advisory-minutes

advisory-minutes is a skill for Claude Code from bam-bam-2/solo-skills. It costs 118 tokens per session (1,709 once invoked), scanned A, original, MIT.

A workflow for turning Zoom transcripts from one-to-one advisory sessions into client coaching records in Notion. It also registers follow-up tasks, updates dashboard text, and can notify the client by messenger.

In plain words
What is it for?
Use it after an advisory session to fetch the transcript, create or update the correct Notion page, add action items, and prepare or send a client notification. It requires Zoom and Notion access, and asks for confirmation before sending messages.
Why use it?
It removes the need to copy meeting notes between Zoom, Notion, task boards, and messaging. It also separates client-facing information from private discussion before publishing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the solo-skills plugin — 39 skills shipped together

Good fit Use it after an advisory session to fetch the transcript, create or update the correct Notion page, add action items, and prepare or send a client notification. It requires Zoom and Notion access, and asks for confirmation before sending messages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bam-bam-2/solo-skills/advisory-minutes
Install

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.

Any agent
npx skills add bam-bam-2/solo-skills --skill advisory-minutes
Clone the repo
git clone --depth 1 https://github.com/bam-bam-2/solo-skills

Made for: Claude Code.

Or install solo-skills, the plugin that ships this one along with the rest of its 39 skills.

Wrote 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.

agentmods badge for advisory-minutes

README.md
[![agentmods](https://agentmods.dev/badge/skills/bam-bam-2/solo-skills/advisory-minutes/github.svg)](https://agentmods.dev/skills/bam-bam-2/solo-skills/advisory-minutes)
Your own site
<a href="https://agentmods.dev/skills/bam-bam-2/solo-skills/advisory-minutes"><img src="https://agentmods.dev/badge/skills/bam-bam-2/solo-skills/advisory-minutes/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.

agentmods 80×15 button for advisory-minutes

Your own site · 80×15
<a href="https://agentmods.dev/skills/bam-bam-2/solo-skills/advisory-minutes"><img src="https://agentmods.dev/badge/skills/bam-bam-2/solo-skills/advisory-minutes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,709 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00118 $0.01709
Opus 5.5 $0.00047 $0.00684
Sonnet 5.5 $0.00024 $0.00342
Haiku 4.5 $0.00012 $0.00171

Measured 1mo ago against content hash ef93ee61ba2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

advisory-minutes scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

→ 응답의 download_access_token 을 download_url 뒤에 ?access_token=... 로 붙여서 curl -L
skills/advisory-minutes/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

이 스킬이 시스템에 하는 일 (설치 전 확인)

  • 전사록을 읽어 노션 페이지를 생성·수정합니다. 노션 API 키가 필요합니다.
  • 클라이언트에게 메신저 통보를 보내는 단계가 있습니다. 기본값은 발송 전 확인입니다.
  • DB ID는 플레이스홀더입니다. 본인 워크스페이스 값으로 바꿔야 합니다.

자문 회의록 파이프라인

밤밤의 1:1 자문 세션은 줌으로 하고, 기록 정본은 노션 클라이언트별 코칭 대시보드다. 세션이 끝나면 이 순서로 처리한다.

0. 먼저 읽을 것

  • ~/Projects/getback/자문/CLAUDE.md — 노션 ID 표, 대시보드 규칙, 톤, 회차 산정 기준(계약 회차 기준이며 로컬 파일명의 "N차미팅"과 다르다)
  • 직전 회차 회의록 페이지 — 형식을 그대로 잇는다

⚠️ 대시보드는 클라이언트에게 공유되는 페이지다. 밤밤이 전달을 지시·승인한 것만 올린다. 밤밤의 내부 판단(수임료, 클라이언트 소속 병원과의 관계, 경쟁자 실명 해부, 협찬 부탁 같은 사담)은 회의록에서 걷어낸다.

1. 줌 전사록 받기

~/Projects/getback/운영/pipeline/.env의 ZOOM_ACCOUNT_ID / ZOOM_CLIENT_ID / ZOOM_CLIENT_SECRET(S2S OAuth).

POST https://zoom.us/oauth/token   grant_type=account_credentials&account_id=...
     Authorization: Basic base64(client_id:client_secret)
GET  https://api.zoom.us/v2/users/me/recordings?from=YYYY-MM-DD&to=YYYY-MM-DD

⚠️ 가장 큰 함정 — 다운로드는 액세스 토큰이 따로다. download_url에 일반 Bearer 토큰을 붙이면 401 {"errorCode":124,"Forbidden"}이 난다. 반드시:

GET https://api.zoom.us/v2/meetings/{URL인코딩된 uuid}/recordings?include_fields=download_access_token&ttl=3600
→ 응답의 download_access_token 을 download_url 뒤에 ?access_token=... 로 붙여서 curl -L
  • 계정 표시명이 **"레코드 나우"**라 회의 제목만으로는 누구와 한 세션인지 알 수 없다. 전사록의 화자 이름으로 확인한다.
  • start_time은 UTC다. 한국 시각은 +9 — 밤 늦게 시작한 세션은 날짜가 하루 넘어간다(밤밤 자문은 자정 넘겨 시작하는 경우가 잦다). 회의록 날짜는 실제 시작 시각 기준으로 적고, 밤밤에게 한 줄로 알린다.
  • VTT는 화자별로 잘게 쪼개져 있으니 같은 화자 연속 발화를 합쳐서 읽는다(96KB → 26KB로 줄어든다).
  • 전사 품질 주의: 고유명사·숫자가 자주 깨진다. 숫자·비율은 회의록에 옮기기 전에 의심하고, 애매하면 밤밤에게 확인한다.
  • 원본은 로컬 ~/Projects/getback/자문/클라이언트/{이름}/YYYY-MM-DD_N차미팅_전사록.txt|.vtt로 저장한다.

2. 회의록 작성

클라이언트/{이름}/에 세션 노트 md를 먼저 쓰고(정본 소스), 그걸 노션에 올린다. 고정 형식:

> 📌 일시 YYYY.MM.DD(요일) HH:MM · 약 N분  |  참석 밤밤(자문) · {클라이언트}  |  주제 ... (N회차)
> 🎯 한 줄 결론 — ...
## 🎯 핵심 결론      (quote 한 문단)
## 🔑 핵심 논의 흐름  (굵은 소제목 + 불릿, 중요한 건 ⭐)
## ✅ 결정사항        (번호 목록)
## 📌 액션 아이템     (체크박스, (예지)/(밤밤) 담당 표기)
## 🗓️ 다음 단계

톤은 프리미엄 존댓말(밤밤 캐주얼 SNS체 아님). 밤밤의 발언을 클라이언트가 읽을 문장으로 다시 쓴다.

Read the full file on GitHub · 88 lines

Changes

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.

  1. 1mo ago First seen · 88 lines · 118 tokens per session scan A ef93ee61ba2e

Subscribe to this mod's changes

advisory-minutes is a skill published in the GitHub repository bam-bam-2/solo-skills (366 stars, last pushed 3d ago), licensed MIT. It adds 118 tokens to every session and 1,709 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.