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 emanueleielo/ciana-parrot --skill nano-pdfgit clone --depth 1 https://github.com/emanueleielo/ciana-parrotWrote 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/emanueleielo/ciana-parrot/nano-pdf)<a href="https://agentmods.dev/skills/emanueleielo/ciana-parrot/nano-pdf"><img src="https://agentmods.dev/badge/skills/emanueleielo/ciana-parrot/nano-pdf/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/emanueleielo/ciana-parrot/nano-pdf"><img src="https://agentmods.dev/badge/skills/emanueleielo/ciana-parrot/nano-pdf.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 | $0.00036 | $0.00401 |
| Opus 5 | $0.00018 | $0.00200 |
| Sonnet 5 | $0.00007 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
nano-pdf 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 12d 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.
What it actually says
Nano PDF
Edit PDF files using natural language instructions, powered by Google Gemini.
When to Use
- "Update this slide to include 2025 data"
- "Change the title on page 3"
- "Add an agenda slide to this deck"
- "Edit this PDF to fix the chart"
- Any natural-language PDF editing request
Edit a Page
nano-pdf edit document.pdf 2 "Change the title to 'Q4 Results'"
Arguments: edit <file> <page_number> "<instruction>"
Add a New Slide
nano-pdf add presentation.pdf 0 "Agenda slide with: Overview, Financial Results, Outlook"
Inserts at position 0 (beginning). Use page count to append at end.
Edit with Style Reference
nano-pdf edit document.pdf 5 "Add a summary section" --style-pages 1,2
Uses pages 1-2 as visual style reference for consistent design.
Batch Edit Multiple Pages
nano-pdf edit report.pdf 1-5 "Update the footer to say 'Confidential 2026'"
Notes
- Requires
GEMINI_API_KEYwith billing enabled (Gemini 3 Pro Image) - Uses Poppler to convert PDF pages to images for processing
- Non-destructive: preserves searchable text layer via OCR re-hydration
- Output overwrites the original file — make a copy first if needed
- Works best with slide decks and visually structured PDFs
- For basic PDF operations (merge, split, rotate) without AI, use
python3with pypdf
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.
- 12d ago First seen · 55 lines · 36 tokens per session scan A 649123e0cfa9
nano-pdf is a skill published in the GitHub repository emanueleielo/ciana-parrot (77 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 401 once invoked, about $0.0002 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
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
pdf-generator
A document tool that turns Markdown, HTML, plain text, or template data into paginated PDF files. It supports A4 pages, page numbers, automatic page breaks, and Chinese text.
pdf-processor
A tool for working with PDF files: it can read text and tables, combine or split documents, convert pages to images, and show basic file details.
document-suite
A single document-processing toolkit for PDF, Word, Excel, PowerPoint, and Markdown files. It chooses a document-specific handler based on the file type or requested task.
youdaonote
A command-line skill for managing Youdao Cloud Notes, a Chinese note-taking service. It supports notes, to-do items, saved web pages, searches, and folders.
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…