capturing-meeting-actions

capturing-meeting-actions is a skill for Claude Code from AstravueOrg/astravue-mcp-server. It costs 68 tokens per session (514 once invoked), scanned A, original, Apache-2.0.

A workflow that turns meeting notes, transcripts, or unstructured thoughts into tasks in Astravue, a project and task management system. It extracts commitments, assigns owners, adds dates when stated or inferable, and keeps a link to the source discussion.

In plain words
What is it for?
Use it after meetings or standups to capture follow-up work, assign it to workspace members, place it in a project, and review the resulting task list.
Why use it?
It prevents action items from being buried in meeting text and makes responsibility and deadlines visible. Unclear owners are flagged instead of guessed, and tasks are shown for confirmation before creation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the astravue plugin — 8 skills, 2 MCP servers shipped together

Good fit Use it after meetings or standups to capture follow-up work, assign it to workspace members, place it in a project, and review the resulting task list.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/astravueorg/astravue-mcp-server/capturing-meeting-actions
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 AstravueOrg/astravue-mcp-server --skill capturing-meeting-actions
Clone the repo
git clone --depth 1 https://github.com/AstravueOrg/astravue-mcp-server

Made for: Claude Code.

Or install astravue, the plugin that ships this one along with the rest of its 8 skills, 2 MCP servers.

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 capturing-meeting-actions

README.md
[![agentmods](https://agentmods.dev/badge/skills/astravueorg/astravue-mcp-server/capturing-meeting-actions/github.svg)](https://agentmods.dev/skills/astravueorg/astravue-mcp-server/capturing-meeting-actions)
Your own site
<a href="https://agentmods.dev/skills/astravueorg/astravue-mcp-server/capturing-meeting-actions"><img src="https://agentmods.dev/badge/skills/astravueorg/astravue-mcp-server/capturing-meeting-actions/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 capturing-meeting-actions

Your own site · 80×15
<a href="https://agentmods.dev/skills/astravueorg/astravue-mcp-server/capturing-meeting-actions"><img src="https://agentmods.dev/badge/skills/astravueorg/astravue-mcp-server/capturing-meeting-actions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 514 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 $0.00068 $0.00514
Opus 5 $0.00034 $0.00257
Sonnet 5 $0.00014 $0.00103
Haiku 4.5 $0.00007 $0.00051

Measured 11d ago against content hash bbe2ff36e899, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

capturing-meeting-actions 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 11d 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/capturing-meeting-actions/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capturing Meeting Actions

Converts unstructured discussion into structured, traceable tasks. Every action item should end up with an owner, a due date, and a link back to where it came from — that traceability is what makes the output trustworthy.

Workflow

  1. Read the source and extract candidate actions

    Pull every commitment, decision-with-follow-up, and "someone should…" out of the notes. For each, capture:

    • A clear task title (imperative: "Send the revised quote to Acme")
    • The owner named or implied in the text
    • A due date if stated or inferable ("by Friday", "before launch")
    • The source line, so the task traces back to the discussion

    Ignore pure status updates and discussion that produced no commitment.

  2. Resolve owners to workspace members

    For each named owner, resolve to a real member with astravue_get_member_by_email (if an email is given) or astravue_get_workspace_members (to match by name). Flag any owner you can't resolve rather than guessing.

  3. Pick the target project

    Confirm which project the tasks belong to. Use astravue_list_projects if unclear.

  4. Present the action list and confirm

    Show a table: title | owner | due date | source. Mark rows missing an owner or due date so the user can fill them. Ask for approval before creating anything.

  5. Create after approval

    • astravue_bulk_create_tasks — create the confirmed action items in one call
    • astravue_add_task_comment — optionally attach the source line as a comment for context

    Report which tasks were created, and re-list any items that were skipped because they lacked an owner or due date.

Important

  • Every action item needs an owner and a due date — flag the ones that don't rather than creating orphan tasks.
  • Resolve owners against real members; never assign to an unverified name.
  • Don't invent due dates the notes don't support — leave them empty and flag instead.
  • Capture commitments, not status chatter.

Read the full file on GitHub · 47 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. 11d ago First seen · 47 lines · 68 tokens per session scan A bbe2ff36e899

Subscribe to this mod's changes

capturing-meeting-actions is a skill published in the GitHub repository AstravueOrg/astravue-mcp-server (12 stars, last pushed 17d ago), licensed Apache-2.0. It adds 68 tokens to every session and 514 once invoked, about $0.0003 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.