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.
npx skills add note1-ai/note1-mcp --skill note1-recordingsgit clone --depth 1 https://github.com/note1-ai/note1-mcpWrote 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.
[](https://agentmods.dev/skills/note1-ai/note1-mcp/note1-recordings)<a href="https://agentmods.dev/skills/note1-ai/note1-mcp/note1-recordings"><img src="https://agentmods.dev/badge/skills/note1-ai/note1-mcp/note1-recordings/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.
<a href="https://agentmods.dev/skills/note1-ai/note1-mcp/note1-recordings"><img src="https://agentmods.dev/badge/skills/note1-ai/note1-mcp/note1-recordings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00081 | $0.01742 |
| Opus 5.5 | $0.00032 | $0.00697 |
| Sonnet 5.5 | $0.00016 | $0.00348 |
| Haiku 4.5 | $0.00008 | $0.00174 |
Grade A, and why
note1-recordings 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
note1 recordings
note1 records meetings with a bot that joins the call, and also accepts recordings the user already has. Every tool takes an optional teamId (omit it for the active team). note1 holds no calendar write access: these tools control note1's bot only and never create or change calendar events or invite anyone.
Schedule the bot
note1_schedule_recording needs exactly one of:
calendarEventId(fromnote1_get_calendar) to record an existing calendar event. AddapplyToSeries: trueto record every occurrence of a recurring event.callUrlto send the bot to any meeting link, withcallAt(ISO start time, default now) and an optionaltitle.
callUrl takes the meeting link. If the bot cannot join it, relay the error; the scheduling link below is limited to Google Meet and Teams.
Convert relative times ("3pm today") to an absolute ISO time with the user's time zone, and repeat the time back when you confirm. Reply with the meetingId and status it returns.
Create a new meeting with the bot already invited
note1 cannot create calendar events. For "set up / book a meeting", call note1_get_scheduling_link with platform meet or teams (Zoom is not supported there; add an IANA timezone, default UTC). Give the user the returned link: they open it and create the event in their own calendar, with note1 pre-invited.
Which events are recorded
note1_get_calendar lists events with their per-event recording status. It defaults to upcoming events; set upcoming: false for past ones and limit (1 to 100) to bound the list. Use it for "which of my meetings tomorrow are being recorded?" and to find a calendarEventId.
Change or cancel
note1_update_meetingchanges the title, bot time (callAt, must be in the future) or link (callUrl), summarystyle,languageandrecordVideo. Time and link changes retarget note1's bot only, attendees' calendars are untouched. Pass at least one field.applyToSeries: trueapplies it to this and future occurrences.note1_cancel_recordingcalls off the bot. A meeting that goes unrecorded cannot be recorded afterwards, so confirm first. For a recurring meeting, ask whether to cancel only this occurrence or the series, and setcancelSeries: trueonly for the series.
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.
- 2d ago Changed · +5 lines e900c1e3167a
- 10d ago First seen · 60 lines · 81 tokens per session scan A eda38e4341f8
note1-recordings is a skill published in the GitHub repository note1-ai/note1-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 1,742 once invoked, about $0.0003 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 2026-11-05.
note1-recordings compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| note1-recordingsnote1-ai/note1-mcp | Skill | 1 | 2d ago | MIT | A | 81 | Claude Code |
| opik-diagnosecomet-ml/opik-mcp | Skill | 226 | today | Apache-2.0 | A | 187 | Claude Code |
| cortex-explore-memorycdeust/Cortex | Skill | 77 | today | MIT | A | 91 | Claude Code |
| qmclaw-workbenchxi-zhao/OpenQuantum | Skill | 72 | 4d ago | MIT | A | 124 | Codex |
| quantum-groverxi-zhao/OpenQuantum | Skill | 72 | 4d ago | MIT | A | 62 | Claude Code, Codex |
| guppy-programsxi-zhao/OpenQuantum | Skill | 72 | 4d ago | MIT | A | 48 | Claude Code, Codex |
| quantum-algorithmsxi-zhao/OpenQuantum | Skill | 72 | 4d ago | MIT | A | 34 | Claude Code, Codex |