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 caelum29/calibre-mcp --skill calibre-study-notesgit clone --depth 1 https://github.com/caelum29/calibre-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/caelum29/calibre-mcp/calibre-study-notes)<a href="https://agentmods.dev/skills/caelum29/calibre-mcp/calibre-study-notes"><img src="https://agentmods.dev/badge/skills/caelum29/calibre-mcp/calibre-study-notes/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/caelum29/calibre-mcp/calibre-study-notes"><img src="https://agentmods.dev/badge/skills/caelum29/calibre-mcp/calibre-study-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium MCP Rug Pull · line 131 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00243 | $0.02352 |
| Opus 5 | $0.00121 | $0.01176 |
| Sonnet 5 | $0.00049 | $0.00470 |
| Haiku 4.5 | $0.00024 | $0.00235 |
Grade A, and why
calibre-study-notes 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
calibre-study-notes
Turn a chapter/topic from the user's Calibre library into a study note a human can actually learn from — or run a review session over an existing note.
Audience is the human learner. Everything follows from that. A perfect prose summary is a FAILURE here: reading a finished summary bypasses the generation effect (people retain what they process, not what they read). The note must force processing: questions before answers, hidden answers, retrieval prompts, blanks for the reader's own words.
Modes
| Mode | What it produces | When |
|---|---|---|
generate |
Full study note file (default) | "законспектуй розділ X" |
scaffold |
Structure + questions + source pointers only; body left as fill-in blanks for the human | User wants maximum retention / asks to "fill it myself" |
review |
Interactive quiz session in chat over an existing note; no new file | "поганяй мене по...", "review", or a note's next_review date has passed |
Depth (orthogonal to mode):
quick— TL;DR + core concepts + 5 self-test questions. No diagrams, no cross-library search. Default when the user asks casually or the runtime model/budget is constrained.deep— full template: reader-domain examples, diagrams,scope: librarycross-check, Anki block, misconceptions, full verification. Default when the user says "глибоко", "детально", or is preparing for interviews/exams.
If mode/depth are ambiguous, infer from phrasing; do not ask about them separately — fold into the scoping step below.
Workflow (generate / scaffold)
1. Scope — before touching the book
Establish, from context or by asking (ONE compact question, not an interview):
- Reader level in this topic: new / adjacent experience / refreshing.
- Goal: interview in N days / deep study / working reference.
- Scope: one chapter, several chapters, or a topic across the book.
A topic across ≥3 books → suggest
calibre-distill-topicinstead.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 189 lines · 243 tokens per session scan A 3714c11eefda
calibre-study-notes is a skill published in the GitHub repository caelum29/calibre-mcp (13 stars, last pushed 18d ago), licensed MIT. It adds 243 tokens to every session and 2,352 once invoked, about $0.0012 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 2026-08-30.
Other skills, from other repositories
reading_recommendations
Description: Get personalized reading recommendations from your Calibre library using series progress, ratings, tags, reading history, and collaborative filtering across similar books.
wiki-tour
Generate a guided, pedagogical reading tour through a vault — an ordered walkthrough that takes a newcomer from "what is this?" to "I get how it fits together", computed from the knowledge graph's link topology. Use when the user says "give me a tour of this vault", "where do I start", "walk me through my notes"…
canvas
Fetch Canvas LMS courses and assignments via API token.
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
skill-creation-walkthrough
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…
memstack-marketing-webinar-script
Use this skill when the user says 'webinar script', 'webinar', 'live presentation', 'teach-to-sell', or needs a timestamped presentation script with slide notes, presenter cues, and replay email sequence. Do NOT use for launch plans or static sales page copy.