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 wavyrai/rm-mcp --skill transcribe-notebook-to-markdowngit clone --depth 1 https://github.com/wavyrai/rm-mcpWrote 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/wavyrai/rm-mcp/transcribe-notebook-to-markdown)<a href="https://agentmods.dev/skills/wavyrai/rm-mcp/transcribe-notebook-to-markdown"><img src="https://agentmods.dev/badge/skills/wavyrai/rm-mcp/transcribe-notebook-to-markdown/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/wavyrai/rm-mcp/transcribe-notebook-to-markdown"><img src="https://agentmods.dev/badge/skills/wavyrai/rm-mcp/transcribe-notebook-to-markdown.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 | $0.00072 | $0.00665 |
| Opus 5.5 | $0.00029 | $0.00266 |
| Sonnet 5.5 | $0.00014 | $0.00133 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
transcribe-notebook-to-markdown 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 8d 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.
What it actually says
Transcribe a reMarkable notebook to Markdown
You need the remarkable MCP server's tools. If remarkable_status says the user is not signed in, tell them to run uvx rm-mcp@latest setup in a terminal and stop.
-
Find it.
remarkable_find(query="<what the user called it>"). If several match, show the names, paths and modified dates and ask which one. Keep theid. -
Read what is already text.
remarkable_read(id=<id>, pages="all"). It returns typed text, PDF text and saved transcripts per page, and marks pages that carry handwriting without a transcript. For a long notebook, read in ranges (pages="1-20") and follow the returned cursor. -
Transcribe handwriting. For each page marked as handwritten with no transcript, call
remarkable_view(id=<id>, pages="<n>")(up to 4 pages per call; usesize="large"for small writing). Transcribe exactly what is written:- keep the writer's words, line breaks between thoughts, lists and headings;
- write
[?]for a word you can't read, and never guess silently; - describe a drawing or diagram in one italic line, such as
*Sketch: three boxes joined by arrows, labelled A, B, C.*
-
Save each transcript with
remarkable_save_transcript(id=<id>, page=<n>, text=<transcript>)before moving on. This makes the page searchable withremarkable_findand means the next run skips it. It writes only the local index, never the tablet. -
Write the Markdown file where the user asked (default: the current directory, named after the notebook, such as
Meeting notes 2026-11.md). Make it Obsidian-friendly:--- title: <notebook name> source: remarkable remarkable_id: <id> remarkable_path: <path> modified: <modified date from find/read> tags: [remarkable] --- # <notebook name> ## Page 1 <text>- one
## Page Nheading per tablet page (page numbers are tablet pages); - turn
#tagwords the writer used into Obsidian tags as written; - keep
[?]markers so the user can fix them; - if the file exists, ask before overwriting it.
- one
-
Report the file path, the page count, how many pages you transcribed now, and how many
[?]markers are left.
Never send, rename or move anything on the tablet as part of this task.
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.
- 8d ago First seen · 43 lines · 72 tokens per session scan A bcb851b7f627
transcribe-notebook-to-markdown is a skill published in the GitHub repository wavyrai/rm-mcp (22 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 665 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-11.
transcribe-notebook-to-markdown compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| transcribe-notebook-to-markdownwavyrai/rm-mcp | Skill | 22 | 8d ago | MIT | A | 72 | Claude Code |
| n8n-binary-and-dataczlonkowski/n8n-mcp | Skill | 23k | today | MIT | A | 135 | Claude Code, Codex |
| excel-clisbroenne/mcp-server-excel | Skill | 901 | today | MIT | A | 59 | Claude Code, Codex |
| markdown-to-pdfstaskh/trading_skills | Skill | 415 | yesterday | MIT | A | 45 | Claude Code |
| kamiEliasOulkadi/shokunin | Skill | 112 | 1mo ago | MIT | A | 0 | Claude Code, Codex |
| @bilig/exceljs-formula-recalcproompteng/bilig | Skill | 35 | 2d ago | MIT | A | 0 | Claude Code, Codex |
| @bilig/sheetjs-formula-recalcproompteng/bilig | Skill | 35 | 2d ago | MIT | A | 0 | Claude Code, Codex |