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 Caprista/KarvyLoop --skill meeting-notesgit clone --depth 1 https://github.com/Caprista/KarvyLoopWrote 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/caprista/karvyloop/meeting-notes)<a href="https://agentmods.dev/skills/caprista/karvyloop/meeting-notes"><img src="https://agentmods.dev/badge/skills/caprista/karvyloop/meeting-notes/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/caprista/karvyloop/meeting-notes"><img src="https://agentmods.dev/badge/skills/caprista/karvyloop/meeting-notes.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00114 | $0.01521 |
| Opus 5.5 | $0.00046 | $0.00608 |
| Sonnet 5.5 | $0.00023 | $0.00304 |
| Haiku 4.5 | $0.00011 | $0.00152 |
Grade A, and why
meeting-notes 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Notes (system template)
Minutes are written for the people who weren't there — and for everyone, two weeks later, arguing about what was decided. So the unit of value is not a summary of what was said; it is an auditable record of what was decided, what will be done, and what is still open. This skill is a method, not a canned answer.
Honest input contract: this skill consumes text — a transcript exported
from your meeting tool (Tencent Meeting, Feishu Minutes, Otter, Teams…) or
whatever notes you pasted. Audio recordings (mp3/wav/m4a) are supported only
via the optional local-ASR extra (pip install "karvyloop[asr]", built on
faster-whisper): the recording is transcribed on this machine — nothing is
uploaded, and the first use downloads a speech model — then the text enters
this same pipeline. Without that extra installed, audio is declined honestly;
pretending to have heard a recording would produce fabricated minutes.
The accountability rule
You (atom) answer to the role; the role answers to the human. A minute that states a decision nobody made — or silently expands a term you didn't actually understand — is worse than a gap marked "unconfirmed". When in doubt, record the uncertainty, never a confident invention.
The three-bucket rule (keep them separate, always)
Standard team-practice pattern (see e.g. Atlassian Team Playbook's meeting notes guidance):
- Decisions — what was settled, who settled it, and the stated basis. No owner-of-the-decision identifiable? It goes to bucket 3, not here.
- Action items — three required elements: who / what / by-when. Any element missing → the item is recorded but flagged "needs confirmation" (an action item without an owner is a wish, not a task).
- Open questions / needs confirmation — everything raised but not settled, plus every flag from the rules above. This bucket being visible is a feature: it is the next meeting's agenda.
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 · 107 lines · 114 tokens per session scan A 1be327c950e4
meeting-notes is a skill published in the GitHub repository Caprista/KarvyLoop (17 stars, last pushed 23d ago), licensed MIT. It adds 114 tokens to every session and 1,521 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A single-page template for helping a new employee understand their first week at work. It includes a five-day schedule, manager and buddy details, learning tasks, equipment, and completion outcomes.
wecom
An administration tool for WeCom, Tencent's workplace messaging platform, including its company department tree and app messages.
checkin
A chat-based tool for checking sign-in points and streaks, and viewing a group's points ranking. Points are rewards recorded by the service, while daily sign-in itself is handled by a separate chat command.
reminder
A personal reminder tool for the current chat. It can create, list, and cancel reminders that send a message back to this conversation.
workflow-interaction
A guide for exploring and operating real web pages and desktop applications. It describes how to locate the correct window or page, inspect available controls, and confirm that an action succeeded.
daily-context
A date and time lookup skill for the current date, time, and day of the week. It uses the Asia/Shanghai time zone and identifies that time zone in the reply.