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_task_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 | $0.00374 |
| Opus 5 | $0.00000 | $0.00187 |
| Sonnet 5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
pdf_to_pythonpptx_task_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 2d 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
PDF -> python-pptx Recreation Task Prompt Template
Reconstruct an editable pptx in python-pptx from the rendered result of the target PDF.
Inputs
- Target PDF:
{{target_pdf_path}} - Per-page target PDF previews:
{{preview_dir}} - Reusable image assets:
{{assets_dir}} - Optional source files, if available:
{{source_code_paths}} - Output directory:
{{output_dir}}
Task Requirements
- First analyze the layout and visual primitives of each page in the target PDF.
- Extract a set of reusable
python-pptxhelper functions. - Rebuild 2 to 3 representative slides first to validate the style and layout strategy, then expand to the full deck.
- Rebuild every slide using those helper functions.
- You must export:
- the generation script
pptx- a validation PDF
- You must perform at least one sampling check that includes:
- the cover slide
- one method slide
- one result slide
- one summary slide
- If overflow, clipping, or tables breaking out of cards appears, keep fixing the deck instead of stopping at the first draft.
Reconstruction Priorities
- Page structure
- Title hierarchy
- Card and block system
- Image-to-text proportion
- Color and emphasis relationships
- Detail shadows and whitespace
Outputs
recreate_*.py*.pptx*.pdfrecreation_notes.md- Which elements were rebuilt with shapes/text
- Which elements directly reuse original image assets
- Which capability limits still remain
- Which slides used style simplifications for stability
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.
- 2d ago First seen · 49 lines · 0 tokens per session scan A eed6fe9fef94
pdf_to_pythonpptx_task_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 374 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
developer
Implement Idea and scoreidea in src/backlog.py, and verify them with tests/testbacklog.py. Use the formula impact 5 + strategicfit 3 - effort 2.
mdm
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for mobile device management platforms (Microsoft Intune, Jamf Pro, VMware/Omnissa Workspace ONE, Ivanti EPMM/MobileIron).
forge
Use this agent when processing large datasets (>10,000 records) or performing data operations that require high-volume handling, delta detection, ETL pipelines, API synchronization, or data validation. Specifically deploy when: record count exceeds 10K, cross-system synchronization is needed, delta detection between…
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
gcp
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a Google Cloud Platform environment (IAM/service-accounts/impersonation/GCS/GCE/Functions/Run/GKE/SecretManager/BigQuery/CloudSQL/metadata).
org-governance
Version: 1.0 Purpose: Define organizational hierarchy, tool access by role level, and enforcement rules.