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 asfbay-bit/opchain-skills --skill ow-start-transcribegit clone --depth 1 https://github.com/asfbay-bit/opchain-skillsWrote 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/asfbay-bit/opchain-skills/ow-start-transcribe)<a href="https://agentmods.dev/skills/asfbay-bit/opchain-skills/ow-start-transcribe"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/ow-start-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/asfbay-bit/opchain-skills/ow-start-transcribe"><img src="https://agentmods.dev/badge/skills/asfbay-bit/opchain-skills/ow-start-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 | $0.00094 | $0.01001 |
| Opus 5.5 | $0.00038 | $0.00400 |
| Sonnet 5.5 | $0.00019 | $0.00200 |
| Haiku 4.5 | $0.00009 | $0.00100 |
Grade A, and why
ow-start-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 2d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ow-start-transcribe
Part of ow-tools, the code add-on for the ow- skills. It runs code on this machine: ffmpeg, whisper.cpp and pyannote, through the ow-tools command. Nothing is uploaded. The speaker model runs with network access off.
Steps
- Setup. If the argument is
--setup, or the user asks what is needed, runow-tools doctorand show its output as it is. Every fix is a command for the user to run in their own terminal. Never runbrew,uv sync, a download or a keychain command yourself. Stop here. - Find the recording. It must be in a folder named
audioinside the workstream, e.g.opchain-work/intake/<client>/audio/<file>.m4a. Naming the folder is enough when it holds one recording. If the recording is somewhere else, ask the user to move it there. Don't move it yourself. - Transcribe. Run
ow-tools transcribe <path> --json. Add--speakers Nwhen the head count is known (the intake'sintake.yamlmay list attendees). Add--out <folder>for a second recording in the same workstream, e.g.plans/<client>/workshops/W1/. If the workstream's handling level is set andopchain-work/profile.mdhas abanner_text, pass it verbatim with--banner "<text>". A 20-minute call takes a few minutes; say so before you start. - Handle the result by exit code.
0: go to step 5.3(something is missing): say what the JSONmissinglist names. Offer the paths that still work: save the meeting tool's own transcript, a.vttfile or pasted transcript text as<workstream>/transcript.md, or use the user's notes; then "use ow-start to extract /". Mention/ow-start-transcribe --setupfor next time.4(refused): show the message. If it lists.gitignorelines, ask whether to add them to that repository's.gitignore. Add them only on a yes, then run again. Never commit a recording or a transcript.5(a tool failed): show the one-line error and offer the same fallbacks as for3.
- Confirm who is who. Show the two sample lines per speaker from the JSON
samples. Ask the user to name each speaker's role:you,client,client (<their role>)orother (<who>). Never guess a speaker from a name, a voice or what they say. Record the answer withow-tools speakers <transcript.json> --set SPEAKER_00=<role> --set SPEAKER_01=<role>. If the user can't tell, leave that speaker unconfirmed. The roles show intranscript.md, so ow-start's extract step can confirm them in one question. - Hand off. For an intake call, print (for a workshop or demo recording, name the ow- skill and step that asked for it instead):
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.
- 2d ago First seen · 36 lines · 94 tokens per session scan A f9956022e024
ow-start-transcribe is a skill published in the GitHub repository asfbay-bit/opchain-skills (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 94 tokens to every session and 1,001 once invoked, about $0.0004 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 2026-10-17.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.