transcriber-transcription
Speech-to-text on the audio-transcriber MCP server — run Whisper (faster-whisper, falling back to openai-whisper) over a local audio/video file or a microphone recording, and export txt/srt/vtt/json captions. Use when the agent must transcribe or translate spoken audio, generate subtitle/caption files, or pick a…
audio-transcriber
Speech-to-text transcription using Whisper API or local engine.
faster-whisper
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables 20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.