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-lintgit 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-lint)<a href="https://agentmods.dev/skills/silverstein/minutes/minutes-lint"><img src="https://agentmods.dev/badge/skills/silverstein/minutes/minutes-lint/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-lint"><img src="https://agentmods.dev/badge/skills/silverstein/minutes/minutes-lint.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 | $0.00061 | $0.00747 |
| Opus 5 | $0.00030 | $0.00374 |
| Sonnet 5 | $0.00012 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
minutes-lint 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/minutes-lint
Run a consistency check across policy-authorized normal meetings to find decision conflicts and stale commitments. Restricted meetings are excluded from this agent workflow by default and must never be described as absent evidence.
How to run the lint
-
Run the consistency check:
minutes consistency --stale-after-days 14Optional filters:
--owner <name>— limit to commitments assigned to a specific person--stale-after-days <N>— change the staleness threshold (default: 7)
-
Parse the JSON output and present it as readable markdown.
Formatting the report
Decision Conflicts
For each conflict, show:
**Topic: {topic}**
- Latest: "{latest decision text}" — *{meeting title}* ({date})
- Prior: "{prior decision text}" — *{meeting title}* ({date})
- **Status**: These decisions may contradict each other.
Frontmatter v2: resolved supersessions. When the resolution field is
present on a conflict, the newer decision has a supersedes: entry in its
frontmatter. Treat this as informational, not a red flag. Format as:
**Topic: {topic}** ✓ Resolved
- Current: "{latest decision text}" — *{meeting title}* ({date})
- Superseded: "{prior decision text}" — *{meeting title}* ({date})
- **Status**: {resolution text}
If the latest decision also carries an authority field (high/medium/low),
surface it next to the title. Authority is optional — when absent, omit the tag.
Stale Commitments
For each stale item, show:
- [ ] **@{who}**: {task} (due {due_date}, {age_days} days overdue)
- Last discussed: *{meeting title}* ({date})
Clean bill of health
If no conflicts and no stale commitments, say: "No decision conflicts or stale commitments found across your meetings. Everything looks consistent."
When to suggest next steps
- If there are decision conflicts: suggest running
/minutes-debriefon the most recent conflicting meeting, or/minutes-search "{topic}"to review the full decision history - If there are stale commitments: suggest the user update the action item status in the meeting file, or bring it up in the next meeting with that person
- Relationship-graph commitments come from
minutes commitments --json; treat a nonzero exit as unavailable, never empty
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 · 77 lines · 61 tokens per session scan A 81e8d4ff47c1
minutes-lint is a skill published in the GitHub repository silverstein/minutes (1,473 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 747 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…