meeting-processor

meeting-processor is a skill for Claude Code, Codex from srinidhis05/agentura. It costs 3 tokens per session (942 once invoked), scanned A, original, Apache-2.0.

A meeting-notes processor that turns transcripts into structured action items, creates tasks in a project-management system, and posts a summary to team channels. MCP, or Model Context Protocol, is a way for an agent to use connected external tools.

In plain words
What is it for?
Use it to fetch a selected project's meeting transcript, identify action items, create or manage related tasks, and publish the results to messaging channels.
Why use it?
It removes the need to copy decisions and follow-up work from meeting notes into several systems by hand.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter; positional $N argument.

Good fit Use it to fetch a selected project's meeting transcript, identify action items, create or manage related tasks, and publish the results to messaging channels.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/srinidhis05/agentura/meeting-processor
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 srinidhis05/agentura --skill meeting-processor
Clone the repo
git clone --depth 1 https://github.com/srinidhis05/agentura

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-processor

README.md
[![agentmods](https://agentmods.dev/badge/skills/srinidhis05/agentura/meeting-processor/github.svg)](https://agentmods.dev/skills/srinidhis05/agentura/meeting-processor)
Your own site
<a href="https://agentmods.dev/skills/srinidhis05/agentura/meeting-processor"><img src="https://agentmods.dev/badge/skills/srinidhis05/agentura/meeting-processor/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.

agentmods 80×15 button for meeting-processor

Your own site · 80×15
<a href="https://agentmods.dev/skills/srinidhis05/agentura/meeting-processor"><img src="https://agentmods.dev/badge/skills/srinidhis05/agentura/meeting-processor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00003 $0.00942
Opus 5.5 $0.00001 $0.00377
Sonnet 5.5 $0.00001 $0.00188
Haiku 4.5 $0.00000 $0.00094

Measured 2mo ago against content hash 0011590c355d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meeting-processor 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 2mo 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/examples/meeting-processor/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meeting Processor

Task

Process meeting notes into structured action items, then create tasks in your project management tool and post a summary to your team channel. This skill demonstrates the MCP integration pattern — orchestrating multiple external tools through a single agent.

Input

You receive:

  • project_slug — project identifier (e.g., "acme-redesign")
  • meeting_source — where to find the notes: "latest" (most recent), or a specific meeting ID
  • output_channels — where to post results: ["tasks", "messaging"] (default: both)

MCP Tools Available

This skill uses external tools via MCP (Model Context Protocol):

Server Tools Purpose
calendar get_meetings, get_transcript Fetch meeting notes and transcripts
tasks create_task, list_tasks, update_task Create and manage action items
messaging post_message, post_thread Post summaries to team channels

Execution Protocol

Phase 1: Fetch Meeting Notes

  1. Call calendar.get_meetings filtered by project_slug and meeting_source
  2. For the target meeting, call calendar.get_transcript to get full notes
  3. If no meeting found, report error and stop

Context gate: "Found meeting '{title}' from {date} with {participant_count} participants."

Phase 2: Extract Action Items

Parse the transcript to identify:

  1. Decisions made — what was agreed upon
  2. Action items — who does what by when
  3. Open questions — unresolved topics needing follow-up
  4. Key updates — status changes or announcements

For each action item, extract:

  • assignee — who is responsible (from participant list)
  • title — concise task title
  • description — context from the discussion
  • due_date — if mentioned, otherwise null
  • priority — high/medium/low based on discussion urgency

Phase 3: Create Tasks

For each action item:

  1. Check if a similar task already exists via tasks.list_tasks
  2. If not, create via tasks.create_task
  3. Record the created task IDs

Read the full file on GitHub · 119 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 119 lines · 3 tokens per session scan A 0011590c355d

Subscribe to this mod's changes

meeting-processor is a skill published in the GitHub repository srinidhis05/agentura (9 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3 tokens to every session and 942 once invoked, about $0.0000 per session on Opus 5.5. 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.