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 agentmods add skills/youngjaedev/my-claude-plugins/plaud-note-takingnpx skills add YoungjaeDev/my-claude-plugins --skill plaud-note-takinggit clone --depth 1 https://github.com/YoungjaeDev/my-claude-pluginsWrote 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/youngjaedev/my-claude-plugins/plaud-note-taking)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/plaud-note-taking"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/plaud-note-taking.svg" alt="Measured on agentmods" 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 | $0.00123 | $0.04006 |
| Opus 5 | $0.00062 | $0.02003 |
| Sonnet 5 | $0.00025 | $0.00801 |
| Haiku 4.5 | $0.00012 | $0.00401 |
Grade A, and why
plaud-note-taking 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 yesterday.
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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PLAUD Note Review & Correction
Cross-runtime interactive input
Every question below runs through a capability-aware interactive-input gate rather than one
hardcoded tool. Read each AskUserQuestion mention as this gate:
- Claude Code: use
AskUserQuestion. - Codex: use
request_user_inputwhen that tool is exposed. When it is not, ask ONE concise blocking question only where a wrong assumption would be costly; otherwise proceed on a documented safe default and state the assumption.
Full policy: AGENTS.md → "Cross-runtime interactive input policy".
The step-6 approval gate is the one place where no safe default exists: an unapproved corrected file must never be distilled or ingested. Where no interactive tool is exposed, stop and report the corrected file instead of continuing past it.
When to use
- A PLAUD note (transcript, or transcript + summary) has been placed in
.llmwiki/raw/transcripts/and needs cleaning before it is usable. - "이 회의록 정정해줘", "plaud 전사 STT 고쳐줘", "전사록 오탈자·용어 맞춰줘", "correct this PLAUD transcript".
What a PLAUD note is (read first)
Read references/plaud-note-format.md before touching content. Two facts drive everything:
- A PLAUD note is two separate artifacts. The transcript is raw single-language Whisper STT output (speaker-labeled). The summary/note is a separate LLM pass over that transcript. They are generated and stored independently.
- The transcript is ground truth; the summary is not. The summary reads fluently even when it silently invents a decision that was never made. Correct against the transcript and audio, never against the summary. Where the summary asserts something the transcript does not support, that is a flag, not a fact.
Role and scope
This skill corrects a transcript conservatively and writes new files beside the frozen
originals. It never edits the uploaded originals. It sorts every span into four states (see
references/correction-policy.md), tagged inline in the corrected file:
What ships with it
5 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.
- yesterday First seen · 252 lines · 123 tokens per session scan A 1b5d981adb1f
plaud-note-taking is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 123 tokens to every session and 4,006 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 2026-09-05.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…