Borrowing it
Nothing to install: this file belongs to Federico-Anastasi/DYLA-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Federico-Anastasi/DYLA-ai/main/.agents/skills/meeting-notes/SKILL.mdgit clone --depth 1 https://github.com/Federico-Anastasi/DYLA-aiWrote 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/federico-anastasi/dyla-ai/meeting-notes)<a href="https://agentmods.dev/skills/federico-anastasi/dyla-ai/meeting-notes"><img src="https://agentmods.dev/badge/skills/federico-anastasi/dyla-ai/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/federico-anastasi/dyla-ai/meeting-notes"><img src="https://agentmods.dev/badge/skills/federico-anastasi/dyla-ai/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 | $0.00043 | $0.02418 |
| Opus 5 | $0.00022 | $0.01209 |
| Sonnet 5 | $0.00009 | $0.00484 |
| Haiku 4.5 | $0.00004 | $0.00242 |
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 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/meeting-notes — From a recording to minutes worth reading
Everyone leaves the meeting agreeing. A week later nobody remembers who was supposed to send the file. This skill closes that gap: it takes what was said and turns it into four things a reader can act on — who was there, what was decided, what is still open, and who does what by when.
It works for any meeting, in any line of work: a project stand-up, a supplier negotiation, a board meeting, a treatment review, a school committee. Nothing here assumes software.
Unlike the rest of Dyla, this skill writes plain markdown, not JSON. There is no schema and no dedicated viewer: minutes are prose, they get read by people, and they get forwarded by email. A file is the right shape for that.
PROTOCOL
- Get the source — a transcript, a recording, or pasted notes
- Read it twice: once for the shape of the meeting, once for the commitments
- Write
meetings/YYYY-MM-DD-title.md - Say in chat what you wrote and, above all, what you could not pin down
- Fix what the user corrects — they were in the room, you were not
PHASE 1 — THE SOURCE
You can be handed:
- a transcript — a
.mdor.txtfile, usually inmeetings/ - a recording — audio uploaded from the Documents menu. The app transcribes it
locally and drops the result in
meetings/. Transcription of a long meeting takes minutes: if a job is still running, say so and wait rather than working from a partial file - notes pasted into chat — rough, half-written, out of order. Perfectly usable
If none of these exist, ask for one in a ```questions block (format in
.Codex/prompts/questions_format.md):
```questions
[
{
"id": 1,
"q": "I don't have a transcript, recording or notes for this meeting yet. How do you want to provide it?",
"options": ["I'll upload the recording or transcript from the Documents menu"],
"hint": "or paste the notes directly here"
}
]
```
Do not write minutes from the project documents: minutes record what was said in a room, and inventing that is the one unforgivable failure of this skill.
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 · 221 lines · 43 tokens per session scan A 6dfca80450fb
meeting-notes is a skill published in the GitHub repository Federico-Anastasi/DYLA-ai (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 2,418 once invoked, about $0.0002 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
jentic
Use this skill whenever the user wants to work with a third-party or external API/tool through the Jentic platform — e.g. asks to "find the vessel-tracking API and add it", "get rows from this Google Sheet", connect Slack, import/search/discover an API, integrate or automate a SaaS, pull data from a service, or call…
contribute-spec-fix
Fix a broken OpenAPI spec in jentic-public-apis with an OpenAPI Overlay, validate it (spectral lint + idempotency check), and contribute it back via a PR to the community catalog. Falls back to applying the same overlay to the local Jentic registry if the user can't wait for maintainer approval, and closes the loop by…
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
fabrik-review
Use when operating as the Fabrik Review stage agent. This skill guides code review of an implementation, finding and fixing issues, and ensuring the PR is ready for human review.
fabrik-implement
Use when operating as the Fabrik Implement stage agent. This skill guides the implementation of a planned feature, following the task checklist to produce committed, tested, pushed code on a feature branch.
clarify
Finds the vague and missing parts of an existing feature specification and fixes them by asking up to five targeted questions, one at a time, writing each answer back into the spec as it is answered. Follows GitHub Spec Kit's clarify workflow. Use this when someone wants to review, tighten, sharpen, sanity-check, poke…