vexa-meetings

vexa-meetings is a skill for Claude Code from Vexa-ai/vexa. It costs 78 tokens per session (595 once invoked), scanned A, original, Apache-2.0.

Meeting tools that send a bot to an online call, follow its live transcript, and save the meeting as notes. The notes can be stored in Obsidian, Notion, or plain Markdown files, with speakers and action items.

In plain words
What is it for?
Use it to join a Google Meet, Teams, or Zoom call, read its transcript, and file a dated meeting note. It can also include participants and tasks mentioned during the meeting.
Why use it?
It removes the manual work of monitoring a call and turning the discussion into notes. It also helps keep meeting records in the note system you already use.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the vexa plugin — 2 skills shipped together

Good fit Use it to join a Google Meet, Teams, or Zoom call, read its transcript, and file a dated meeting note. It can also include participants and tasks mentioned during the meeting.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vexa-ai/vexa/meetings
About the project

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.

Vexa-ai/vexa · 2,766 stars · on GitHub · vexa.ai

Install

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.

Any agent
npx skills add Vexa-ai/vexa --skill meetings
Clone the repo
git clone --depth 1 https://github.com/Vexa-ai/vexa

Made for: Claude Code.

Or install vexa, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for vexa-meetings

README.md
[![agentmods](https://agentmods.dev/badge/skills/vexa-ai/vexa/meetings/github.svg)](https://agentmods.dev/skills/vexa-ai/vexa/meetings)
Your own site
<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.

agentmods 80×15 button for vexa-meetings

Your own site · 80×15
<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>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 595 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash f979a136527e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

clients/claude-plugin/skills/meetings/SKILL.md · 39 lines

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

  1. parse_meeting_link(meeting_url) → platform + native_meeting_id.
  2. request_meeting_bot(meeting_url). A human in the call must admit the bot; expect a delay between requested and active.
  3. get_meeting_transcript(platform, native_meeting_id) while the meeting runs. Pass since_index to read only what is new. A meeting that is active with zero segments usually means the bot is not admitted yet or nobody has spoken.
  4. 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_transcript for the segments; get_meeting_participants is 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_meeting unless 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.

Read the full file on GitHub · 39 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 39 lines · 78 tokens per session scan A f979a136527e

Subscribe to this mod's changes

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.

Related

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.

leecyno1/boutique-skills · 58 tokens

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…

stenolabs/stenoai · 300 tokens

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.

LeoYeAI/openclaw-master-skills · 58 tokens

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…

stenolabs/stenoai · 163 tokens

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…

silverstein/minutes · 171 tokens

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.

silverstein/minutes · 70 tokens