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 axutse/aos-agent-skill-document --skill aos-process-pdfgit clone --depth 1 https://github.com/axutse/aos-agent-skill-documentWrote 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/axutse/aos-agent-skill-document/aos-process-pdf)<a href="https://agentmods.dev/skills/axutse/aos-agent-skill-document/aos-process-pdf"><img src="https://agentmods.dev/badge/skills/axutse/aos-agent-skill-document/aos-process-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/axutse/aos-agent-skill-document/aos-process-pdf"><img src="https://agentmods.dev/badge/skills/axutse/aos-agent-skill-document/aos-process-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 | $0.00087 | $0.00431 |
| Opus 5 | $0.00044 | $0.00216 |
| Sonnet 5 | $0.00017 | $0.00086 |
| Haiku 4.5 | $0.00009 | $0.00043 |
Grade A, and why
aos-process-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 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.
What it actually says
AOS PDF Processing
Preserve vector content and verify both document structure and rendered appearance. Read references/pdf-workflow.md before complex PDF work.
Treat fixed-layout integrity and full-page inspection as the primary contract. Do not infer visual correctness from extracted text, and do not modify an audit-only input until the user approves the reported repair scope.
Workflow
- Inspect page count, dimensions, rotation, encryption, metadata, forms, links, and image usage.
- Use ReportLab for deterministic creation and pypdf for structural operations.
- Preserve vector content unless rasterization is explicitly required.
- Render the complete final PDF with Poppler.
- Inspect every page at readable zoom; use a contact sheet only for overview.
- Reopen and structurally verify any edited or generated PDF.
- Scrub metadata before public release when personal metadata is not required.
Commands
python scripts/inspect_pdf.py input.pdf --json
python scripts/scrub_pdf_metadata.py input.pdf public.pdf
python scripts/render_pdf.py public.pdf --output-dir render --dpi 200
python scripts/make_contact_sheet.py 'render/page-*.png' --output contact-sheet.jpg
Quality rules
- Do not approve a PDF from extracted text alone.
- Confirm page count, dimensions, metadata policy, links/forms where applicable, and successful reopening.
- Inspect every page for clipping, overlaps, missing glyphs, incorrect page boxes, blur, or broken tables.
- Keep temporary PNGs outside final delivery unless requested.
- Use ASCII hyphens in generated technical text when renderer compatibility is uncertain.
What ships with it
6 files 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 · 38 lines · 87 tokens per session scan A 12b5e7404616
aos-process-pdf is a skill published in the GitHub repository axutse/aos-agent-skill-document (2 stars, last pushed 27d ago), licensed MIT. It adds 87 tokens to every session and 431 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
document-generation
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. Use when someone needs a deliverable rather than an answer — a change record to attach to a CR, an audit workbook for a compliance reviewer, a…
document-processing
Use when the deliverable is a document's bytes or its literal content — text/tables out of PDFs, AcroForm fill and flatten, page merge/split, PDF/DOCX from templates, OCR of image-only scans. NOT schema-typed fields pulled from text (that is structured-extraction), NOT signature routing (e-signature) or spreadsheet…
docx
Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.
document-processing-expert
Read, generate and modify office documents and PDFs from code: PDF extraction and forms, Word documents, Excel workbooks and PowerPoint decks. Use when the user mentions PDF, DOCX, XLSX, PPTX, Word, Excel, PowerPoint or spreadsheets, wants data extracted from documents, needs a report or invoice generated as a file…
bank-statement-parsing
Guidelines for parsing bank statements using YOLO layout detection + OCR + LLM.
all2md
Convert, read, generate, search, and compare documents with the all2md CLI and Python library. Use whenever a task involves reading or extracting text/tables from a document (PDF, Word, PowerPoint, Excel, HTML, email, EPUB, Jupyter, images, or 100+ source-code and text file types); converting between formats…