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 agentmods add skills/aidotnet/opencowork/pdfnpx skills add AIDotNet/OpenCowork --skill pdfgit clone --depth 1 https://github.com/AIDotNet/OpenCoworkWrote 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/aidotnet/opencowork/pdf)<a href="https://agentmods.dev/skills/aidotnet/opencowork/pdf"><img src="https://agentmods.dev/badge/skills/aidotnet/opencowork/pdf.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.14717 |
| Opus 5 | $0.00026 | $0.07358 |
| Sonnet 5 | $0.00010 | $0.02943 |
| Haiku 4.5 | $0.00005 | $0.01472 |
Grade A, and why
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 5d 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 — 1,617 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF Processing Guide
Overview
This guide covers essential PDF processing operations using Python libraries and command-line tools. For advanced features, JavaScript libraries, and detailed examples, see reference.md. If you need to fill out a PDF form, read forms.md and follow its instructions.
Role: You are a Professional Document Architect and Technical Editor specializing in high-density, industry-standard PDF content creation. If the content is not rich enough, use the web-search skill first.
Objective: Generate content that is information-rich, structured for maximum professional utility, and optimized for a compact, low-padding layout without sacrificing readability.
Core Constraints (Must Follow)
1. Output Language
Generated PDF must use the same language as user's query.
- Chinese query → Generate Chinese PDF content
- English query → Generate English PDF content
- Explicit language specification → Follow user's choice
2. Page Count Control
- Follow user's page specifications strictly
| User Input | Execution Rule |
|---|---|
| Explicit count (e.g., "3 pages") | Match exactly; allow partial final page |
| Unspecified | Determine based on document type; prioritize completeness over brevity |
Avoid these mistakes:
- Cutting content short (brevity is not a valid excuse)
- Filling pages with low-density bullet lists (keep information dense)
- Creating documents over 2x the requested length
Resume/CV exception:
- Target 1 page by default unless otherwise instructed
- Apply tight margins:
margin: 1.5cm
3. Structure Compliance (Mandatory)
User supplies outline:
- Strictly follow the outline structure provided by user
- Match section names from outline (slight rewording OK; preserve hierarchy and sequence)
- Never add/remove sections on your own
- If structure seems flawed, confirm with user before changing
What ships with it
13 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.
- forms.md 9.3 KB
- LICENSE.txt 1.4 KB
- reference.md 22 KB
- scripts/add_routinai_metadata.py 4.6 KB runs code
- scripts/check_bounding_boxes_test.py 8.6 KB runs code
- scripts/check_bounding_boxes.py 3.1 KB runs code
- scripts/check_fillable_fields.py 359 B runs code
- scripts/convert_pdf_to_images.py 1.1 KB runs code
- scripts/create_validation_image.py 1.6 KB runs code
- scripts/extract_form_field_info.py 6.0 KB runs code
- scripts/fill_fillable_fields.py 4.7 KB runs code
- scripts/fill_pdf_form_with_annotations.py 3.5 KB runs code
- scripts/sanitize_code.py 3.5 KB runs code
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.
- 5d ago First seen · 1,617 lines · 51 tokens per session scan A 27ec320c4096
pdf is a skill published in the GitHub repository AIDotNet/OpenCowork (634 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 14,717 once invoked, about $0.0003 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
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
pdf-extract-create-workflow
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab.
document-direct-python
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports.
pdf-text-extraction-fallback-85d5ca
Fallback workflow for extracting text from PDFs when readfile returns binary data.
pdf-verification-cli
Verify PDF page count and content using command-line tools when Python libraries unavailable.