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 stablebaseline/mcp --skill sb-meetinggit clone --depth 1 https://github.com/stablebaseline/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/stablebaseline/mcp/sb-meeting)<a href="https://agentmods.dev/skills/stablebaseline/mcp/sb-meeting"><img src="https://agentmods.dev/badge/skills/stablebaseline/mcp/sb-meeting.svg" alt="Measured on agentmods" 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 | $0.00126 | $0.01750 |
| Opus 5 | $0.00063 | $0.00875 |
| Sonnet 5 | $0.00025 | $0.00350 |
| Haiku 4.5 | $0.00013 | $0.00175 |
Grade A, and why
sb-meeting 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 7d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stable Baseline: meeting scribe
What this skill does
Invites a bot into a live meeting. While the call runs, the bot paints an existing whiteboard with sticky notes and topic clusters, ticks off an agenda, and pins decisions and actions to rails. When the meeting ends the board holds a finished meeting map that the team keeps working in.
The bot transcribes only and stores no recording.
Consent comes first, and it is not inferable
Never start a scribe unless the user has asked for it in this conversation, in words.
Sending a bot into someone's meeting has legal and social consequences that vary by jurisdiction and by company. It is never a reasonable inference from "I have a meeting at three" or "can you help with my standup". If the request is implicit, ask.
Before starting, tell the user in one line, plainly:
- a visible bot will join the meeting,
- it transcribes and stores no recording,
- everyone in the call can see it is there.
Then let them decide. If they hesitate, do not start.
A board is required
startMeetingScribe requires documentId, the id of an existing whiteboard, and
meetingUrl.
If you do not have a whiteboard id, ask the user which board to paint. Do not create one automatically.
agenda seeds the items the scribe ticks off. settings carries scribe options.
Cost and approval
It bills 2 credits per minute in 5-minute blocks while it runs. A 60-minute meeting is about 120 credits. There is a hard cap of 180 minutes. It is available on the Pro and Enterprise plans.
Call startMeetingScribe first without confirm to get the exact quote plus the
workspace balance. Show both to the user. Only call again with confirm: true once they
agree. Approval for one meeting is never approval for the next.
While it runs
getMeetingScribeStatus requires the sessionId returned by startMeetingScribe. Poll
every 15 to 30 seconds. It reports the session state, which is one of joining, in the
waiting room, live in the call, paused, ending, ended or failed, plus a live activity feed
of what the scribe has painted and the board it is painting.
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.
- 7d ago First seen · 162 lines · 126 tokens per session scan A 262b97da960a
sb-meeting is a skill published in the GitHub repository stablebaseline/mcp (0 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 1,750 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.