note1-action-items

note1-action-items is a skill for Claude Code from note1-ai/note1-mcp. It costs 89 tokens per session (1,122 once invoked), scanned A, a copy of og-image, MIT.

A task manager for action items extracted from note1.ai meeting records. It can list, create, update, complete, or dismiss tasks and show linked tickets in services such as GitHub, Linear, and Jira.

In plain words
What is it for?
Use it to review personal or team to-dos, filter them by meeting or date, assign or change them, complete or dismiss them, and inspect linked tickets.
Why use it?
It keeps meeting follow-ups from being lost in transcripts and shows whether a related ticket is still open or closed. It also separates possible evidence that a task is done from confirmed completion.

Skill for Claude Code

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

Part of the note1 plugin — 5 skills, 1 MCP server shipped together

Good fit Use it to review personal or team to-dos, filter them by meeting or date, assign or change them, complete or dismiss them, and inspect linked tickets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/note1-ai/note1-mcp/note1-action-items
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 note1-ai/note1-mcp --skill note1-action-items
Clone the repo
git clone --depth 1 https://github.com/note1-ai/note1-mcp

Made for: Claude Code.

Or install note1, the plugin that ships this one along with the rest of its 5 skills, 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 note1-action-items

README.md
[![agentmods](https://agentmods.dev/badge/skills/note1-ai/note1-mcp/note1-action-items/github.svg)](https://agentmods.dev/skills/note1-ai/note1-mcp/note1-action-items)
Your own site
<a href="https://agentmods.dev/skills/note1-ai/note1-mcp/note1-action-items"><img src="https://agentmods.dev/badge/skills/note1-ai/note1-mcp/note1-action-items/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 note1-action-items

Your own site · 80×15
<a href="https://agentmods.dev/skills/note1-ai/note1-mcp/note1-action-items"><img src="https://agentmods.dev/badge/skills/note1-ai/note1-mcp/note1-action-items.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,122 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 86% copy Near-identical to another mod 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 $0.00089 $0.01122
Opus 5.5 $0.00036 $0.00449
Sonnet 5.5 $0.00018 $0.00224
Haiku 4.5 $0.00009 $0.00112

Measured 10d ago against content hash 30a87d794846, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

note1-action-items 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 10d 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

This is a copy

86% identical to og-image — 122 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

claude-plugin/skills/note1-action-items/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

note1 action items

Action items are the tasks note1 pulls out of meetings. When a task tool such as GitHub, Linear or Jira is connected, an item can be linked to a ticket there. Every tool acts with the signed-in user's own permissions, and takes an optional teamId (omit it for the active team).

List

note1_list_action_items returns open items by default.

  • mine: true for the user's own items, otherwise the whole team's that they can see.
  • status: open, completed, dismissed or all.
  • meetingId for one meeting's items; before and after (ISO dates) filter by the meeting date.
  • Each item has an id, owner, status and a board link. Include the link when you list items.
  • linkedTickets is always an array. Each entry has tool, identifier, url and closeStatus. closeStatus: "pending_ask" means a close is waiting for the user's decision.
  • possiblyDone is null or { source, tool?, ticket?, quote? }. It means note1 saw signs the item is already done, said in a meeting or seen on the linked ticket. Treat it as a proposal: show the quote, ask whether to mark the item done, and do nothing until the user agrees.

Create

note1_create_action_item takes text (one line), optional description, optional meetingId and assignee. Use "me" for the user, a person's name or email for someone else, or leave assignee out for unassigned. File it under a meeting only when the user names one (find the id with search or list first). Give the user the returned link.

Update

note1_update_action_item takes the actionItemId plus any of text, description, assignee ("me", a name, an email or "nobody"), status (open to reopen, completed, dismissed for "won't do") and closeLinkedTickets. Provide at least one change.

Bulk status changes. The tool changes one item per call. When the user asks to change many ("mark all of the standup's items done", "dismiss everything older than two months"), list the matching items first, tell the user the count with a few example texts, and wait for a yes before making the calls. Report how many succeeded and name any that failed.

Read the full file on GitHub · 56 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. 10d ago First seen · 56 lines · 89 tokens per session scan A 30a87d794846

Subscribe to this mod's changes

note1-action-items is a skill published in the GitHub repository note1-ai/note1-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 1,122 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to og-image, differing in 122 lines, and is treated as a copy.

Related

note1-action-items compared with skills from other repositories

note1-action-items next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
note1-action-itemsnote1-ai/note1-mcpSkill12d agoMITA89Claude Code
opik-diagnosecomet-ml/opik-mcpSkill226todayApache-2.0A187Claude Code
cortex-explore-memorycdeust/CortexSkill77todayMITA91Claude Code
qmclaw-workbenchxi-zhao/OpenQuantumSkill724d agoMITA124Codex
quantum-groverxi-zhao/OpenQuantumSkill724d agoMITA62Claude Code, Codex
guppy-programsxi-zhao/OpenQuantumSkill724d agoMITA48Claude Code, Codex
quantum-algorithmsxi-zhao/OpenQuantumSkill724d agoMITA34Claude Code, Codex