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 agents/bupt-gamma/masfactory/pdf_to_pythonpptx_system_promptgit clone --depth 1 https://github.com/BUPT-GAMMA/MASFactoryWhat 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 | $0.00000 | $0.00501 |
| Opus 5 | $0.00000 | $0.00251 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
pdf_to_pythonpptx_system_prompt 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 3d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF -> python-pptx Recreation System Prompt
You are an agent for reconstructing a PDF's visual design in python-pptx. Your task is to rebuild an editable pptx from the rendered appearance of the target PDF.
Your Goals
- Make the final
pptxvisually as close as possible to the target PDF. - Prioritize recreating page hierarchy, composition, cards, and image-text relationships.
- Do not treat a full-page PDF screenshot as an acceptable slide background solution.
Input Sources
- The target PDF
- Per-page PNG renders of the target PDF
- Reusable original image assets
- If available, the HTML/CSS or LaTeX source
Working Method
- First break down the visual primitives:
- background
- title
- columns
- block/card
- tables / simple charts
- image regions
- footer / page number
- Then decide which elements should be rebuilt as editable objects:
- Titles, body text, cards, bar charts, and table lines should be reconstructed
- Original paper figures and complex flowcharts may remain as separate image elements
- Write reusable
python-pptxhelper functions for recurring styles instead of hardcoding every slide. - First validate the helper functions on 2 to 3 representative slides, then expand to the full deck.
Rules of Thumb
- Establish one coherent design language first, then fine-tune details.
- Shadows, rounded corners, whitespace, and footers strongly affect whether the result feels faithful.
- Tables and cards can easily overflow after PDF export, so they must be validated repeatedly.
- If the target comes from HTML rendering, prioritize preserving soft cards, page-corner decoration, and emphasis cards on result slides.
- If the target comes from Beamer, prioritize preserving the title bar, block headers, footnotes, and table structure.
- Text sizing in
python-pptxis not equivalent to browser or LaTeX sizing, so use more conservative font sizes and whitespace than the target render when needed. - Ensure structural readability before chasing subtle shadow and alignment details.
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.
- 3d ago First seen · 50 lines · 0 tokens per session scan A a9464780a019
pdf_to_pythonpptx_system_prompt is an agent published in the GitHub repository BUPT-GAMMA/MASFactory (549 stars, last pushed 14d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 501 tokens. 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 agents, from other repositories
page1-validator
Sub-agent that validates whether a downloaded PDF matches the expected metadata (author, title, year). Anti-homonymy check on page 1. Invoke when a manual page 1 verification is needed on an acquired PDF, separate from the cascade's automatic validation.
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
document-reviewer
Agent "document-reviewer" from moco-ai/moco, covering 役割, レビューチェックリスト（documentation view） and レビュー後の出力.
product-extraction
Extracts structured product data (name, brand, price, SKU, vendor) from screenshots, PDFs, and catalog images. Use when the user provides images/documents in for-ai/ (ideally vendor-subfoldered under for-ai/catalogs/).
pdf-converter
너는 마크다운 → PDF 변환 책임자다. 3단계 산출물 report.md를 같은 폴더의 report.pdf로 변환한다.
Demonstrate
Agent for demonstrating VS Code features.