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 lukaisailovic/remarkable-mcp --skill remarkable-mcpgit clone --depth 1 https://github.com/lukaisailovic/remarkable-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/lukaisailovic/remarkable-mcp/remarkable-mcp)<a href="https://agentmods.dev/skills/lukaisailovic/remarkable-mcp/remarkable-mcp"><img src="https://agentmods.dev/badge/skills/lukaisailovic/remarkable-mcp/remarkable-mcp/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/lukaisailovic/remarkable-mcp/remarkable-mcp"><img src="https://agentmods.dev/badge/skills/lukaisailovic/remarkable-mcp/remarkable-mcp.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 | $0.00098 | $0.01903 |
| Opus 5 | $0.00049 | $0.00951 |
| Sonnet 5 | $0.00020 | $0.00381 |
| Haiku 4.5 | $0.00010 | $0.00190 |
Grade A, and why
remarkable-mcp 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 9d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
remarkable-mcp
The client exposes one tool: remarkable_execute. Pass a JavaScript async arrow function. Methods live on rme. No TypeScript. No process / require / fetch.
async () => {
const folder = await rme.mkdir({ name: "Projects" });
await rme.createNotebook({ name: "Ideas", parent: folder.id });
await rme.writeText({
notebook: "Ideas",
newPage: true,
blocks: [
{ text: "Ship it", style: "title" },
{ text: "Talk to design", style: "checkbox" },
],
});
return await rme.read({ notebook: "Ideas", page: 2 });
};
Batch related work in one call. Writes apply once after the function returns (SSH restarts xochitl; rmfakecloud commits sync). Do not call refresh() unless you need an extra apply mid-script. Return only what the user asked for.
Resolve
- notebook (also used for folders, PDFs, EPUBs): UUID, unique visible name, or
/Folder/Name. Duplicate names throwambiguous name. - page: 1-based. Write defaults: last page.
exportPagedefaults to page 1. - Ink points:
[x, y]in 0–1 from the top-left. remove= trash (parent: "trash"), not unlink.
Item: { id, name, type, fileType, parent, path, pageCount, tags, lastModified, trashed, page?, pages? }. type is notebook | folder | pdf | epub.
Page writes (writeText / writeInk / writeMermaid / addPage / removePage / exportPage) are for notebooks. PDFs/EPUBs have no ink pages — read extracts text, download returns bytes.
Handwriting is not OCR'd. Typed Type Folio text is in read. Ink is in exportPage.
search matches name/path (optional tag), not page text. To find content, list/browse then read.
Discover
| Call | Args | Returns |
|---|---|---|
rme.list |
{ includeTrash?, folder? } |
Library. Trash hidden unless includeTrash. folder limits to that folder's children. |
rme.browse |
{ path? } |
One folder (default /). A notebook path returns that single item. |
rme.search |
{ query, tag? } |
Name/path substring. tag is an extra filter. |
rme.info |
{ notebook } |
One item. Notebooks include pages[].title (first title/heading, else first line). |
rme.tags |
{} |
Sorted unique tag names on the tablet. |
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.
- 9d ago First seen · 158 lines · 98 tokens per session scan A 685cd9eb0a2c
remarkable-mcp is a skill published in the GitHub repository lukaisailovic/remarkable-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 98 tokens to every session and 1,903 once invoked, about $0.0005 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.