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 meeting-followupgit 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-followup)<a href="https://agentmods.dev/skills/ozzy-labs/suasor/meeting-followup"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/meeting-followup/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-followup"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/meeting-followup.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 | $0.00139 | $0.00872 |
| Opus 5 | $0.00069 | $0.00436 |
| Sonnet 5 | $0.00028 | $0.00174 |
| Haiku 4.5 | $0.00014 | $0.00087 |
Grade A, and why
meeting-followup 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- source-extract — 86% identical, 39 lines differ
What it actually says
meeting-followup
会議後に action items を抽出する HITL write skill（ADR-0004）。pair: 会議前は meeting。
いつ発火するか
- 「会議後の action items」「ミーティングのフォローアップ」「議事録から task 抽出」
- 「昨日の会議どうだった」「打ち合わせのフォロー」
何をするか（MCP tool flow）
read で集め、write は HITL。auto-apply 経路は存在しない（ADR-0004）。
source.list（calendar のsourceType、observedBefore=nowで直近）で対象会議を集めるsource.get（externalId）で議事録 / 関連やりとりを読むsearch（mode=semantic） で会議トピックの関連 context を引く（embedding 無効時はsignal: embedding_disabledを見てsearch（FTS）へフォールバック、ADR-0005）propose.generate（mode=meeting_followup）で task / decision 候補を生成する（TaskProposed/DecisionRecorded候補に対応、data-model.md）propose.list（state=pending）で生成済み候補を一覧し、ユーザーに提示して確認を取る（native framing: ホスト側で人の承認を促す。Issue #89）- ユーザーが承認した候補のみ
propose.applyで保存する（idempotent）。不要な候補はpropose.reject（任意で理由）で却下する（却下は記録され、再 apply されない）
制約
- HITL。人の承認なしに
propose.applyを呼ばない。auto-apply しない。propose.listは read（候補確認）、propose.rejectは却下の記録 - 本 skill は手順書のみで実処理を持たない
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 · 48 lines · 139 tokens per session scan A 68f0ed8f0a7a
meeting-followup is a skill published in the GitHub repository ozzy-labs/suasor (0 stars, last pushed 1mo ago), licensed MIT. It adds 139 tokens to every session and 872 once invoked, about $0.0007 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
meeting-notes
A meeting-notes layout that records the meeting title, attendees, agenda, decisions, action items, owners, deadlines, status, and next meeting. Action items are tasks agreed during the meeting.
meeting-notes
This skill transforms raw meeting notes, transcripts, or audio summaries into clear, structured documentation with action items, decisions, and key takeaways.
note.thread-threads
Guidelines and lifecycle rules for using thread Notes as a high-efficiency comment and chat thread channel across Kylrix resources (calls, tasks, tags, projects, events, forms) without database bloat.
workspace.projects-table
Canonical architecture for Workspaces and the projectobjects join table in Kylrix. Use when working on /workspaces, workspace switches, object filtering (ideas, goals, secrets, events, forms), or LocalEngine caching.
why.free-tier-limits-8-collaborators
Explain why databases, notes, passwords, forms, and TOTPs are completely free and unlimited, but capped at 8 collaborators per resource to avoid undocumented rendering/concurrency bugs.
system.cross-app-linking
Maintains cross-app pointers and metadata links between notes, tasks, calls, and secure objects. Use when connecting features across domain surfaces without duplicating data.