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-mcp-recallgit 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-mcp-recall)<a href="https://agentmods.dev/skills/silverstein/minutes/minutes-mcp-recall"><img src="https://agentmods.dev/badge/skills/silverstein/minutes/minutes-mcp-recall/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-mcp-recall"><img src="https://agentmods.dev/badge/skills/silverstein/minutes/minutes-mcp-recall.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 | $0.00018 | $0.00549 |
| Opus 5.5 | $0.00007 | $0.00220 |
| Sonnet 5.5 | $0.00004 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
minutes-mcp-recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Path
Before running helper scripts or opening bundled references, set:
export MINUTES_SKILLS_ROOT="$(git rev-parse --show-toplevel)/.agents/skills/minutes"
export MINUTES_SKILL_ROOT="$MINUTES_SKILLS_ROOT/minutes-mcp-recall"
/minutes-mcp-recall
Route a meeting-memory question to the smallest useful Minutes MCP tool. This
skill is tool-name-oriented for MCP hosts such as OpenClaw, Hermes-agent, and
other MCP clients. Use minutes-search instead when the host only has CLI or
shell access.
Read the complete tool map only when the decision table does not cover the request.
Decision table
| User is asking... | Call |
|---|---|
| "What did we say about X?" or "Find that meeting about Y." | search_meetings |
| "What is the full transcript of this specific meeting?" | get_meeting after finding its id or date with list_meetings or search_meetings |
| About what is happening right now, mid-call | read_live_transcript with a cursor or time window |
| "What do I still owe?" or "Who owes me?" | track_commitments |
| "What is my history with this person?" | get_person_profile or relationship_map |
| "Have I contradicted myself?" or "Which decisions are stale?" | consistency_report |
| Broad research across many meetings | research_topic |
Tool-name prefix by host
- OpenClaw and generic MCP clients use bare tool names such as
search_meetings. - Hermes-agent prefixes each tool with
mcp_minutes_, sosearch_meetingsbecomesmcp_minutes_search_meetings.
Apply the same prefix rule to every tool in the decision table and tool map.
Anti-patterns
- Do not call
get_meetingspeculatively to browse. It returns a full transcript. Usesearch_meetingsorlist_meetingsfirst to find the right id or date and preserve context budget. - Do not call
read_live_transcriptwithout a cursor after one is available. Replaying the whole transcript wastes tokens and duplicates content already in context. - Do not use capture, dictation, processing, annotation, or speaker-mutation tools for a recall question.
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.
- 1mo ago First seen · 57 lines · 18 tokens per session scan A 2ccfc58c3bed
minutes-mcp-recall is a skill published in the GitHub repository silverstein/minutes (1,557 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 549 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
Migrate
Intakes external content, classifies chunks against LifeOS taxonomy, commits with provenance. Sources: .md/.txt, stdin, LifeOS dirs, CLAUDE.md/Cursor/OpenAI Custom Instructions, Obsidian/Notion/Apple Notes exports. MigrateScan classifies → routing table. MigrateApprove with…
wiki-dashboard
Create dynamic, queryable Obsidian dashboard views using Bases or Dataview. Use for auto-updating tables, indexes, or structured views of vault content; not for ordinary question answering.
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…
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.