send-to-remarkable

send-to-remarkable is a skill for Claude Code from wavyrai/rm-mcp. It costs 64 tokens per session (419 once invoked), scanned A, original, MIT.

A workflow for sending a PDF, EPUB, Markdown file, web document or written text to a reMarkable tablet. It can place the item in a named folder, creating missing folders when needed.

In plain words
What is it for?
It helps put articles, ebooks, local files, summaries, reading lists, meeting notes and checklists on a reMarkable for reading or handwriting.
Why use it?
It removes the manual steps of converting reading material or notes into a tablet-friendly file and uploading it. It also makes the destination and source explicit before an irreversible send.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the remarkable plugin — 3 skills, 1 MCP server shipped together

Good fit It helps put articles, ebooks, local files, summaries, reading lists, meeting notes and checklists on a reMarkable for reading or handwriting.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wavyrai/rm-mcp/send-to-remarkable
Install

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.

Any agent
npx skills add wavyrai/rm-mcp --skill send-to-remarkable
Clone the repo
git clone --depth 1 https://github.com/wavyrai/rm-mcp

Made for: Claude Code.

Or install remarkable, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote 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.

agentmods badge for send-to-remarkable

README.md
[![agentmods](https://agentmods.dev/badge/skills/wavyrai/rm-mcp/send-to-remarkable/github.svg)](https://agentmods.dev/skills/wavyrai/rm-mcp/send-to-remarkable)
Your own site
<a href="https://agentmods.dev/skills/wavyrai/rm-mcp/send-to-remarkable"><img src="https://agentmods.dev/badge/skills/wavyrai/rm-mcp/send-to-remarkable/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.

agentmods 80×15 button for send-to-remarkable

Your own site · 80×15
<a href="https://agentmods.dev/skills/wavyrai/rm-mcp/send-to-remarkable"><img src="https://agentmods.dev/badge/skills/wavyrai/rm-mcp/send-to-remarkable.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 419 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.00419
Opus 5.5 $0.00026 $0.00168
Sonnet 5.5 $0.00013 $0.00084
Haiku 4.5 $0.00006 $0.00042

Measured 8d ago against content hash c4eeb58bbfef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

send-to-remarkable 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.

plugin/skills/send-to-remarkable/SKILL.md · 18 lines

What it actually says

Send something to the reMarkable

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. If it reports read-only mode, say so and stop: writes are switched off on purpose.

  1. Work out the source.
    • A file path ending in .pdf, .epub or .md: pass the path.
    • An http(s) URL to a PDF or EPUB: pass the URL (public hosts only, up to 100 MB).
    • Anything else to read on the tablet (a summary you write, notes, a checklist): write it as Markdown with a # Title first line and pass the Markdown text. It is typeset into a PDF sized for the tablet.
  2. Pick the folder. Use the folder the user names (/Reading, Inbox). A path without a leading / goes under the default write folder that remarkable_status shows. Missing folders are created. If the user named no folder, use the default and say where it went.
  3. Confirm when it isn't obvious. A send cannot be undone (undo would mean deleting, which rm-mcp never does). If the user didn't clearly ask to send this exact thing, show the title, source and folder and ask first.
  4. Send. remarkable_send(source=<source>, folder=<folder>, title=<optional title>).
  5. Report the name, folder and page count from the result, and that it appears on the tablet after it syncs.
Changes

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.

  1. 8d ago First seen · 18 lines · 64 tokens per session scan A c4eeb58bbfef

Subscribe to this mod's changes

send-to-remarkable is a skill published in the GitHub repository wavyrai/rm-mcp (22 stars, last pushed 8d ago), licensed MIT. It adds 64 tokens to every session and 419 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.

Related

send-to-remarkable compared with skills from other repositories

send-to-remarkable next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
send-to-remarkablewavyrai/rm-mcpSkill228d agoMITA64Claude Code
n8n-binary-and-dataczlonkowski/n8n-mcpSkill23ktodayMITA135Claude Code, Codex
markdown-to-pdfstaskh/trading_skillsSkill415yesterdayMITA45Claude Code
remarkableSamMorrowDrums/remarkable-mcpSkill2666d agoMITA91Claude Code, Codex
kamiEliasOulkadi/shokuninSkill1121mo agoMITA0Claude Code, Codex
kagenEliasOulkadi/shokuninSkill1121mo agoMITA0Claude Code, Codex
pdf-guideAI-Riksarkivet/ra-mcpSkill272d agoApache-2.0A67Claude Code