Vexa is an open-source meeting transcription system whose bots join Google Meet, Microsoft Teams, and Zoom calls and stream speaker-labeled transcripts through an API. It is for teams that want meeting transcription and downstream knowledge processing either through hosted services or by running the stack themselves. The catalogue entries provide agents and instructions for working with Vexa.
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 Vexa-ai/vexa --skill meetingsgit clone --depth 1 https://github.com/Vexa-ai/vexaWrote 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/vexa-ai/vexa/meetings)<a href="https://agentmods.dev/skills/vexa-ai/vexa/meetings"><img src="https://agentmods.dev/badge/skills/vexa-ai/vexa/meetings/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/vexa-ai/vexa/meetings"><img src="https://agentmods.dev/badge/skills/vexa-ai/vexa/meetings.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 | $0.00078 | $0.00595 |
| Opus 5 | $0.00039 | $0.00298 |
| Sonnet 5 | $0.00016 | $0.00119 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
vexa-meetings 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vexa meetings
The vexa MCP server is connected. Start with whats_waiting — it says what the user's Vexa needs right now.
Send a bot to a call
parse_meeting_link(meeting_url)→ platform + native_meeting_id.request_meeting_bot(meeting_url). A human in the call must admit the bot; expect a delay betweenrequestedandactive.get_meeting_transcript(platform, native_meeting_id)while the meeting runs. Passsince_indexto read only what is new. A meeting that isactivewith zero segments usually means the bot is not admitted yet or nobody has spoken.stop_bot(platform, native_meeting_id)when done.
Every tool returns platform + native_meeting_id; feed one tool's output straight into the next.
Write a meeting into the user's notes
When asked to sync, log, or file a meeting:
list_meetings(filters: status, platform, metadata) to find it;get_meeting_transcriptfor the segments;get_meeting_participantsis not a tool — participants come from the segments' speaker names.- Write one note per meeting, dated, in the user's existing format if there is one (look at a recent note first). Include: title, date, participants (from speaker labels), a short summary, decisions, action items with owners, and the transcript or a link to it. Keep speaker labels as they are — do not guess names the transcript does not carry.
- Ask before writing outside the folder the user named.
Search across meetings
search_transcripts returns ranked snippets of what was said, not whole transcripts. Use it for "what did we decide about X", then open the meeting for context.
Make the data durable
annotate_meeting attaches a title and metadata (a CRM id, a ticket, tags). Anything you put there is findable later with list_meetings(metadata_filter=...). If you learn something durable about a meeting, write it back.
Do not
- Do not call
speak_in_meetingunless the user asked for that exact thing to be said. It is audible to everyone present and irreversible. - Do not read a meeting's
meetings_failed-style counters as reliability; a meeting ends in many states that are not errors.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 39 lines · 78 tokens per session scan A f979a136527e
vexa-meetings is a skill published in the GitHub repository Vexa-ai/vexa (2,766 stars, last pushed 2d ago), licensed Apache-2.0. It adds 78 tokens to every session and 595 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 2026-09-07.
Other skills, from other repositories
ai-meeting-notes
Messy notes → Clear action items. Instantly. Paste any meeting notes, transcript, or text. Get summaries, action items with owners and deadlines. Auto-saved, searchable, with integrated to-do tracking. No bot. No subscription. No setup.
steno
Make the agent aware of the user's Steno meeting notes and able to pull them in on request. Steno (https://github.com/stenolabs/stenoai) records, transcribes, and summarizes meetings entirely on-device, storing each as a Markdown summary plus a transcript. This skill locates that store cross-platform (macOS, Windows…
ai-meeting-notes
Messy notes → Clear action items. Instantly. Paste any meeting notes, transcript, or text. Get summaries, action items with owners and deadlines. Auto-saved, searchable, with integrated to-do tracking. No bot. No subscription. No setup.
granola-to-steno
Sync Granola meeting notes into Steno's file-based store. Reads recent meetings from the Granola MCP (titles, dates, participants, AI summaries, verbatim transcripts) and regenerates Steno's output/summary.md and transcripts/transcript.txt files in a target folder (e.g. an iCloud Drive directory). The operation is…
minutes-mirror
Self-coaching analysis of your own behavior across meetings — talk-time ratio, filler words, hedging language, monologue length, energy patterns, and (when meetings are tagged via /minutes-tag) what your behavior in winning meetings looks like vs losing ones. Use this whenever the user says "how did I do", "review my…
minutes-debrief
Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording.