meeting-prep

meeting-prep is a skill for Claude Code, Codex from mpaarating/ai-workflow-kit. It costs 19 tokens per session (1,039 once invoked), scanned A, original, MIT.

A meeting-preparation workflow that gathers an upcoming calendar event, earlier notes, related documents, and open action items.

In plain words
What is it for?
Find a meeting by its title, topic, or attendee; collect its agenda and participants; review recent notes; and assemble preparation context.
Why use it?
It saves time spent searching across calendars and notes and gives you the relevant background before the meeting starts.

Skill for Claude CodeCodex

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 skills/mpaarating/ai-workflow-kit/meeting-prep
Any agent
npx skills add mpaarating/ai-workflow-kit --skill meeting-prep
Clone the repo
git clone --depth 1 https://github.com/mpaarating/ai-workflow-kit

Made for: Claude Code, Codex.

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 meeting-prep

README.md
[![agentmods](https://agentmods.dev/badge/skills/mpaarating/ai-workflow-kit/meeting-prep.svg)](https://agentmods.dev/skills/mpaarating/ai-workflow-kit/meeting-prep)
Your own site
<a href="https://agentmods.dev/skills/mpaarating/ai-workflow-kit/meeting-prep"><img src="https://agentmods.dev/badge/skills/mpaarating/ai-workflow-kit/meeting-prep.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,039 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 $0.00019 $0.01039
Opus 5 $0.00010 $0.00519
Sonnet 5 $0.00004 $0.00208
Haiku 4.5 $0.00002 $0.00104

Measured 3d ago against content hash 28f6dd2f8a38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meeting-prep 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 3d 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.

skills/meeting-prep/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meeting Prep

Trigger Phrases

  • "prep for [meeting]"
  • "prepare for [meeting]"
  • "meeting prep"
  • "get ready for [meeting]"

Inputs

The user provides a meeting name, topic, or attendee name. This can be:

  • An exact meeting title: "prep for Sprint Retrospective"
  • A person's name (implies their next 1:1): "prep for my meeting with Sarah"
  • A topic: "prep for the API migration discussion"

Workflow

Step 1: Find the Meeting

Search {{calendar}} for upcoming events matching the user's input.

  • Match by title, attendee name, or description keywords
  • If multiple matches, show a numbered list and ask which one
  • If no matches, ask the user to clarify the meeting name or date
  • Extract from the matched event:
    • Title
    • Date and time
    • Attendees (names and roles if available)
    • Description/agenda (if present in the calendar event)
    • Recurring? (note if this is a recurring meeting — previous notes are more likely to exist)

Step 2: Find Previous Meeting Notes

Search {{notes}} for notes from prior instances of this meeting.

  • Search by meeting title, attendee names, and topic keywords
  • Look for the most recent 2-3 instances
  • Extract:
    • Action items from the last meeting (especially any assigned to the user)
    • Open questions or decisions that were deferred
    • Topics that were tabled for follow-up
  • If no previous notes exist, note this and move on

Step 3: Find Related Tickets

Search {{tasks}} for tickets related to the meeting topic.

  • Use the meeting title, description keywords, and attendee names as search terms
  • Filter to tickets that are:
    • Assigned to the user or attendees
    • Recently updated (last 2 weeks)
    • In active states (not closed/done)
  • Extract ticket ID, title, status, and assignee for each match

Step 4: Find Related Documents

Search {{notes}} more broadly for documents related to the meeting topic.

  • Search by topic keywords, project names, or technical terms from the meeting description
  • Look for: design docs, RFCs, decision records, relevant wiki pages
  • Keep to the top 3-5 most relevant results

Read the full file on GitHub · 121 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. 3d ago First seen · 121 lines · 19 tokens per session scan A 28f6dd2f8a38

Subscribe to this mod's changes

meeting-prep is a skill published in the GitHub repository mpaarating/ai-workflow-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 1,039 once invoked, about $0.0001 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.