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 TheSmokeDev/taskchad-os --skill voice-transcribegit clone --depth 1 https://github.com/TheSmokeDev/taskchad-osWrote 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/thesmokedev/taskchad-os/voice-transcribe)<a href="https://agentmods.dev/skills/thesmokedev/taskchad-os/voice-transcribe"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/voice-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/thesmokedev/taskchad-os/voice-transcribe"><img src="https://agentmods.dev/badge/skills/thesmokedev/taskchad-os/voice-transcribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 27 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00053 | $0.00469 |
| Opus 5 | $0.00026 | $0.00234 |
| Sonnet 5 | $0.00011 | $0.00094 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
voice-transcribe scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://api.openai.com/v1/audio/transcriptions \ What it actually says
Voice Transcribe
Convert a voice note into text so the normal chat pipeline can handle it. This runs as a pre-processing step on inbound audio, before routing.
Pipeline
- Receive — the channel adapter saves the audio attachment to a temp path.
- Transcribe — run speech-to-text (preference order):
- OpenAI Whisper API if
OPENAI_API_KEYis set (fast, no local deps):curl -s https://api.openai.com/v1/audio/transcriptions \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -F model=whisper-1 -F [email protected] - Local
faster-whisperif no key is configured and CPU/GPU allows.
- OpenAI Whisper API if
- Inject — replace the message body with the transcript, tag it
[voice], and hand it to the router as if the user had typed it. - Clean up — delete the temp audio file after transcription.
Notes
- WhatsApp/Telegram voice notes are usually
.ogg(Opus). Whisper accepts it directly;faster-whispermay needffmpeginstalled. - Keep the original duration in metadata so the agent can say "got your 0:42 voice note" when useful.
- Transcription is read-only — no capability gate needed. The reply still goes
out through the normal gated
chat.sendpath. - Never persist raw audio beyond the transcription step unless the user opts in.
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.
- 8d ago First seen · 45 lines · 53 tokens per session scan A 6aa45e500134
voice-transcribe is a skill published in the GitHub repository TheSmokeDev/taskchad-os (24 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 469 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
graphify
Use when the user invokes /graphify or asks to build, update, or query a knowledge graph from a folder of files (code, docs, papers, notes, images). Triggers: 'map this codebase', 'graph my notes', 'what is connected across these files', 'community detection', 'GraphRAG', incremental graph update, Neo4j/SVG/GraphML…
insights
Use when the user types /weekly or /monthly, asks for a weekly or monthly journal review or retrospective, asks 'how was my week' or 'how was my month', or wants trends, anomalies, or patterns across recent journal entries. Also fires when regenerating an insight report for a past week or month. NOT for writing…
setup-brain
Set up or upgrade an AI-powered Obsidian vault. Interviews you, builds your vault structure (or works with what you already have), creates your CLAUDE.md memory file, installs tools, and gets you journaling — all in one conversation. Also has a repair/upgrade path for existing users.
second-brain-mapping
Use when the user wants to map or remap their second brain, refresh the vault's queryable metadata index, extract structured frontmatter from typed notes (books, meetings, people, journals, goals), fill wikilink gaps, or surface cross-type insights and patterns no single file shows. Triggers: /second-brain-mapping…
sunday-review
Use when the user asks for the weekly meta-review or Sunday wrap-up of their week and vault: says /sunday, /sunday-review, 'let's do the weekly review,' 'Sunday review,' 'review my week,' 'weekly retro,' 'week in review,' 'end-of-week review,' or wants journals, patterns, vault health, and stale decisions reviewed…
cierre-de-llamada
Use when a SALES or CLIENT call just ended and the follow-up needs to be produced from its transcript. Triggers: /cierre, "close out this call", "acabo de tener una llamada", "arma el seguimiento", "what's the follow-up on this call", "qué sigue con este cliente", or the user pastes a sales-call transcript. Produces…