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 sandraschi/calibremcp --skill reading_recommendationsgit clone --depth 1 https://github.com/sandraschi/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/sandraschi/calibremcp/reading_recommendations)<a href="https://agentmods.dev/skills/sandraschi/calibremcp/reading_recommendations"><img src="https://agentmods.dev/badge/skills/sandraschi/calibremcp/reading_recommendations/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/sandraschi/calibremcp/reading_recommendations"><img src="https://agentmods.dev/badge/skills/sandraschi/calibremcp/reading_recommendations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00481 |
| Opus 5 | $0.00000 | $0.00241 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
reading_recommendations 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- reading_recommendations — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading Recommendations
Description: Get personalized reading recommendations from your Calibre library using series progress, ratings, tags, reading history, and collaborative filtering across similar books.
Trigger Phrases
- "What should I read next?"
- "Recommend a book like [title]"
- "What's good in my unread [genre]?"
- "Suggest something from my TBR pile"
- "Find my next series to start"
- "What have I been neglecting?"
Tools
query_books(sort="rating", unread=True, tags=[...], limit=20)— Find top-rated unread books in a genre.manage_analysis(operation="reading_stats")— Reading statistics: completion rate, genre distribution, pages read, author diversity.manage_analysis(operation="series_progress")— Series tracking: which series are started but unfinished, next-in-series ordering.manage_metadata(operation="show", book_id=...)— Get full metadata for a candidate book: description, rating, tags, series position.calibre_metadata_search(query="similar to [title]")— Semantic similarity search using LanceDB embeddings.
Workflow
- Profile the reader: Call
manage_analysis(operation="reading_stats")to understand reading patterns, preferred genres, and completion behavior. - Surface candidates: Use
query_books(unread=True, sort="rating", tags=[preferred_genre])to get top-rated unread books. Combine multiple tag filters for precision. - Series catch-up: Call
manage_analysis(operation="series_progress")to find series with book 1 read but book 2+ unread — these are high-confidence recommendations. - Similarity match: For "like this book" queries, use
calibre_metadata_search()with a descriptive query of the source book's themes. - Rank and present: Score candidates by (rating + recency + series_position). Present top 3-5 with reasoning: why this matches the reader's taste, what tags overlap.
Example
"Recommend my next read from unread fantasy with high ratings." → query_books(tags=["fantasy"], unread=True, sort="rating", limit=30) → filter top 5 → manage_analysis(operation="series_progress") to prioritize continuations → present with per-book reasoning.
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 · 33 lines · 0 tokens per session scan A 6114b44d32f6
reading_recommendations is a skill published in the GitHub repository sandraschi/calibremcp (42 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 481 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 2026-08-30.
Other skills, from other repositories
calibre-study-notes
A tool that creates study notes from books in a Calibre library for a human learner. It uses questions, recall exercises, source pointers, and optional Anki export rather than only providing a summary.
calibre-distill
Turn ONE Calibre book into a reusable agent skill — frameworks, mental models, principles, techniques, anti-patterns, glossary, cheatsheet — by driving the calibre-mcp server (chapter map, keyword + semantic in-book search; no temp files, no Python). Use when the user wants to study a Calibre book through Claude Code…
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
sprite-animation
A pixel-art educational animation frame with large numbers or dates, a mascot, kinetic text, and a moving timeline. The repeating animation uses CSS keyframes, which are browser rules for changing visual properties over time.
extract-wisdom
Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.