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 ozzy-labs/suasor --skill meetinggit clone --depth 1 https://github.com/ozzy-labs/suasorWrote 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/ozzy-labs/suasor/meeting)<a href="https://agentmods.dev/skills/ozzy-labs/suasor/meeting"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/meeting/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/ozzy-labs/suasor/meeting"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/meeting.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 | $0.00100 | $0.01161 |
| Opus 5 | $0.00050 | $0.00580 |
| Sonnet 5 | $0.00020 | $0.00232 |
| Haiku 4.5 | $0.00010 | $0.00116 |
Grade A, and why
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 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.
What it actually says
meeting
会議まわりの read 系単一入口（ADR-0046）。phase で会議の前後を切り替える。read-only。pair: 会議直後の action item 抽出（write / HITL）は meeting-followup。
以前は meeting-prep（前）と action-item-status（後）に分かれていた。どちらも「あの会議まわりで何がある / どうなった」であり、違いは時間の向きだけである。
いつ発火するか
| 言いかた | phase |
|---|---|
| 「来週の会議準備」「明日のミーティング前確認」「次の会議の context」「打ち合わせ前に状況教えて」 | prep（既定） |
| 「あの会議から何が実装されたか」「会議で決めた action item の進捗」「決めたことの実装状況」 | status |
何をするか（MCP tool flow）
すべて read tool（ADR-0004）。
phase=prep
source.listで対象の calendar event を引く。startsAfter/startsBefore（イベント自身の開始時刻）で絞る —observedAfter/observedBeforeは更新時刻の窓なので別の問いに答えてしまう（3 か月前に予約された明日の会議が落ち、昨日タイトルを直した先月の会議が入る。ADR-0044 決定 2 / #490）- 「次の会議」「そろそろ何かある?」のように対象を指定されていないときは
demand.list（source="calendar"）を使う。準備が要る予定（meeting_prep: 24 時間以内 かつ 議題 / 添付 / 自分が organizer）と直前の予定（meeting_soon: 120 分以内）だけが、開始が近い順に返る。辞退済み・任意参加・終日予定は除外済み（ADR-0044 決定 4）
- 「次の会議」「そろそろ何かある?」のように対象を指定されていないときは
source.get（externalId）で event 本文・議題を取るsearchで過去の関連やりとりを引くgraph.relatedで関連 decisions / sources を辿る- 目的 / 過去文脈 / 関連 decisions / 参考 sources を組み立てて返す
phase=status
source.list（startsAfter/startsBefore）で対象の会議 event を特定するgraph.relatedでその会議に由来する task / decision を辿るtask.list（state）で各 task の現在状態を引く- **決めたことごとに「実装された / 進行中 / 手つかず」**を対応付けて返す
制約
- read-only。persist しない（action item の登録は
meeting-followup、HITL） - calendar が未取り込みなら該当 connector の sync を案内する
- 会議由来かどうかの判定は provenance link（
graph.related）に基づく。推測で紐付けない
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.
- 11d ago First seen · 62 lines · 100 tokens per session scan A 17fee530174b
meeting is a skill published in the GitHub repository ozzy-labs/suasor (0 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,161 once invoked, about $0.0005 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
zoom-meeting-scribe
A listen-only note-taking workflow for Zoom meetings. It receives live transcript sections, organizes what was said, and prepares a report after the meeting ends.
meeting-reminder-email
A scheduled task that sends one meeting reminder email at 6:00 in the morning to [email protected]. The supplied description does not specify the meeting time or date.
lark-meeting
Use Lark CLI to locate meetings, manage Minutes and AI notes, inspect transcripts, and run authorized live-meeting interactions.
meeting-summary
A meeting-notes tool that turns supplied records into a structured summary of topics, decisions, and follow-up tasks.
Meeting Distiller Pro
Transform messy meeting notes and transcripts into structured action items, decisions, and follow-ups. Never lose a meeting insight again.
meetily
A meeting assistant that runs entirely on the local computer: it captures audio, transcribes speech with Parakeet or Whisper, and uses Ollama or another language model to create summaries. No cloud service is required.