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.
git clone --depth 1 https://github.com/rianvdm/product-ai-publicWrote 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/rianvdm/product-ai-public/meeting)<a href="https://agentmods.dev/commands/rianvdm/product-ai-public/meeting"><img src="https://agentmods.dev/badge/commands/rianvdm/product-ai-public/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/rianvdm/product-ai-public/meeting"><img src="https://agentmods.dev/badge/commands/rianvdm/product-ai-public/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 | $0.00014 | $0.04738 |
| Opus 5.5 | $0.00006 | $0.01895 |
| Sonnet 5.5 | $0.00003 | $0.00948 |
| Haiku 4.5 | $0.00001 | $0.00474 |
Grade A, and why
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 21d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Summary
Turn a meeting transcript into scannable notes that surface themes, decisions, open questions and action items, with every claim traceable to what was said or to a cited source.
Arguments
$INPUT— the transcript text, a Google Doc URL, or a file path. Any trailing text is context from the user, such as the topic or where related docs live.
Workflow
Work through these in order. The run is complete when every step is done, or skipped with the reason given in the report.
- Get the complete transcript (§1). Never draft from a truncated tool result: it silently drops the end of the meeting.
- Gather the sources that settle it (§2): the deck or document the meeting reviewed, the attendee list, and the related project brain.
- Resolve names, products and dates (§3).
- Draft topic-grouped notes (§4), then apply provenance markers in a separate pass (§5).
- Save to the right
meetings/folder using the template (§6). - Update stakeholder memory (§7).
- Offer to update the related project
CONTEXT.mdwith new decisions, status changes, open questions and next steps. Update it if the user confirms or asked for it up front. - Report back briefly: the file path; stakeholder changes and anyone not in memory; names or terms left unresolved; any post-meeting check that changes a decision; and the CONTEXT offer. Opening the file in Obsidian follows AGENTS.md.
1. Get the complete transcript
- Pasted text: use it. File path: read it.
- Google Doc URL: the document ID is the string between
/d/and/edit. Read01-context/agent-tooling.md→ cf-portal codemode first, then fetch withcodemode.google_workspace_mcp_docs_get({ documentId, format: "markdown" }). If the tool fails, ask the user to paste the transcript. - Gemini meeting docs have three tabs: Quick notes, Full notes and Transcript. A
?tab=in the URL only names one of them. Markdown export concatenates all three, so the transcript follows both notes tabs. To read one tab alone, fetchformat: "raw"withincludeTabsContent: true, pick the tab fromdoc.tabs[]bytabProperties.title, and jointextRun.contentfromdocumentTab.body.content. The Full notes tab carries the Invited list and a link to the calendar event. Those names are person chips, so readperson.personProperties.nametoo or the line comes back empty (verified 2026-09-22).
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.
- 21d ago Changed · +3 lines 15b77d9871c8
- 27d ago Changed · -95 lines · +2 tokens per session 12fe91704669
- 1mo ago First seen · 316 lines · 12 tokens per session scan A c0bb95a07557
meeting is a command published in the GitHub repository rianvdm/product-ai-public (18 stars, last pushed 21d ago), licensed MIT. It adds 14 tokens to every session and 4,738 once invoked, about $0.0001 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 2026-09-09.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.