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 moonlight-lupin/agent-skills --skill pdf2epub-calibrationgit clone --depth 1 https://github.com/moonlight-lupin/agent-skillsWrote 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/moonlight-lupin/agent-skills/pdf2epub-calibration)<a href="https://agentmods.dev/skills/moonlight-lupin/agent-skills/pdf2epub-calibration"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/pdf2epub-calibration/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/moonlight-lupin/agent-skills/pdf2epub-calibration"><img src="https://agentmods.dev/badge/skills/moonlight-lupin/agent-skills/pdf2epub-calibration.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 | $0.00095 | $0.02951 |
| Opus 5.5 | $0.00038 | $0.01180 |
| Sonnet 5.5 | $0.00019 | $0.00590 |
| Haiku 4.5 | $0.00010 | $0.00295 |
Grade A, and why
pdf2epub-calibration 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 11d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF→EPUB Classifier Calibration
When to Use
- A converted EPUB has citations in body text, page numbers as phantom endnotes, or broken/duplicate footnote links
- Chapter headings resolve to wrong PDF pages
- The cover image comes out as a texture fragment or a naked photo without typography
Span-merge reality (check the dump, not the flag)
page.get_text("dict")gives lines whose spans merge text at different font sizes. A body line can contain a 5pt footnote-ref span inside 12pt text — text extraction sees ONE line at the max span size.- Superscript flags are unreliable: several authoring tools (QuarkXPress-style CJK exports included) emit footnote refs as STANDALONE 6pt lines with the sup flag UNSET, and emit the note's own number as a leading 5pt span merged into the note's first line. Gate ref detection on size + position, never on the sup flag alone.
- Before changing any threshold, dump per-page lines with text/size/flags/y-ratio. Most classification misses are span-merge artifacts, not wrong thresholds.
Classification order and thresholds (validated values)
- FOLIO first: bare 1-4 digit (or roman i-vi) number, font < 0.85*body, y > 0.90. Rules run in order; if the footnote rule runs before the folio rule, page numbers become phantom notes.
- FNREF: whole line is a bare digit, font < 0.75*body, any y.
- FOOTNOTE: font < 0.92*body, y > 0.60, not a list marker. Long note blocks climb to 2/3 page height — a fixed 'footnotes below 80%' y-cut loses note starts. Use the largest threshold that still excludes body text.
- BODY: everything else.
- Body font size is LEARNED (2-char-mode of line sizes), never hard-coded. Books legitimately differ.
Footnote block grouping
- A note starts at a line whose first token is a bare digit followed by body text; bare-digit strays are dropped. Continuations attach unconditionally to the previous block.
- Per-chapter note numbering restarts are normal in books — scope anchor ids by chapter or duplicate ids fail the link check.
- Glued CJK note numbers need a monotonic matcher (see Endnotes-section books below), not a whitespace-required regex.
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.
- 11d ago First seen · 97 lines · 95 tokens per session scan A 2e10c6e202d5
pdf2epub-calibration is a skill published in the GitHub repository moonlight-lupin/agent-skills (101 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 2,951 once invoked, about $0.0004 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 2026-10-06.
Other skills, from other repositories
nano-pdf
Edit text in existing PDFs via natural-language prompts.
kagen
Convert Kami HTML templates to production-grade PDF via Chromium/Playwright. Complements Kami (design) with PDF rendering. Use when user asks to generate PDF files, render HTML to PDF, or export documents.
kami
Generate PDFs, resumes, CVs, letters, slide decks, portfolios, one-pagers, white papers, and professional documents. Use when user asks to create a PDF, make a resume, write a letter, design slides, format a document, typeset a report, build a portfolio, make a presentation, or create a one-pager. Warm parchment…
pdf-processing
Inspect, extract, OCR, create, merge, split, reorder, rotate, annotate, fill, redact, compress, secure, and verify PDF documents while preserving source files and visual fidelity. Use when working with one or more .pdf files; converting documents to or from PDF; extracting text, tables, images, metadata, forms, or…
document-converter-suite
Convert local PDF, Office, Markdown, HTML, text, CSV, TSV, and JSON files; batch-convert folders, extract tables, fill templates, and edit PDF pages.
Create, inspect, extract, merge, split, rotate, and render PDF files with local open-source tools, including structural and visual verification.