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 samkawsarani/sams-product-plugins --skill sync-meetingsgit clone --depth 1 https://github.com/samkawsarani/sams-product-pluginsWrote 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/samkawsarani/sams-product-plugins/sync-meetings)<a href="https://agentmods.dev/skills/samkawsarani/sams-product-plugins/sync-meetings"><img src="https://agentmods.dev/badge/skills/samkawsarani/sams-product-plugins/sync-meetings/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/samkawsarani/sams-product-plugins/sync-meetings"><img src="https://agentmods.dev/badge/skills/samkawsarani/sams-product-plugins/sync-meetings.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 | $0.00045 | $0.01221 |
| Opus 5.5 | $0.00018 | $0.00488 |
| Sonnet 5.5 | $0.00009 | $0.00244 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
sync-meetings 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 2mo 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependency Check
Before starting, verify required dependencies:
- Granola MCP (required): Check if Granola MCP tools are available in your tools list.
- If missing: Tell the user: "The Granola MCP server is not configured. This skill requires Granola MCP. Please install and configure the Granola MCP server (see https://granola.ai) and try again." Stop here.
Context
Sync state is tracked in <target-folder>/.synced-meetings.json.
Today's date: $TODAY
Arguments: $ARGUMENTS
Your Task
Sync Granola meetings to <target-folder> using the Granola MCP.
Step 1: Parse Arguments
- First positional arg = target folder (default:
meetings/) --days N= sync meetings from the last N days--all= re-sync all meetings, ignoring sync state
Step 2: Check Sync State
Read <target-folder>/.synced-meetings.json. If it doesn't exist, this is a first sync.
{
"last_sync": "<ISO timestamp>",
"synced": {
"<meeting-uuid>": {
"title": "Meeting Title",
"synced_at": "<ISO timestamp>",
"file_path": "meetings/2026-03-16-Meeting-Title.md"
}
}
}
Step 3: List Meetings from Granola
Via Granola MCP, list meetings with the appropriate time range:
- First sync (no
.synced-meetings.json): uselast_30_days - Subsequent syncs: use
this_week --days N: use custom range based on N--all: uselast_30_daysand ignore existing sync state
Step 4: Filter Unsynced Meetings
Compare returned meeting IDs against the synced keys in .synced-meetings.json.
- Skip any meeting whose ID is already synced (unless
--allwas passed) - Build a list of unsynced meetings with title + date
Step 5: Present to User
Show the list of unsynced meetings:
Found N new meetings to sync:
1. 2026-03-18 — Weekly Standup
2. 2026-03-17 — Product Review
3. 2026-03-16 — 1:1 with Manager
Sync all, select specific (e.g. "1,3"), or skip?
Wait for user confirmation before proceeding.
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.
- 2mo ago First seen · 156 lines · 45 tokens per session scan A ec9cbbc7e009
sync-meetings is a skill published in the GitHub repository samkawsarani/sams-product-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,221 once invoked, about $0.0002 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 2026-08-31.
sync-meetings compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sync-meetingssamkawsarani/sams-product-plugins | Skill | 2 | 1mo ago | MIT | A | 45 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 112k | today | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | 2d ago | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | today | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 11d ago | MIT | A | 52 | Claude Code, Codex |