What is analyze-meeting?

A meeting-transcript analysis tool that extracts summaries, decisions, action items, and unanswered questions.

It reads transcripts from files, pasted text, or Neotoma records; creates meeting analyses and tasks; and can look up related Google Calendar information.

It turns a transcript into follow-up work so decisions and commitments are less likely to be missed.

analyze-meeting — Skill for Claude Code by markmhendrickson

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.

Any agent

npx skills add markmhendrickson/ateles --skill analyze-meeting

Clone the repo

git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/analyze-meeting/github.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/analyze-meeting)

Your own site

<a href="https://agentmods.dev/skills/markmhendrickson/ateles/analyze-meeting"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/analyze-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/markmhendrickson/ateles/analyze-meeting"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/analyze-meeting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 171 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,543 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00171	$0.07543
Opus 5	$0.00086	$0.03771
Sonnet 5	$0.00034	$0.01509
Haiku 4.5	$0.00017	$0.00754

Measured 8d ago against content hash 2e0cd13c0af5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

analyze-meeting scanned grade C with 1 finding 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 8d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

If classification is ambiguous, pick the most defensible and explain in the report. Do not refuse.

.claude/skills/analyze-meeting/SKILL.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Meeting

Produce a structured, actionable analysis of a meeting transcript and stage all follow-ups (Neotoma tasks, proposed public issues). Recap messages are drafted only on request (see Step 5). Complement to analyze-neotoma-feedback: that skill is Neotoma-customer-development-specific; this one handles any meeting type and focuses on follow-through rather than positioning analysis.

When both skills fire on the same transcript (typical for a Neotoma evaluator call), this skill produces the operational follow-up; analyze-neotoma-feedback produces the customer-development analysis. They do not duplicate each other — they are linked via shared transcription and contact entities.

When to use

Auto-invoked by record-meeting after a successful stop+transcribe.
Invoked manually with /analyze-meeting <source> for an existing transcript on disk or a Neotoma transcription entity id.
Skip silently when the transcript is empty, was clearly not a meeting (e.g. solo voice memo without action content), or when RECORD_MEETING_AUTO_ANALYZE_MEETING=0 is set in env.

Invocation

/analyze-meeting <source>
/analyze-meeting <source> --open-issues          # open real GH issues instead of staging drafts
/analyze-meeting <source> --recap                # ALSO draft recap messages per participant (off by default)
/analyze-meeting <source> --participants "Alice <alice@x>, Bob <bob@y>"

<source> is auto-detected:

Absolute file path (exists on disk) — read the file. Handles transcripts produced by transcribe_audio.py, including last_meeting_transcription.txt.
Neotoma entity reference — a transcription entity id, or a name / canonical identifier resolvable to a transcription via retrieve_entity_by_identifier.
Raw pasted text — anything that doesn't match the above.

Flags:

--open-issues — actually open public issues in relevant repos via the GitHub MCP. Default is off: issues are staged as proposed_github_issue entities in Neotoma and written to the local report only. Same effect as setting MEETING_ANALYSIS_OPEN_GH_ISSUES=1 in env.
--recap — draft recap messages per participant (email when address is known, otherwise generic message text). Default is off: no recap is drafted and no Gmail draft is staged. Same effect as setting MEETING_ANALYSIS_RECAP=1 in env. Without this flag, Step 5 and Step 8 are skipped entirely and no recap_message entities are created.
--participants — comma-separated Name <email> overrides when speaker labels in the transcript are unreliable (diarization missed names, etc.).

Read the full file on GitHub · 408 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.

8d ago First seen · 408 lines · 171 tokens per session scan C 2e0cd13c0af5

Subscribe to this mod's changes

analyze-meeting is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed yesterday), licensed MIT. It adds 171 tokens to every session and 7,543 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Autonomous Agents LLM Productivity aauth agent-swarm ai-agents claude

analyze-meeting

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade C, and why

Tells the agent never to refusehighAnti-refusal

How it starts

Analyze Meeting

When to use

Invocation

What this file has done since we first saw it

Other skills, from other repositories

life-automation-audit

discord

slack

bluebubbles

notion

himalaya