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 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/steno)<a href="https://agentmods.dev/skills/stenolabs/stenoai/steno"><img src="https://agentmods.dev/badge/skills/stenolabs/stenoai/steno.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 17 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00300 | $0.01753 |
| Opus 5 | $0.00150 | $0.00877 |
| Sonnet 5 | $0.00060 | $0.00351 |
| Haiku 4.5 | $0.00030 | $0.00175 |
Grade A, and why
steno 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 8d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/steno — the agent's gateway to Steno meeting notes
Steno keeps every meeting on-device as a Markdown summary and a plain-text transcript. This skill makes the agent aware of that store and lets it pull the relevant notes into context, then do whatever the user asked with them.
Data access is one stdlib-only, read-only script: scripts/steno.py — no
dependencies. Run it with python3 scripts/steno.py … (or uv run scripts/steno.py … if the user has uv but no Python on PATH). It never writes,
moves, or deletes — authoring notes is Steno's job, not this skill's.
The pattern: gather → then do the task
Almost every /steno request is two steps. Gather the right notes with the
CLI, then do the task (answer, summarize, draft) with them in context.
- Always start with
locateto confirm the store is found. If it reports 0 meetings, ask the user where their notes are — don't invent meetings. - Find the relevant meetings with
list(browse by date) orsearch(by topic). Use--jsonso you can chain the results. - Pull the full text with
read <stem> -tfor each meeting you need. - Do what was asked with that material.
python3 scripts/steno.py locate # find the store, count meetings
python3 scripts/steno.py list --since 2026-07-01 --json
python3 scripts/steno.py search "pricing" -t --json
python3 scripts/steno.py read "acme" -t # one meeting, summary + transcript
python3 scripts/steno.py folders
What the user can ask /steno to do
The CLI gives you the raw material; you do the reasoning. Common functions:
- Answer a question across meetings.
searchfor the topic,readthe top hits, answer with citations (meeting title + date). "What did we decide about the pricing page?" - Pull one meeting in.
read <query>(add-tif the ask needs the verbatim transcript, not just the summary). "Summarize the Acme call." - Recap a day / week / range.
list --since <date>, read the summaries, produce a digest grouped by meeting. "Recap this week's meetings." - Extract action items or decisions. Read the
## Action Itemssections (and scan summaries/transcripts) across the relevant meetings into one list, noting owners. "What are my open action items from this week?" - Ground a document in real meetings. Gather the meetings, then draft the artifact from them — a spec/PRD, a follow-up email, a status update, release notes. Quote or cite the source meetings so the user can trace claims. "Write a spec from the Acme discovery calls."
What ships with it
3 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.
- 8d ago First seen · 139 lines · 300 tokens per session scan A 545584ce5e36
steno is a skill published in the GitHub repository stenolabs/stenoai (1,305 stars, last pushed yesterday), licensed MIT. It adds 300 tokens to every session and 1,753 once invoked, about $0.0015 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 2026-08-30.
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…
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…
minutes-mirror
Self-coaching analysis of your own behavior across meetings — talk-time ratio, filler words, hedging language, monologue length, energy patterns, and (when meetings are tagged via /minutes-tag) what your behavior in winning meetings looks like vs losing ones. Use this whenever the user says "how did I do", "review my…
minutes-debrief
Post-meeting debrief — analyzes what happened, compares outcomes to your prep intentions, tracks decision evolution. Use when the user says "debrief", "what just happened in that meeting", "what did we decide", "debrief that call", "post-meeting", "what changed", or right after stopping a recording.
minutes-live-sidekick
Act as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start…
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…