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 LeeYudok/doksam-skills --skill yd-session-recordinggit clone --depth 1 https://github.com/LeeYudok/doksam-skillsWrote 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/leeyudok/doksam-skills/yd-session-recording)<a href="https://agentmods.dev/skills/leeyudok/doksam-skills/yd-session-recording"><img src="https://agentmods.dev/badge/skills/leeyudok/doksam-skills/yd-session-recording/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/leeyudok/doksam-skills/yd-session-recording"><img src="https://agentmods.dev/badge/skills/leeyudok/doksam-skills/yd-session-recording.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 | $0.00117 | $0.03379 |
| Opus 5.5 | $0.00047 | $0.01352 |
| Sonnet 5.5 | $0.00023 | $0.00676 |
| Haiku 4.5 | $0.00012 | $0.00338 |
Grade A, and why
yd-session-recording 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 20d 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.
This is a copy
100% identical to yd-session-recording — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
세션 실시간 녹음·요약 (강의·회의·교육)
whisper-stream으로 마이크 입력을 실시간 전사하고, ffmpeg로 오디오 원본(session.m4a)을 병행 저장하며, 10분 간격 루프로 누적 요약과 질문 후보를 갱신한다. 회차 산출물은 전부 작업 디렉터리 아래 session-<YYYY-MM-DD_HHMM>/ 안에 모은다 (기존 자료가 lecture-<날짜>/ 관례를 쓰는 레포면 그 관례를 따른다).
전제 조건
whisper-stream바이너리(whisper.cpp의 stream 예제)와 한국어 지원 모델이 설치돼 있어야 한다. 시작 전에 한 번 확인하고, 없으면 사용자에게 설치 여부를 먼저 묻는다 — 임의로 대용량 모델을 다운로드하지 않는다.- 바이너리:
command -v whisper-stream(macOS는brew install whisper-cpp계열로 설치 가능) - 세 도구를 한 번에 점검하는 명령:
python3 <스킬경로>/scripts/session_ctl.py check-tools. whisper-stream 이나 모델이 없으면 exit 1 이다. ffmpeg 만 없으면 exit 0 으로 두고 전사만 진행하라고 안내한다. - 모델:
~/models/whisper/ggml-large-v3-turbo.bin(기본 가정 경로 — 다르면 사용자에게 확인)
- 바이너리:
- 오디오 원본 저장에는
ffmpeg가 필요하다 (command -v ffmpeg, macOS 는brew install ffmpeg). 없으면 사용자에게 설치 여부를 묻고, 설치를 원치 않으면 전사만으로 진행한다 — 오디오 저장이 없으면 부정확한 구간을 재청취·재전사할 수 없다는 점을 한 줄 알린다. - 용어집(glossary) — 고유명사 오인식을 줄이는 2층 사전 구조를 쓴다:
- 스킬 내장 공용 사전:
resources/glossary.d/00-common-it.txt(도메인 무관 IT 용어. 프로젝트·회사 고유명사를 여기에 커밋하지 않는다 — 공개 레포다) - 로컬 사전:
~/.config/session-recording/glossary.d/*.txt(개인 전역) 와 작업 디렉터리의glossary.txt(프로젝트별). 둘 다 없으면 "용어집 없이 시작할까요?" 를 한 번 묻는다. - 형식은 한 줄 한 항목
정식표기 | 오인식1, 오인식2 | 비고('#' 줄과 빈 줄 무시).
- 스킬 내장 공용 사전:
- 이미 설치돼 있으면 재설치·재다운로드하지 않는다.
트리거
| 사용자 발화 | 동작 |
|---|---|
녹음시작, 녹음 시작, 강의 녹음 시작, 회의 녹음 시작, 전사 시작 |
아래 시작 절차 실행 |
녹음종료, 녹음 끝, 강의 끝, 회의 끝 |
아래 종료 절차 실행 |
지금까지 요약, 중간 요약 |
루프 회차 1회를 수동 실행 |
시작 절차
-
세션(강의·회의) 제목·주제를 한 줄 묻는다. 요약 헤더와 교정 프롬프트의 도메인 맥락으로 쓴다. 이미 대화에서 알 수 있으면 묻지 않는다.
-
회차 디렉터리 생성, 입력 볼륨 설정, whisper-stream 기동 순서다 (프로젝트 루트 기준).
session_ctl.py가 디렉터리 이름 짓기, 용어집 병합, PID 기록을 맡는다:CTL="python3 <스킬경로>/scripts/session_ctl.py" SESSION=$($CTL new .) # session-<YYYY-MM-DD_HHMM>, 같은 분에 또 만들면 -2 를 붙인다 osascript -e 'set volume input volume 70' # macOS # 용어집 병합 → 정식표기만 뽑아 프롬프트로 (내장 공용 + 로컬 전역 + 프로젝트) $CTL run "$SESSION" whisper -- whisper-stream \ -m ~/models/whisper/ggml-large-v3-turbo.bin \ -l ko -t 8 --step 3000 --length 10000 \ --prompt "다음 용어가 등장하는 회의: $($CTL glossary)" \ -f transcript.txt
What ships with it
4 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.
- 20d ago First seen · 143 lines · 117 tokens per session scan A 0a1bf6538210
yd-session-recording is a skill published in the GitHub repository LeeYudok/doksam-skills (14 stars, last pushed 7d ago), licensed MIT. It adds 117 tokens to every session and 3,379 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to yd-session-recording, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
apify-competitor-intelligence
Analyze competitor strategies, content, pricing, ads, and market positioning across Google Maps, Booking.com, Facebook, Instagram, YouTube, and TikTok.
autonomous-agent-patterns
Design patterns for building autonomous coding agents, inspired by Cline and OpenAI Codex.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".
deployment-engineer
Expert deployment engineer specializing in modern CI/CD pipelines, GitOps workflows, and advanced deployment automation. Masters GitHub Actions, ArgoCD/Flux, progressive delivery, container security, and platform engineering. Handles zero-downtime deployments, security scanning, and developer experience optimization.…
haskell-pro
Expert Haskell engineer specializing in advanced type systems, pure functional design, and high-reliability software. Use PROACTIVELY for type-level programming, concurrency, and architecture guidance.