A search tool for Granola meeting notes, summaries, and transcripts. Granola is a meeting-notes service that records or stores written accounts of meetings.

Use it to find relevant meetings and read their notes, summaries, or transcripts.

It reduces the need to search through meeting records by hand when you need past decisions or discussion details.

granola — Skill for Claude Code and Codex by asgeirtj

About the project

System Prompts Leaks is a collection of captured system instructions used to guide AI chatbots and coding agents before they receive user messages. It serves researchers and developers studying how different AI assistants are directed.

asgeirtj/system_prompts_leaks · 69,084 stars · on GitHub

Install

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.

Any agent

npx skills add asgeirtj/system_prompts_leaks --skill granola

Clone the repo

git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/granola/github.svg)](https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/granola)

Your own site

<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/granola"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/granola"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/granola.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 784 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00021	$0.00784
Opus 5.5	$0.00008	$0.00314
Sonnet 5.5	$0.00004	$0.00157
Haiku 4.5	$0.00002	$0.00078

Measured 3d ago against content hash 02b98ed66f57, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 3d 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.

Meta/muse-agent/skills/granola/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Granola

Purpose

Search Granola meeting notes, summaries, and transcripts through the hosted
Granola MCP server (https://mcp.granola.ai/mcp).

Tooling

Use exec to run:

granola-cli <subcommand> [options]

Connection management

granola-cli status
granola-cli authorize-url
granola-cli exchange-code --code <code> [--redirect-uri <url>]
granola-cli refresh
granola-cli disconnect

MCP operations

granola-cli list-tools
granola-cli call-tool --name <tool> --arguments-json '<json-object>'

--arguments-json must be a JSON object; arrays or scalars are rejected. Use list-tools first to discover the tool catalogue and each tool's
input_schema.

Auth

OAuth is handled by authd via Dynamic Client Registration + PKCE (S256). The credential stays behind authd; do not read or edit connector auth files.

First-use setup flow

Run granola-cli status.
If status is not_connected, run granola-cli authorize-url. When connect_url is present, replace <connect_url> with the returned URL and share exactly this Markdown link: [Connect Granola](<connect_url>); do not paste the raw URL separately. Wait for the user to complete authorization.
After the user authorizes, the browser is redirected via the Muse relay back to this VM, and authd completes the code exchange automatically. The agent resumes once the token lands.
Re-run granola-cli status. When status flips to connected the output also includes the discovered MCP tool catalogue.

For manual environments where the relay is not wired up, call granola-cli exchange-code --code <auth-code> after receiving the code.

Operating Rules

Run granola-cli status before any MCP work. If not connected, complete the setup flow first.
Call list-tools before call-tool unless you already know the tool name and its argument shape. Never guess tool names.
arguments-json must be a JSON object; wrap every argument appropriately.
Prefer query_granola_meetings for natural-language questions, list_meetings for metadata, get_meetings for known meeting IDs, and get_meeting_transcript only when the user needs verbatim detail. Use get_account_info to answer which account/workspace is connected and, when results come back empty, to check mcp_note_access.scopes — a workspace whose MCP access is public-only excludes personal notes. list_meetings defaults to the last 30 days; when it returns zero meetings, retry with time_range: "custom" plus custom_start and custom_end before concluding the account has no meetings, and use list_meeting_folders to see what the workspace actually holds.
Preserve Granola citation links in user-facing answers.
Do not use Granola for calendar scheduling or upcoming-event planning.
Token refresh happens automatically on 401. If call-tool keeps failing with unauthorized, run granola-cli refresh explicitly or ask the user to re-authorize.

Read the full file on GitHub · 83 lines

Files

What ships with it

2 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.

Changes

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.

3d ago First seen · 83 lines · 21 tokens per session scan A 02b98ed66f57

Subscribe to this mod's changes

granola is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,084 stars, last pushed today), licensed CC0-1.0. It adds 21 tokens to every session and 784 once invoked, about $0.0001 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 2026-10-05.

Claude Code Productivity ai anthropic chatbot chatgpt claude

granola

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Granola

Purpose

Tooling

Connection management

MCP operations

Auth

First-use setup flow

Operating Rules

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

google-workspace

simplify-code

himalaya

apple-reminders

apple-notes

imessage