Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bam-bam-2/solo-skillsnpx agentmods add skills/bam-bam-2/solo-skills/meeting-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/bam-bam-2/solo-skills/meeting-minutes)<a href="https://agentmods.dev/skills/bam-bam-2/solo-skills/meeting-minutes"><img src="https://agentmods.dev/badge/skills/bam-bam-2/solo-skills/meeting-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.
<a href="https://agentmods.dev/skills/bam-bam-2/solo-skills/meeting-minutes"><img src="https://agentmods.dev/badge/skills/bam-bam-2/solo-skills/meeting-minutes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 19 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 67 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 20 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Rogue Agent · line 61 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 68 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- low Supply Chain · line 20 Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
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 | $0.00038 | $0.04802 |
| Opus 5 | $0.00019 | $0.02401 |
| Sonnet 5 | $0.00008 | $0.00960 |
| Haiku 4.5 | $0.00004 | $0.00480 |
Grade A, and why
meeting-minutes scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
CH=$(curl -s -X POST -H "Authorization: Bot $TOKEN" -H "Content-Type: application/json" \ How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
프로젝트 회의록 발행
디스코드 음성 회의 → 전사본 수신 → 회의록 작성 → 노션 등록 → 디스코드 공지까지의 정본 절차.
프로젝트 개요·인물·일정은 볼트 프로젝트/프로젝트.md 참조.
작업 폴더: ~/Projects/<프로젝트>/이벤트/버추얼 프로젝트
1. 전사본 받기
프로젝트 조사봇이 회의 종료 후 사용자 DM으로 transcript.md를 보낸다.
cd "~/Projects/<프로젝트>/이벤트/버추얼 프로젝트"
TOKEN=$(grep '^프로젝트_DISCORD_BOT_TOKEN=' .env | cut -d= -f2-)
CH=$(curl -s -X POST -H "Authorization: Bot $TOKEN" -H "Content-Type: application/json" \
-H "User-Agent: DiscordBot (https://github.com/bambam/twc-pm, 1.0)" \
-d '{"recipient_id":"483902030243692546"}' \
"https://discord.com/api/v10/users/@me/channels" \
| python3 -c "import json,sys;print(json.load(sys.stdin)['id'])")
bash scripts/twc-dm-download-transcripts.sh "$CH" "회의록 전사/_dm받은전사" 5
원본은 원격 머신 ~/Projects/<프로젝트>/recordings/<ISO시각>_1515265088167346317/ 에도 있다.
저장되는 건 발화자별 음성(.ogg/.pcm)과 transcript.md뿐 — 화면 영상은 없다.
받자마자 유실 여부를 확인한다 (2026-08-18 사고 후)
전사본을 열어 "(전사된 발언이 없습니다)"이거나 발화수가 비정상으로 적으면 보령을 본다.
ssh remote-host 'grep -E "녹음 시작|디코더 오류|전사 완료" ~/Projects/<프로젝트>/logs/bot.log | tail -20'
디코더 오류 <userId> The compressed data passed is corrupted 가 보이면 그 사람은 그 시점 이후 녹음이 안 된 것이다.
녹음 시작 직후(수 ms 내)에 뜨면 그 참석자 발언은 회의 전체가 없다. 봇이 들어올 때 이미 말하고 있던 사람이 걸린다.
- 원인이던 봇 버그(디코딩 실패 후 재구독 안 함)는 2026-08-19에 수정했고, 이제 발화 0건이거나 음성 0바이트인 참석자가 있으면 DM 상단에 경고 배너가 붙는다.
- 그래도 유실이 생기면 지어내지 말고, 회의록 상단 콜아웃에 "전사 유실 · 무엇을 근거로 썼는지"를 명시하고 참석자에게 DM으로 보완을 요청한다. 사례: 회차 18(8/18).
⚠️ 유실이면 발행보다 사본 요청이 먼저다
봇 녹음이 없다고 기록이 없는 게 아니다. 참석자가 개인 녹취를 갖고 있을 수 있다. 회의 주변 텍스트(디스코드 후속 대화)로 재구성한 문서를 먼저 발행하지 말고, 참석자에게 녹취 유무를 먼저 물어볼 것.
8/18 건은 디스코드 기록만으로 발행했다가 나중에 녹취를 받았는데, 회의 본론이 통째로 빠져 있었다. 주변 텍스트에 남는 건 회의 직후 후속 논의지 회의 그 자체가 아니다. 재구성본을 굳이 내야 한다면 "회의에서 나온 것"과 "회의 후에 오간 것"을 별도 절로 분리해야 나중에 원본이 나왔을 때 무엇이 빠졌는지 바로 보인다.
외부 녹취(mp3)를 받았을 때 전사하는 법
봇과 같은 파이프라인을 손으로 태운다. 무거우니 원격 머신에서 돌린다.
ssh remote-host 'mkdir -p ~/tmp/<이름>'
scp "<mp3>" remote-host:~/tmp/<이름>/raw.mp3
ssh remote-host 'cd ~/tmp/<이름> && /opt/homebrew/bin/ffmpeg -hide_banner -loglevel error -y \
-i raw.mp3 -ac 1 -ar 16000 -c:a libopus -b:a 24k meeting.ogg'
# 42MB mp3 → 5MB ogg. Groq 25MB 제한을 안 넘긴다.
ssh remote-host 'cd ~/tmp/<이름> && KEY=$(grep -h "^GROQ_API_KEY=" ~/.config/watch/.env | cut -d= -f2- | tr -d "\"") && \
curl -s -X POST "https://api.groq.com/openai/v1/audio/transcriptions" \
-H "Authorization: Bearer $KEY" -F "[email protected]" -F "model=whisper-large-v3" \
-F "language=ko" -F "response_format=verbose_json" \
-F "prompt=<고유명사 나열>" -o result.json'
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.
- 12d ago First seen · 280 lines · 38 tokens per session scan A 5393a17863d4
meeting-minutes is a skill published in the GitHub repository bam-bam-2/solo-skills (363 stars, last pushed 9d ago), licensed MIT. It adds 38 tokens to every session and 4,802 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
gws-gmail
Gmail: Send, read, and manage email.
recipe-block-focus-time
Create recurring focus time blocks on Google Calendar to protect deep work hours.
recipe-create-vacation-responder
Enable a Gmail out-of-office auto-reply with a custom message and date range.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.