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 surfmind-space/awesome-surfmind --skill meeting-follow-upgit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/meeting-follow-up)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/meeting-follow-up"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/meeting-follow-up/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/surfmind-space/awesome-surfmind/meeting-follow-up"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/meeting-follow-up.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 | $0.00062 | $0.00514 |
| Opus 5 | $0.00031 | $0.00257 |
| Sonnet 5 | $0.00012 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
meeting-follow-up 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 12d 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.
What it actually says
Meeting Follow-Up
Turn the user's meeting notes or transcript into decisions, action items, open questions, and a sendable recap. Preserve names, numbers, dates, and commitments exactly as stated. Never invent owners or deadlines.
- Extract decisions, action items, owners, deadlines, dependencies, and unresolved questions from the source.
- Keep explicit commitments verbatim. Mark any owner or date you inferred as
(inferred)rather than asserting it. - Group action items by owner or workstream when that makes the recap easier to scan.
- If owners or due dates are missing or ambiguous, flag them so the user can confirm before sending.
- Draft a sendable follow-up message that matches the tone of the source and the user's audience.
Return these sections, omitting any that do not apply: Decisions, Action items (one per line as owner — task — due date), Open questions, Suggested follow-up message. Respond in the same language as the user's notes.
Example
Notes:
standup 6/24 — Priya, Marcus, me agreed to ship the export feature behind a flag Marcus takes the API endpoint, due Friday need to decide pricing tier still — ask Dana someone should update the docs
Output:
Decisions
- Ship the export feature behind a feature flag.
Action items
- Marcus — build the export API endpoint — Fri Jun 26
- You (inferred) — update the docs — no due date set
Open questions
- Which pricing tier does export belong to? (ask Dana)
Suggested follow-up message
Hi team — quick recap of today's standup. We're shipping export behind a flag. Marcus owns the API endpoint, targeting Friday. I'll take the docs update. Still open: which pricing tier export lands in — Dana, can you weigh in?
Owner for the docs update isn't explicit in the notes — confirm before sending.
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.
- 12d ago First seen · 54 lines · 62 tokens per session scan A bce64b90a122
meeting-follow-up is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 514 once invoked, about $0.0003 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 skills, from other repositories
communications-productivity-integrations
Class-level workflow for messaging, email, calendars, notes, boards, workspaces, and collaboration integrations via CLIs/APIs: Discord, Slack, Gmail/IMAP, Google Workspace, CalDAV, Trello, Notion, Obsidian, Apple Notes/Reminders, iMessage/SMS, and Clawk. Use when asked to send/read/manage messages, email, calendar…
cron
Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/update/pause/resume/delete/run, and always pass --agent-id explicitly.
cron
A procedure for creating and managing tasks that run automatically at a future time or repeat on a schedule. It uses QwenPaw's scheduling commands and requires an agent identifier.
mailbox
A guide for performing email and mailbox tasks through the QwenPaw mailbox system. It covers supported personal email providers, credentials, configuration, and the required mailbox workflow.
channel_message
Use this skill to proactively send a one-way message to a user/session/channel, usually only when the user explicitly asks to send to a channel/session or when proactive notification is needed. First query sessions with qwenpaw chats list, then push with qwenpaw channels send.
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Otto to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.