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 Knuckles-Team/audio-transcriber --skill audio-transcriber-developmentgit clone --depth 1 https://github.com/Knuckles-Team/audio-transcriberWrote 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/knuckles-team/audio-transcriber/audio-transcriber-development)<a href="https://agentmods.dev/skills/knuckles-team/audio-transcriber/audio-transcriber-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/audio-transcriber/audio-transcriber-development/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/knuckles-team/audio-transcriber/audio-transcriber-development"><img src="https://agentmods.dev/badge/skills/knuckles-team/audio-transcriber/audio-transcriber-development.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 | $0.00040 | $0.01121 |
| Opus 5.5 | $0.00016 | $0.00448 |
| Sonnet 5.5 | $0.00008 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
audio-transcriber-development 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 today.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio Transcriber Development
This is the repository development skill for audio-transcriber. The owning
central delivery row is PIPE-CONNSPEC-R107.4; use this skill with the
repository AGENTS.md, the connector-content specifications, and focused tests.
Repository and runtime map
audio_transcriber/mcp_server.pyregisters transcription, media-sidecar, health, and KG-ingestion tools plus the packaged prompts. Preserve the public tool names, progress reporting, and Connector registration boundary.audio_transcriber/audio_transcriber.pyowns theTranscriberBackendinterface, faster-whisper/openai-whisper selection, file and microphone paths, bounded exports, and best-effort KG handoff. Keep microphone dependencies optional so file transcription remains importable without PortAudio.audio_transcriber/connector_sources.pyis the live transcript source and schema declaration. Change source IDs, record mappings, and resource names there rather than duplicating them in tool code.audio_transcriber/kg_ingest.pyandkg_media.pymap transcript documents, segments, and audio assets through the SDK/epistemic-graph ingestion boundary. Preserve stable IDs and no-op behavior when no engine is available.audio_transcriber/skills/**,prompts/**,ontology/**, andconnectors/**are package data. A skill change needs a package-content check before release.
Runtime and security contract
WHISPER_MODEL selects the default model and TRANSCRIBE_DIRECTORY selects
connector-owned scratch storage, with XDG_DATA_HOME supplying the safe default
root. Keep paths explicit and bounded; do not persist audio, transcripts, model
credentials, or provider data in source, skills, fixtures, or logs.
Preserve the optional pyaudio import boundary, the supported faster-whisper
and openai-whisper backends, MCP_TOOL_MODE surface selection, SDK transport
configuration, and the SDK credential/TLS settings inherited by the connector.
Model downloads and microphone access remain operator-controlled; never add a
network or hardware bypass.
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.
- today First seen · 104 lines · 40 tokens per session scan A 6c1c3d50915f
audio-transcriber-development is a skill published in the GitHub repository Knuckles-Team/audio-transcriber (3 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,121 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 2026-10-27.
Other skills, from other repositories
archivebox-api-development
Develop and maintain the ArchiveBox connector while preserving its governed API actions, web-source contract, credential boundary, package resources, and public-first release evidence.
transcribe-tool
Audio transcription tool. Converts audio files to text using Whisper, with optional LLM post-processing as needed. Use when: Use when: transcribing meeting recordings, podcast transcripts, or when text extraction from audio files is required.
jellyfin-kg-ingestion
Natively ingest a Jellyfin library into the epistemic-graph knowledge graph via the jellyfin-mcp MCP server — push library items as typed :MediaAsset/:Book nodes with :hasGenre/:performedBy/:authoredBy links and item overviews as searchable :Document nodes (jellyfiningestlibrary), and item posters as content-addressed…
searxng-kg-ingestion
Persist SearXNG search results into the epistemic-graph knowledge graph via the searxng-mcp MCP server. Use when the agent must turn a web search into durable, semantically-searchable KG memory — each result becomes a :Document (plus :SearchQuery and :SearchEngine typed nodes with :resultOf / :fromEngine links) so…
archivebox-kg-ingestion
Natively ingest an ArchiveBox archive into the epistemic-graph knowledge graph via the archivebox-api MCP server — push snapshots as typed :Snapshot nodes (with :Tag + :hasTag links and per-snapshot :Document page-text) and archive results as :ArchiveResult nodes, best-effort, with the Wire-First ingest tools. Use…
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…