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 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/session-recording)<a href="https://agentmods.dev/skills/leeyudok/doksam-skills/session-recording"><img src="https://agentmods.dev/badge/skills/leeyudok/doksam-skills/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/session-recording"><img src="https://agentmods.dev/badge/skills/leeyudok/doksam-skills/session-recording.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 42 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.
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 | $0.00116 | $0.03149 |
| Opus 5 | $0.00058 | $0.01574 |
| Sonnet 5 | $0.00023 | $0.00630 |
| Haiku 4.5 | $0.00012 | $0.00315 |
Grade A, and why
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 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.
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 — 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>/ 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) - 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 백그라운드 기동 (프로젝트 루트 기준):
mkdir -p session-$(date +%F) osascript -e 'set volume input volume 70' # macOS # 용어집 병합 → 정식표기만 뽑아 프롬프트로 (내장 공용 + 로컬 전역 + 프로젝트) GLOSSARY=$(cat <스킬경로>/resources/glossary.d/*.txt \ ~/.config/session-recording/glossary.d/*.txt \ ./glossary.txt 2>/dev/null \ | grep -v '^#' | grep -v '^$' | cut -d'|' -f1 | tr '\n' ',' | tr -s ' ') cd session-$(date +%F) && whisper-stream \ -m ~/models/whisper/ggml-large-v3-turbo.bin \ -l ko -t 8 --step 3000 --length 10000 \ --prompt "다음 용어가 등장하는 회의: $GLOSSARY" \ -f transcript.txt
What ships with it
1 file 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.
- 12d ago First seen · 143 lines · 116 tokens per session scan A 9aa7a08e4435
session-recording is a skill published in the GitHub repository LeeYudok/doksam-skills (10 stars, last pushed 20d ago), licensed MIT. It adds 116 tokens to every session and 3,149 once invoked, about $0.0006 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
architecture-decision-records
Comprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and rationale behind significant technical decisions.
aria
Designs the data model, API contracts, and structural foundation of the system.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
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".
conductor-implement
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.