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/kcdjmaxx/homaruscc/transcribenpx skills add kcdjmaxx/HomarUScc --skill transcribegit clone --depth 1 https://github.com/kcdjmaxx/HomarUSccWrote 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/kcdjmaxx/homaruscc/transcribe)<a href="https://agentmods.dev/skills/kcdjmaxx/homaruscc/transcribe"><img src="https://agentmods.dev/badge/skills/kcdjmaxx/homaruscc/transcribe.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 | $0.00084 | $0.00694 |
| Opus 5 | $0.00042 | $0.00347 |
| Sonnet 5 | $0.00017 | $0.00139 |
| Haiku 4.5 | $0.00008 | $0.00069 |
Grade A, and why
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 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transcribe
Local audio/video transcription using Apple Silicon-optimized whisper models. No cloud APIs.
Usage
When the user invokes /transcribe, they will provide one of:
- A YouTube URL
- A local file path (audio or video)
- A reference to a Telegram voice message
Pipeline
1. Identify the source
- YouTube URL: Download audio with yt-dlp
- Local file: Use directly
- Telegram voice message: File is already downloaded to
~/.homaruscc/telegram-media/
2. Download (YouTube only)
yt-dlp -x --audio-format wav -o "/tmp/transcribe-%(id)s.%(ext)s" "<URL>"
If yt-dlp isn't found, tell the user to install it: brew install yt-dlp
3. Transcribe with mlx-whisper
python3 -c "
import mlx_whisper
result = mlx_whisper.transcribe('<audio_file>', path_or_hf_repo='mlx-community/whisper-large-v3-turbo', language='en')
print(result['text'])
"
Model selection:
- Default:
mlx-community/whisper-large-v3-turbo(best quality, still fast on Apple Silicon) - Fast/short clips:
mlx-community/whisper-base-mlx(use for voice messages under 30s) - If user requests speed over accuracy, use base model
Fallback chain: mlx-whisper -> faster-whisper -> whisper-cli (whisper-cpp)
If mlx-whisper isn't installed: pip3 install mlx-whisper
4. Save output
- YouTube transcripts: Save to
ClawdBot/HalShare/transcripts/<date>-<video-id>.mdwith frontmatter:# <Video Title> **Video:** <URL> **Video ID:** <id> **Source:** mlx-whisper (local) **Model:** <model used> **Date extracted:** <YYYY-MM-DD> --- <transcript text> - Local file transcripts: Save next to the source file as
<filename>.transcript.md, or to/tmp/if the source is in a read-only location - Telegram voice messages: Return the text inline (don't save unless asked)
5. Report
- Tell the user the transcript is done
- For long transcripts (>2000 chars), provide a brief summary and the file path
- For short transcripts, include the full text inline
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 · 82 lines · 84 tokens per session scan A 3acb772fc837
transcribe is a skill published in the GitHub repository kcdjmaxx/HomarUScc (1 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 694 once invoked, about $0.0004 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…