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 regen-coordination/org-os-template --skill meeting-processorgit clone --depth 1 https://github.com/regen-coordination/org-os-templateWrote 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/regen-coordination/org-os-template/meeting-processor)<a href="https://agentmods.dev/skills/regen-coordination/org-os-template/meeting-processor"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/meeting-processor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00023 | $0.01275 |
| Opus 5 | $0.00012 | $0.00638 |
| Sonnet 5 | $0.00005 | $0.00255 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
meeting-processor 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 6d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Processor
What This Is
Processes meeting transcripts (from Granola, Google Meet, Otter.ai, Zoom, or manual notes) into structured meeting notes following Organizational OS conventions. Extracts action items, updates project pages, and writes entries to organizational memory.
This skill can also be used to process meeting records from a Notion Notes & Documents data source into local structured artifacts (instance-specific — see the customization note below).
When to Use
- When you receive a raw meeting transcript or recording
- When someone pastes meeting notes to be formatted and filed
- When asked to "process", "clean up", or "file" meeting notes
- After a meeting: "can you take these notes and process them?"
When NOT to Use
- For informal chat logs → use knowledge-curator instead
- For async decisions (no meeting) → write directly to project page
- For very short exchanges (< 5 min) → add directly to memory
Recommended pre-processor: meeting-notes-transcription-fixer
If raw notes contain transcription errors (misheard proper nouns, acronyms, project names that recur in your org), run meeting-notes-transcription-fixer first to normalize the corpus, then run this skill. The transcription-fixer maintains per-instance dictionaries of recurring corrections; meeting-processor consumes already-clean text.
Instance customization point. If your instance uses Notion as the source of meeting records, add your org's root page / data source IDs and any record-prioritization rules here (see
docs/OPERATOR-GUIDE.md).
Usage
Step 1: Receive Input
Accept any of:
- Raw transcript text (paste or file)
- Pre-formatted notes to standardize
- File path to a transcript file
Step 2: Extract Structure
From the transcript, identify:
- Date: Look for explicit date, or infer from "today", "this morning", etc.
- Participants: Speaker labels, names mentioned in greetings, @mentions
- Key decisions: "we decided", "agreed to", "confirmed", "going with", "approved", "final call"
- Action items: "will [do X]", "[Name] to [do X]", "by [date]", "- [ ]", "next step", "follow up"
- Main topics: What were the major themes discussed?
- Related projects: Which projects were discussed? (cross-reference
data/projects.yaml) - Next steps / follow-ups: Anything time-bound or explicitly mentioned as next
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.
- 6d ago First seen · 158 lines · 23 tokens per session scan A e8f02a7bdd9d
meeting-processor is a skill published in the GitHub repository regen-coordination/org-os-template (5 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,275 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
gsd-mempalace-capture
File a phase artifact into MemPalace; mirror decision facts into its temporal KG.
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
after-action-report
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event.…