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 jej2k5/meetey --skill skillgit clone --depth 1 https://github.com/jej2k5/meeteyWrote 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/jej2k5/meetey/skill)<a href="https://agentmods.dev/skills/jej2k5/meetey/skill"><img src="https://agentmods.dev/badge/skills/jej2k5/meetey/skill/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/jej2k5/meetey/skill"><img src="https://agentmods.dev/badge/skills/jej2k5/meetey/skill.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 | $0.05456 |
| Opus 5.5 | $0.00016 | $0.02182 |
| Sonnet 5.5 | $0.00008 | $0.01091 |
| Haiku 4.5 | $0.00004 | $0.00546 |
Grade A, and why
skill 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 1mo 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meetey Skill
Meetey captures meeting audio locally using ScreenCaptureKit, transcribes it with whisper.cpp, and produces a structured summary — all without audio leaving your machine.
It can optionally capture screen keyframes as well: slides, screen shares, code, and diagrams. Text is recognized on-device, so the default path still sends only text to Claude.
Invocation
/meetey [subcommand]
Two groups of subcommands: start, stop, status drive a recording; list, show,
search, delete, doctor operate on the library of past ones. Running /meetey with
no subcommand shows the available commands.
Every library subcommand also has a plain-language equivalent — "what meetings do I have
this week?" is /meetey list. Both routes reach the same tools, so honour whichever the
user used and don't redirect them to the other.
/meetey (no subcommand)
Reply with exactly this, then wait for the user to choose:
Meetey — local meeting capture
/meetey start Start recording a meeting
/meetey stop Stop recording and transcribe
/meetey status Check if a recording is active
/meetey watch Ask to record meetings automatically (off by default)
/meetey writeup Write notes for meetings recorded while you were away
/meetey list Browse past meetings
/meetey show Open one meeting's notes
/meetey search Find a moment across every meeting
/meetey delete Remove a recording
/meetey doctor Check the install
/meetey start
- Call
list_appsto get running capturable apps. - If no apps are found, tell the user: "No supported meeting apps are running. Start your meeting in Chrome (Google Meet or Teams web), Zoom, or Microsoft Teams, then try again."
- If exactly one app is found, confirm with the user: "I found [App Name]. Start recording?" and proceed on confirmation.
- If multiple apps are found, show a numbered list and ask the user to choose.
- Ask about screen capture, unless the user already said (
/meetey start --videomeans yes,/meetey start --audio-onlymeans no). Ask it as a plain question defaulting to no:
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.
- 1mo ago First seen · 370 lines · 40 tokens per session scan A e0f267efbd65
skill is a skill published in the GitHub repository jej2k5/meetey (1 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 5,456 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 2026-08-31.
Other skills, from other repositories
starcat-ui-prototype
A design skill for creating macOS interface prototypes and visual designs for Starcat, a GitHub star-management and AI knowledge-organising app. It follows Apple’s Liquid Glass design language for macOS 26.
starcat-update-changelog
Update Starcat changelog documents in supports/starcat-pro/ by reading ALL git commits from the main Starcat project and generating categorized release notes in both English and Chinese. Use this skill whenever the user wants to update changelog, release notes, update records, or sync the changelog with recent…
starcat-release
A project-specific procedure for releasing the Starcat macOS app through its App Store and direct-download channels.
starcat-localization-sync
A process for managing Starcat’s app translations from draft text through review, import, and release across 18 languages. It keeps the app’s translation catalogue and the public translation repository aligned.
starcat-cli-release
A release process for Starcat’s command-line program and its Homebrew package. Homebrew is a tool for installing software on macOS and Linux from package definitions.
hex-personal-commands
Configure HEX personal voice commands, voice-dictation control phrases, and deterministic transcript transformations. Use when the user wants to add or change commands or transformations for the HEX macOS voice app.