StenoAI is a private desktop notepad and meeting notetaker that records conversations, summarizes them, and lets users query them with local AI models. It is intended for confidential meetings in government, defence, and executive settings on Windows and macOS.
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 stenolabs/stenoai --skill granola-to-stenogit clone --depth 1 https://github.com/stenolabs/stenoaiWrote 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/stenolabs/stenoai/granola-to-steno)<a href="https://agentmods.dev/skills/stenolabs/stenoai/granola-to-steno"><img src="https://agentmods.dev/badge/skills/stenolabs/stenoai/granola-to-steno/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/stenolabs/stenoai/granola-to-steno"><img src="https://agentmods.dev/badge/skills/stenolabs/stenoai/granola-to-steno.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 140 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 140 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00163 | $0.02497 |
| Opus 5 | $0.00081 | $0.01248 |
| Sonnet 5 | $0.00033 | $0.00499 |
| Haiku 4.5 | $0.00016 | $0.00250 |
Grade C, and why
granola-to-steno scanned grade C with 1 finding 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 12d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /tmp/steno_out How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Granola -> Steno sync
This skill rebuilds Steno's local meeting files from Granola. Steno stores each meeting as two files in a folder it watches:
<STENO_DIR>/output/<stem>_summary.md # frontmatter + Summary + Transcript + sections
<STENO_DIR>/transcripts/<stem>_transcript.txt
<stem> is YYYYMMDD-HHMM_<slugified-title>. Because the stem is derived from
the meeting's date and title, rewriting an existing meeting is a no-op and new
meetings are simply added - the whole flow is safe to run repeatedly and on a
schedule.
The bundled generator (scripts/steno_gen.py) does the Steno-specific
formatting (cleans Granola markdown into the plain-text shape Steno renders,
diarises the transcript, writes both files). This skill's job is to gather the
raw Granola data into a simple staging folder and hand it to the generator.
Prerequisites
- A connected Granola MCP exposing
list_meetings,get_meetings, andget_meeting_transcript. The MCP server id is environment-specific, so load the tools by name with ToolSearch rather than assuming a fixed prefix. - Python 3 available in the shell.
- A target Steno directory containing (or able to contain)
output/andtranscripts/subfolders. This is often inside iCloud Drive - see Step 3.
Step 0 - Gather settings
Decide these up front (ask the user only if not obvious; otherwise use the defaults):
- Time range - default: union of
this_weekandlast_week. For a one-off backfill uselast_30_daysor acustomrange. - Target Steno directory (
STENO_DIR) - see Step 3. - Language - the language your meetings are in, as a short code (
en,fr,de, ...). Defaults toen. Passed to the generator via--languagein Step 6.
Step 1 - Load the Granola tools
Load the three Granola tools in one ToolSearch call, e.g.:
ToolSearch { query: "list_meetings get_meetings get_meeting_transcript", max_results: 5 }
Confirm the matched tools belong to the Granola server before calling them.
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.
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.
- 12d ago First seen · 204 lines · 163 tokens per session scan C f1404dae7800
granola-to-steno is a skill published in the GitHub repository stenolabs/stenoai (1,310 stars, last pushed 4d ago), licensed MIT. It adds 163 tokens to every session and 2,497 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
scheduling
Set up recurring or scheduled work — anything the user wants run on a schedule, repeatedly, or at a future time ("every morning", "each weekday at 9am", "daily digest", "weekly report", "remind me", "run this on a cron"). Teaches how to author a durable Vexa Scheduler routine that survives restarts. Use this instead…
minutes-record
Start or stop recording a meeting, call, or voice memo. Use this whenever the user says "record", "start recording", "capture this meeting", "stop recording", "I'm in a meeting", "take notes on this call", or wants to transcribe live audio. Also use when they ask about recording status or want to know if something is…
minutes-note
Add a note to the current recording or annotate a past meeting. Use whenever the user says "note that", "remember this", "mark this as important", "add a note about", "annotate the meeting", or wants to capture a thought during or after a recording. Plain text input — no markdown needed.
vexa-meetings
Work with the user's meetings through the Vexa MCP tools — send a bot to a call, follow the transcript while it runs, and write meetings into their notes (Obsidian, Notion, plain markdown) with speakers and action items. Use whenever the user mentions a meeting, a call, a transcript, meeting notes, or asks what was…
Files, Office & Drive on Mac (Local MCP)
Use when the user wants to find, read or create files and Office documents (Word/Excel/PowerPoint/PDF) on a Mac, or browse OneDrive / Google Drive. Powered by Local MCP, on-device.
notion
Read and write Notion pages, databases (data sources), and blocks via the Notion REST API.