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 nweii/agent-stuff --skill obsidian-granolagit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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/nweii/agent-stuff/obsidian-granola)<a href="https://agentmods.dev/skills/nweii/agent-stuff/obsidian-granola"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/obsidian-granola/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/nweii/agent-stuff/obsidian-granola"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/obsidian-granola.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 | $0.00040 | $0.02471 |
| Opus 5.5 | $0.00016 | $0.00988 |
| Sonnet 5.5 | $0.00008 | $0.00494 |
| Haiku 4.5 | $0.00004 | $0.00247 |
Grade A, and why
obsidian-granola 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 13d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Granola meeting notes
Import meeting data into linked meeting and transcript notes. Read the vault's instructions before note work and use its available CLI or connector; tool names vary by environment.
Choose the workflow
- Import: requests to sync or fetch a meeting follow the steps below. Finish after the notes are saved, linked, and read back; auditing and enrichment are separate unless requested.
- Process: requests to process a meeting, audit and enrich it, or resume after pasting a transcript follow Process a meeting. Reuse existing notes before importing anything.
- Recording: when the input is an audio/video file, use
transcribe-audioonly if local transcription is requested and the runtime supports it. Feed the resulting transcript into processing; the other branches need no local transcription runtime.
An ambiguous meeting needs identifying before any writes. Carry supplied titles, destinations, and earlier approvals forward.
1. Capture Intent & Context
First, determine which meeting the user wants to sync.
- If they say "my last meeting", you will need to list recent meetings to find it.
- If they specify a person or topic, search or list recent meetings to identify the correct one.
- If the user says they already have an existing prepared note for this meeting in Obsidian, append the Granola contents to their existing note, and create a separate transcript note.
- Otherwise, you will generate a new title and create both the meeting note and transcript note from scratch.
2. Fetch Granola Data
Use the connected Granola tools to list or search meetings, read the selected meeting's summary/action items/private notes, and fetch its verbatim transcript. Discover the tools actually exposed rather than requiring one provider's identifiers.
If transcript access fails or is unavailable, continue importing the meeting and save an empty transcript staging note for manual paste. Check the returned data and saved note; plan restrictions are a possible reason, not a fact to assume.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago Changed · +8 lines · -20 tokens per session 1eeeb3c622f5
- 18d ago Changed 31620979a4d3
- 1mo ago Changed · +2 lines 7e210257c245
- 1mo ago First seen · 151 lines · 60 tokens per session scan A b66308691759
obsidian-granola is a skill published in the GitHub repository nweii/agent-stuff (10 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 2,471 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.
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…
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
box
Box manages cloud files, sharing, search, and metadata.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
material-organizer
Organize only the materials the user has already provided or explicitly pointed to. The job is to make messy inputs easier to scan, reuse, archive, or continue from later while preserving source traceability.