meetsync

meetsync is a command for Claude Code from vmarcondes-nilo/personal-os. It costs 0 tokens per session (907 once invoked), scanned A, original, MIT.

A meeting follow-up workflow that finds recent Google Calendar events, reads attached transcripts or notes in Google Docs, and turns them into structured notes and action items.

In plain words
What is it for?
Use it to process Google Meet notes or transcripts from other supported storage, then organize decisions and follow-up tasks. It requires Google Calendar and Google Docs connections through MCP.
Why use it?
It avoids manually searching calendar events and meeting documents after every meeting.

Command for Claude Code

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.

agentmods
npx agentmods add commands/vmarcondes-nilo/personal-os/meetsync
Clone the repo
git clone --depth 1 https://github.com/vmarcondes-nilo/personal-os

Made for: Claude Code.

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 meetsync

README.md
[![agentmods](https://agentmods.dev/badge/commands/vmarcondes-nilo/personal-os/meetsync.svg)](https://agentmods.dev/commands/vmarcondes-nilo/personal-os/meetsync)
Your own site
<a href="https://agentmods.dev/commands/vmarcondes-nilo/personal-os/meetsync"><img src="https://agentmods.dev/badge/commands/vmarcondes-nilo/personal-os/meetsync.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 907 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00907
Opus 5 $0.00000 $0.00453
Sonnet 5 $0.00000 $0.00181
Haiku 4.5 $0.00000 $0.00091

Measured 5d ago against content hash 3152596b7d3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meetsync 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.

.claude/commands/meetsync.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meeting Sync

Process meeting transcripts into structured notes and action items. Requires Google Calendar and Google Docs connected via MCP.


Setup Required

This command requires MCP integrations for:

  1. Google Calendar — to fetch events and find transcript attachments
  2. Google Docs — to read the transcript content

Options:

  • Rube — managed MCP gateway with Google Calendar + Docs toolkits
  • Google's official MCP servers — see Claude Code MCP docs

How transcripts work: If you use Google Meet with Gemini note-taking enabled, Google auto-attaches a summary doc to the calendar event after the meeting. This command finds those docs and processes them. The attachment title varies by language (e.g., "Gemini notes" in English, "Anotações do Gemini" in Portuguese).

If you use a different transcription tool (Otter, Fireflies, etc.), adapt Step 3 to find transcripts wherever your tool stores them.


1. Determine Date Range

Read meetings/.last-sync to find the last processed date.

  • If the file exists: fetch events from the day after last sync through yesterday
  • If the file does not exist: default to the last 48 hours

2. Fetch Calendar Events

Fetch calendar events for the date range:

  • Use your calendar MCP tool with the determined time range
  • Set timezone to your local timezone
  • Only query your primary calendar (not shared/subscribed calendars) to avoid noise

3. Identify Events with Transcripts

Step 3a — Filter to real meetings:

  • Skip all-day events
  • Skip cancelled events
  • Only keep events with a video conferencing link (Google Meet, Zoom, etc.)

Step 3b — Check for transcript attachments: For each remaining meeting, check for attached documents:

  • Google Meet + Gemini: Look for a Google Doc attachment (title varies by language — "Gemini notes", "Anotações do Gemini", etc.)
  • Other tools: Adapt this check based on where your transcription tool saves output

Read the full file on GitHub · 118 lines

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. 5d ago First seen · 118 lines · 0 tokens per session scan A 3152596b7d3b

Subscribe to this mod's changes

meetsync is a command published in the GitHub repository vmarcondes-nilo/personal-os (43 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 907 tokens. 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 2026-08-30.