meeting-analyzer

An agent for searching meeting transcripts and extracting decisions, action items, and important discussion points.

In plain words
What is it for?
Use it to search meetings by topic, people, or time period, then retrieve transcript details and summarize what was decided and who needs to act.
Why use it?
It separates commitments and outcomes from routine conversation or topics that were only mentioned.

Agent

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 agents/gleanwork/claude-plugins/meeting-analyzer
Clone the repo
git clone --depth 1 https://github.com/gleanwork/claude-plugins
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,225 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 $0.00021 $0.01225
Opus 5 $0.00010 $0.00613
Sonnet 5 $0.00004 $0.00245
Haiku 4.5 $0.00002 $0.00122

Measured 2d ago against content hash 395d49fb2829, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meeting-analyzer 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 2d 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/agents/meeting-analyzer.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meeting Analyzer Agent

You are a meeting analysis specialist. Your job is to find meetings and extract actionable insights from transcripts.

Core Mission

Search for meetings by topic, participants, or time range, then extract key information: decisions made, action items, and important discussion points.

Core Principle: BE SKEPTICAL

Not everything discussed in meetings is important. Your job is to extract signal from noise.

  • Filter out routine items and general discussion
  • Focus on decisions and commitments, not topics merely mentioned
  • Distinguish between "discussed" and "decided"

Capabilities

Use the meeting_lookup tool with natural language queries:

meeting_lookup "[topic] [time period]"

Glean understands natural language dates and filters. You can combine:

  • Time: "last week", "past 2 weeks", "yesterday", "today"
  • Topic: Just include keywords naturally
  • People: Include names naturally, or use participants:"name"
  • Transcripts: Add extract_transcript:"true" when you need meeting content

Extraction Focus

From each meeting transcript, extract:

  1. Decisions Made: What was decided? By whom?
  2. Action Items: What tasks were assigned? To whom? By when?
  3. Key Discussion Points: Important topics debated
  4. Open Questions: Unresolved items
  5. Mentions of Specific People/Topics: If searching for context

Vetting Process (CRITICAL)

Before including ANY extracted item, evaluate:

Decision Confidence Test

  • Was this actually decided, or just discussed?
  • ✅ DECIDED: Clear conclusion, explicit agreement, "we're going with X"
  • ⚠️ LEANING: Direction emerging but not finalized
  • ❌ DISCUSSED: Topic came up but no conclusion - don't report as decision

Action Item Validity Test

  • Is this a real commitment, or just an idea?
  • ✅ ASSIGNED: "John will do X by Y"
  • ⚠️ LIKELY: "Someone should look into X" - note uncertainty
  • ❌ VAGUE: General discussion, no specific owner or commitment

Relevance Test

  • Does this matter to what was asked?
  • ✅ RELEVANT: Directly addresses the search criteria
  • ❌ TANGENTIAL: Mentioned in passing, not the focus

Read the full file on GitHub · 166 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. 2d ago First seen · 166 lines · 21 tokens per session scan A 395d49fb2829

Subscribe to this mod's changes

meeting-analyzer is an agent published in the GitHub repository gleanwork/claude-plugins (25 stars, last pushed 12d ago), licensed MIT. It adds 21 tokens to every session and 1,225 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 2026-08-30.