Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Elnora-AI/elnora-google-workspace/plugin install google-workspaceWrote 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/commands/elnora-ai/elnora-google-workspace/prep-meeting)<a href="https://agentmods.dev/commands/elnora-ai/elnora-google-workspace/prep-meeting"><img src="https://agentmods.dev/badge/commands/elnora-ai/elnora-google-workspace/prep-meeting/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/commands/elnora-ai/elnora-google-workspace/prep-meeting"><img src="https://agentmods.dev/badge/commands/elnora-ai/elnora-google-workspace/prep-meeting.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 | $0.00048 | $0.00606 |
| Opus 5 | $0.00024 | $0.00303 |
| Sonnet 5 | $0.00010 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
prep-meeting 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 9d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-meeting brief: $ARGUMENTS
Task
Generate a pre-meeting brief for a Google Calendar event and deliver it to you over Slack (or stdout). The brief is intentionally short (3-5 bullets) — it's what you read on your phone in the 5 minutes before walking into the meeting, not a full briefing document.
Run
python3 ${CLAUDE_PLUGIN_ROOT}/cli/prep_meeting.py {{ARGUMENTS}}
The CLI accepts either an event ID or a title substring (it'll search the next 3 days of calendar events).
What it includes
- Who — name, role, company (from contacts.csv)
- Last touch — last_contact_date + channel (so you know if you've spoken recently)
- Open next_action — anything overdue/owed (from contacts.csv)
- Customer file pointer — for paying customers, points to the CRM's company/account detail file
- Recent transcripts — last 1–2 transcripts with this person, with a one-line summary of what was discussed
What it deliberately doesn't include
- Full meeting agenda or talking points
- Exhaustive history (use the customer file or transcript directly for that)
- Any commercial/pricing/scope discussion (those are judgment calls you make live)
Examples
By event id (from gw calendar list):
/prep-meeting abc123def456ghi789jklm
By title substring (next 3 days):
/prep-meeting Acme
/prep-meeting <attendee-name>
Print only, don't DM Slack:
/prep-meeting Acme --no-slack
Notes
- The brief is DM'd to the Slack user in
$GW_SLACK_USER_IDvia the Slack CLI at$GW_SLACK_CLI_BIN. If either is unset, the brief is printed to stdout instead. - Requires the optional knowledge base for CRM/transcript lookups. If no knowledge base is configured, the command no-ops with a message. Transcript scanning uses the directories in
GW_TRANSCRIPT_DIRS(comma-separated, relative to the company dir). - If the attendees aren't in
contacts.csv, the brief falls back to listing their email addresses (so you know who to research). - Best run 15-30 minutes before the meeting. Could be wired into a scheduled job that scans upcoming meetings hourly and DMs briefs 30 min before, but right now it's manual.
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.
- 9d ago First seen · 60 lines · 48 tokens per session scan A 1da7ed65bae7
prep-meeting is a command published in the GitHub repository Elnora-AI/elnora-google-workspace (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 48 tokens to every session and 606 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
google-workspace-setup
One-time setup for the google-workspace-mcp plugin — check prerequisites, create/locate the OAuth client, define accounts, authorize each in the right browser, and wire it into the current project.
ask
Ask a single expert agent a question - like a Slack ping to a colleague.
triage-inbox
Sort application mail into the freehire tracker and drain the link queues.
audit-release
Diagnose release-readiness against the Starter Series quality bar — matched starter, version-vs-last-tag drift, CHANGELOG drift vs merged PRs, and publish-workflow kind. Read-only.
install-deprecated
First-time global setup - install plugins, configure environment, explain workflow.
yank
Copy the last Claude response to clipboard.