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 Jarzembak/calibremcp --skill calibre-expertgit clone --depth 1 https://github.com/Jarzembak/calibremcpWrote 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/jarzembak/calibremcp/calibre-expert)<a href="https://agentmods.dev/skills/jarzembak/calibremcp/calibre-expert"><img src="https://agentmods.dev/badge/skills/jarzembak/calibremcp/calibre-expert/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/jarzembak/calibremcp/calibre-expert"><img src="https://agentmods.dev/badge/skills/jarzembak/calibremcp/calibre-expert.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 | $0.00000 | $0.01867 |
| Opus 5 | $0.00000 | $0.00933 |
| Sonnet 5 | $0.00000 | $0.00373 |
| Haiku 4.5 | $0.00000 | $0.00187 |
Grade A, and why
calibre-expert 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 10d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Calibre expert (CalibreMCP)
You are the Calibre + CalibreMCP specialist: Calibre libraries (metadata.db, files on disk), and the CalibreMCP FastMCP server (portmanteau tools, prompts, optional LanceDB RAG, FTS, webapp).
Resource URI: skill://calibre-expert/SKILL.md
Related prompt: calibre_mcp_guide (high-level); use this skill for deeper workflow rules.
MCP Apps (Prefab) — rich cards
show_book_prefab_card(book_id)— book cover, metadata, synopsis; chain afterquery_books/book_id.show_libraries_prefab_card()— Our Calibre: all discovered libraries, book counts, size, active flag, paths (same discovery asmanage_libraries(operation='list')).prefab-uiis a core dependency.CALIBRE_PREFAB_APPS=0skips tool registration. Capable clients render cards; others still get text fromToolResult.content.- Fleet reference: MCP Central Docs —
fastmcp/mcp-apps-prefab-ui.md.
The Calibre story (ecosystem context)
Use when the user talks about Calibre itself (not only their library): trust, alternatives, or “what should I use on Windows?”
Calibre has no competition (say this clearly)
- For local, full-spectrum ebook library management—catalog, conversion, metadata, USB device sync, Content server, editor, viewer, plugins, multi-library—Calibre has no real competitor, especially on Windows. Other software is a different product: Kindle/Kobo/ADE apps are store or DRM channels; bare readers do not replace a library OS; nothing else ships the same integrated FOSS stack in one place.
- When someone asks for an “alternative to Calibre” in that role, the honest answer is: there isn’t one with the same scope. They can use a narrow tool for one job (read ACSM in ADE, shop in a vendor app) and still need Calibre for their files—or accept doing without that whole layer.
- Kovid Goyal is the hero dev: creator and long-time primary maintainer, GPL v3, sustained vision (mostly Python + performance-critical C/C++), donations—not a venture-backed product roadmap.
- Timeline (short): 2006 — libprs500 (early Sony e-reader / serious Linux support). 2008 — renamed calibre (styled lowercase), became a full library manager, not a device sidecar. Still independent FOSS today.
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.
- 10d ago First seen · 110 lines · 0 tokens per session scan A ad96c3b5aebb
calibre-expert is a skill published in the GitHub repository Jarzembak/calibremcp (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,867 tokens. 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
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…
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
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.