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-debriefgit 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-debrief)<a href="https://agentmods.dev/skills/silverstein/minutes/minutes-debrief"><img src="https://agentmods.dev/badge/skills/silverstein/minutes/minutes-debrief/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-debrief"><img src="https://agentmods.dev/badge/skills/silverstein/minutes/minutes-debrief.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 | $0.00070 | $0.02410 |
| Opus 5 | $0.00035 | $0.01205 |
| Sonnet 5 | $0.00014 | $0.00482 |
| Haiku 4.5 | $0.00007 | $0.00241 |
Grade A, and why
minutes-debrief scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Path
Before running helper scripts or opening bundled references, set:
export MINUTES_SKILLS_ROOT="$(git rev-parse --show-toplevel)/.agents/skills/minutes"
export MINUTES_SKILL_ROOT="$MINUTES_SKILLS_ROOT/minutes-debrief"
/minutes-debrief
Post-meeting analysis that reads your latest recording, compares what happened to what you planned, and surfaces decision evolution — so nothing falls through the cracks.
How it works
This is a multi-phase interactive flow. It connects to /minutes-prep when a prep file exists, creating a before→after loop.
Phase 1: Find the most recent recording
minutes list --limit 5
Pick the most recent recording. If there are multiple from today, ask via AskUserQuestion: "You have [N] recordings today. Which one are you debriefing?" with options listing the titles.
If no recent recording exists:
Say: "I don't see any recent recordings. Did you run minutes record and minutes stop? If the recording is from a specific meeting, tell me the title or date and I'll find it."
Don't proceed without a recording to debrief.
Phase 2: Read the transcript
Run minutes get "<exact path>" --json, require exit status 0, and use only the
returned transcript and frontmatter. Never reopen the list path with the host
Read tool. Extract:
- Decisions made (from
decisions:frontmatter or## Decisionssection) - Action items created (from
action_items:frontmatter or## Action Itemssection) - Key discussion points (from
## Summaryor the transcript itself) - Attendees (from
attendees:frontmatter)
Phase 2a: No-capture sensitive meetings (capture: none)
If the authorized frontmatter says capture: none, there is no transcript by design: the
meeting was designated sensitive and the recorder never ran. The debrief IS the
record. Switch to debrief-from-memory mode:
- Use the already-authorized response: the
## Markerssection (timestamped notes typed during the meeting) and the frontmatter (title,date,duration,debrief:state). - Ask the user to recount the meeting: who was there, what was discussed, decisions, action items. Use the markers as memory joggers.
- Present the account in the conversation, but do not edit the meeting path through a host filesystem tool. Until Minutes exposes a native authorized debrief-update command, ask the user to persist it in the desktop app or a human-operated CLI flow.
- If the user says it was a test or accidental trigger, report that conclusion without mutating the source path from this skill.
- Sensitivity is binding, not advisory. A restricted meeting is not available to this agent skill by default. Do not bypass a failed native read; direct the user to a human-operated Minutes app/CLI flow with the explicit audited restricted-access controls.
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.
- 11d ago First seen · 232 lines · 70 tokens per session scan A 6dbb47f36423
minutes-debrief is a skill published in the GitHub repository silverstein/minutes (1,471 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 2,410 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 2026-08-30.
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…