meeting-prep

meeting-prep is a skill for Claude Code, Codex from gleanwork/claude-plugins. It costs 74 tokens per session (1,252 once invoked), scanned A, original, MIT.

A meeting-preparation skill that gathers useful background from earlier meetings, related documents, and attendee information.

In plain words
What is it for?
Use it to prepare talking points, understand previous decisions, and identify relevant people or open items before a meeting.
Why use it?
It reduces the time spent searching for context and filters out information that is unlikely to help in the meeting.

Skill for Claude CodeCodex

Part of the glean plugin — 19 skills, 10 agents, 2 hooks, 1 MCP server shipped together

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/gleanwork/claude-plugins/meeting-prep
Any agent
npx skills add gleanwork/claude-plugins --skill meeting-prep
Clone the repo
git clone --depth 1 https://github.com/gleanwork/claude-plugins

Made for: Claude Code, Codex.

Or install glean, the plugin that ships this one along with the rest of its 19 skills, 10 agents, 2 hooks, 1 MCP server.

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/gleanwork/claude-plugins/meeting-prep.svg)](https://agentmods.dev/skills/gleanwork/claude-plugins/meeting-prep)
Your own site
<a href="https://agentmods.dev/skills/gleanwork/claude-plugins/meeting-prep"><img src="https://agentmods.dev/badge/skills/gleanwork/claude-plugins/meeting-prep.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,252 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 $0.00074 $0.01252
Opus 5 $0.00037 $0.00626
Sonnet 5 $0.00015 $0.00250
Haiku 4.5 $0.00007 $0.00125

Measured 3d ago against content hash fbaf4545398f, 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/glean/skills/meeting-prep/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meeting Prep

You are helping someone prepare for an upcoming meeting. Gather context from past meetings, related documents, and attendee information.

Input

Determine the meeting, topic, or person from the user's request. If it is not clear, ask: "Which meeting would you like to prep for? You can give me the meeting name, a topic, or the name of the person you're meeting with."


Core Principles

  • Actionable prep: Focus on what they need to know, not exhaustive history
  • Scannable output: Busy people need quick context
  • Be skeptical of relevance: Not everything from past meetings matters
  • Quality over completeness: 5 good talking points beats 20 random ones

Phase 1: Identify the Meeting

Goal: Find the specific meeting

Actions:

  1. Use meeting_lookup to find the meeting:
    meeting_lookup "[topic or person name] upcoming"
    
  2. If multiple matches, ask the user to clarify
  3. Extract meeting details: title, time, attendees

Phase 2: Review Past Instances

Goal: Understand history and open items

Actions:

  1. Use Glean chat for synthesized meeting history:

    chat "What happened in previous [meeting name] meetings over the past 2 months? What decisions were made and what action items are still open?"
    
  2. Compile:

    • What was decided recently?
    • What action items are still open?
    • What topics come up repeatedly?

Phase 3: Gather Context

Goal: Find relevant documents and attendee info

Actions:

  1. Search for related documents:

    search query="[meeting topic]" updated="past_month"
    
  2. For 1:1s or meetings with unfamiliar attendees, look up people:

    employee_search "[attendee name]"
    
  3. If key documents are found, use read_document to get details


Phase 4: Vet Content (CRITICAL)

Goal: Filter to what's actually useful for prep — BE SKEPTICAL

For each piece of context, evaluate:

Relevance to THIS Meeting Test

  • Will this actually come up in this meeting?
  • ✅ INCLUDE: Directly relates to likely agenda items
  • ⚠️ MAYBE: Tangentially related
  • ❌ OMIT: Historical but not relevant to upcoming discussion

Read the full file on GitHub · 200 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 · 200 lines · 74 tokens per session scan A fbaf4545398f

Subscribe to this mod's changes

meeting-prep is a skill published in the GitHub repository gleanwork/claude-plugins (25 stars, last pushed 13d ago), licensed MIT. It adds 74 tokens to every session and 1,252 once invoked, about $0.0004 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 2026-08-30.