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 glebis/claude-skills --skill granolagit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/granola)<a href="https://agentmods.dev/skills/glebis/claude-skills/granola"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/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/glebis/claude-skills/granola"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/granola.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.00931 |
| Opus 5 | $0.00024 | $0.00465 |
| Sonnet 5 | $0.00010 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
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 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Granola Meeting Importer
Query Granola via Personal API to list notes, view transcripts, and export to Obsidian vault in the same format as the Fathom skill.
Prerequisites
- Granola Business or Enterprise plan (Personal API required)
- API key in sops-encrypted
~/Brains/brain/.env.granolaasGRANOLA_API_KEY=grn_... - No additional dependencies (uses stdlib only)
Usage
python3 ~/.claude/skills/granola/scripts/granola.py <command> [options]
Commands
| Command | Description |
|---|---|
list |
List notes from Personal API |
show <note_id> |
Show note details (summary, attendees, optionally transcript) |
export <note_id> |
Export note to Obsidian markdown (Fathom-compatible format) |
Options
| Option | Applies to | Description |
|---|---|---|
--format text|json |
list, show | Output format (default: text) |
--after <ISO date> |
list | Filter notes created after date |
--all |
list | Paginate through all results |
--transcript |
show | Include transcript in output |
--vault <path> |
export | Obsidian vault path (default: ~/Brains/brain) |
--output <path> |
export | Custom output file path |
Examples
List recent meetings
python3 ~/.claude/skills/granola/scripts/granola.py list
python3 ~/.claude/skills/granola/scripts/granola.py list --format json
python3 ~/.claude/skills/granola/scripts/granola.py list --after 2026-05-01
Show note with transcript
python3 ~/.claude/skills/granola/scripts/granola.py show not_5FkswTp4Omkpm5
python3 ~/.claude/skills/granola/scripts/granola.py show not_5FkswTp4Omkpm5 --transcript --format json
Export to Obsidian
python3 ~/.claude/skills/granola/scripts/granola.py export not_5FkswTp4Omkpm5
python3 ~/.claude/skills/granola/scripts/granola.py export not_5FkswTp4Omkpm5 --vault ~/Brains/brain
Output Format
Exported notes match Fathom skill format for consistency:
---
granola_id: not_xxxx
title: "Meeting Title"
date: YYYY-MM-DD
participants: ['Name 1', 'Name 2']
duration: HH:MM
source: granola
---
# Meeting Title
## Summary
{AI-generated summary}
## Transcript
**Speaker Name**: What they said...
What ships with it
15 files 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.
- .claude-plugin/plugin.json 289 B
- references/cache-structure.md 2.0 KB
- scripts/granola.py 9.2 KB runs code
- scripts/sync.sh 2.1 KB runs code
- scripts/tests/__init__.py 0 B runs code
- scripts/tests/fixtures/cache_object_state.json 811 B
- scripts/tests/fixtures/cache_string_state.json 1.0 KB
- scripts/tests/test_cmd_export.py 1.2 KB runs code
- scripts/tests/test_cmd_list.py 1.0 KB runs code
- scripts/tests/test_cmd_show.py 1.3 KB runs code
- scripts/tests/test_compute_duration.py 724 B runs code
- scripts/tests/test_extract_calendar_times.py 915 B runs code
- scripts/tests/test_extract_people.py 1.1 KB runs code
- scripts/tests/test_format_time.py 427 B runs code
- scripts/tests/test_load_cache.py 878 B runs code
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 · 104 lines · 49 tokens per session scan A 304bea397ac4
granola is a skill published in the GitHub repository glebis/claude-skills (374 stars, last pushed 9d ago), licensed MIT. It adds 49 tokens to every session and 931 once invoked, about $0.0002 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 2026-09-03.
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…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.