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 sleeyax/promptfiles --skill granola-notesgit clone --depth 1 https://github.com/sleeyax/promptfilesWrote 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/sleeyax/promptfiles/granola-notes)<a href="https://agentmods.dev/skills/sleeyax/promptfiles/granola-notes"><img src="https://agentmods.dev/badge/skills/sleeyax/promptfiles/granola-notes/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/sleeyax/promptfiles/granola-notes"><img src="https://agentmods.dev/badge/skills/sleeyax/promptfiles/granola-notes.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 | $0.00052 | $0.00750 |
| Opus 5 | $0.00026 | $0.00375 |
| Sonnet 5 | $0.00010 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
granola-notes 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 9d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Granola Notes
Document: $ARGUMENTS
Pull a Granola meeting document down and hand back its notes as markdown. Example invocations: /granola-notes <share-url>, /granola-notes ec46e3a2-335f-4fca-b9b0-e41c188ebebd.
$ARGUMENTS is the share URL (query string and all) or the bare document UUID. Empty means the link is somewhere in the conversation — use it; if there is none, ask.
Hard rules
- Use
fetch-granola.py, which lives next to this file. Do not fetch the URL withWebFetch(Granola answers HTTP 403 without a browser User-Agent) and do not reach for browser automation — the page's data is in the served HTML. - What a share link exposes is Granola's AI-written summary, not the verbatim transcript. Never present it as a word-for-word record, and never fill gaps by inventing speech.
- Do not follow the "Chat with meeting transcript" link (
notes.granola.ai/t/...) that Granola appends to the notes. It requires a login and redirects away. If the user wants the raw transcript, say it isn't reachable from a share link and let them export it from the Granola app. - Granola's speech-to-text mangles names, product names and jargon. Correct them against what you already know from the conversation or the destination notes, and say which ones you changed.
- When writing the notes somewhere (a file, Logseq, an issue), report anything in the source that contradicts what's already there rather than silently overwriting or silently keeping both.
Workflow
1. Resolve the document
Take the URL or UUID from $ARGUMENTS, or from the conversation. A /t/ transcript URL is not usable — ask for the /d/ document URL.
2. Fetch
./fetch-granola.py <url-or-id>
Markdown goes to stdout: title, creation timestamp, owner, source URL, then the notes. Add --format json when you need the raw ProseMirror document instead of prose — for example to map the note hierarchy onto another tool's block structure.
Errors go to stderr with a non-zero exit and are self-explanatory (403 for a private or revoked link, 404 for a bad id, "no document content" when the link grants no access). Report the failure rather than guessing at the content or retrying with a different tool.
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.
- 9d ago First seen · 54 lines · 52 tokens per session scan A 85030171071f
granola-notes is a skill published in the GitHub repository sleeyax/promptfiles (2 stars, last pushed 10d ago), licensed MIT. It adds 52 tokens to every session and 750 once invoked, about $0.0003 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
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…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.