Minutes is an open-source, local-first meeting recorder that transcribes meetings, calls, and voice memos on the device and stores the results as Markdown files. It is for people who want their meeting records available to Claude Code, Codex, Cursor, and other MCP clients without uploading them. The catalogue add-ons extend agent workflows for querying and using those local meeting files.
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 silverstein/minutes --skill minutes-copilotgit clone --depth 1 https://github.com/silverstein/minutesWrote 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/silverstein/minutes/minutes-copilot)<a href="https://agentmods.dev/skills/silverstein/minutes/minutes-copilot"><img src="https://agentmods.dev/badge/skills/silverstein/minutes/minutes-copilot/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/silverstein/minutes/minutes-copilot"><img src="https://agentmods.dev/badge/skills/silverstein/minutes/minutes-copilot.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 | $0.00116 | $0.00685 |
| Opus 5 | $0.00058 | $0.00342 |
| Sonnet 5 | $0.00023 | $0.00137 |
| Haiku 4.5 | $0.00012 | $0.00068 |
Grade A, and why
minutes-copilot 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/minutes-copilot
Use the real Minutes copilot runtime to start or control Coach. Do not build a transcript reader, event poller, prompt loop, or shell tailer in this skill.
If the user explicitly asks you or the current terminal agent to watch, advise, or strategize, use /minutes-live-sidekick instead. If the user says only "coach me live" or otherwise leaves the surface ambiguous, ask exactly: "Do you want me in this terminal to be your sidekick, or should I open the Minutes Coach HUD?" Do not start Coach while clarifying.
Start Coach
- Get one concrete meeting goal. Use the user's stated goal; if none is present, ask exactly: "What outcome should Coach help you achieve in this meeting?"
- Choose a supported mode only when the user makes it clear:
sales,discovery,interview,negotiation,difficult-conversation,decision, orgeneric. Default togeneric. - If first-party Minutes copilot MCP controls are actually available, call their start control with the same goal, mode, and
tuisurface. Never invent an MCP tool name. - Otherwise invoke the foreground CLI, passing the goal as one safely escaped argument:
minutes copilot start --goal '<meeting goal>' --surface tui --mode generic
The tui surface is the Coach HUD. Keep the command attached as the live session. Add --live only when the user explicitly asks Coach to own a standalone capture; normally Coach attaches to the existing Minutes capture stream.
Control an active session
Use the matching real MCP control when present; otherwise run exactly one of:
minutes copilot status
minutes copilot pause
minutes copilot resume
minutes copilot stop
Do not start a second session when minutes copilot status reports one active. Pausing or stopping Coach must not stop recording.
Output
After a successful start, report the goal and mode in one line: Coach is listening — goal: <goal> · mode: <mode>. For status or control actions, relay the command result concisely. If the provider is unavailable, say that Coach degraded or did not start and make clear that recording remains unaffected.
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 · 48 lines · 116 tokens per session scan A e6771ee75f4f
minutes-copilot is a skill published in the GitHub repository silverstein/minutes (1,469 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 685 once invoked, about $0.0006 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…
steno
Make the agent aware of the user's Steno meeting notes and able to pull them in on request. Steno (https://github.com/stenolabs/stenoai) records, transcribes, and summarizes meetings entirely on-device, storing each as a Markdown summary plus a transcript. This skill locates that store cross-platform (macOS, Windows…
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…
meeting_notes
Structure raw meeting notes into actionable minutes with follow-ups.
focus-and-priority-management
Delivers daily scheduling habits, meeting hygiene, attention management, and boundary-setting techniques for leaders whose calendars have become their strategy by default. Use when urgent tasks crowd out important ones, when meeting load exceeds productive work time, when a leader cannot recall their last hour of…
granola-to-steno
Sync Granola meeting notes into Steno's file-based store. Reads recent meetings from the Granola MCP (titles, dates, participants, AI summaries, verbatim transcripts) and regenerates Steno's output/summary.md and transcripts/transcript.txt files in a target folder (e.g. an iCloud Drive directory). The operation is…