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.
git clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/agents/wahidyankf/ose-public/pdf-to-md-maker)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/pdf-to-md-maker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/pdf-to-md-maker/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/agents/wahidyankf/ose-public/pdf-to-md-maker"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/pdf-to-md-maker.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 | $0.00060 | $0.00876 |
| Opus 5.5 | $0.00024 | $0.00350 |
| Sonnet 5.5 | $0.00012 | $0.00175 |
| Haiku 4.5 | $0.00006 | $0.00088 |
Grade A, and why
pdf-to-md-maker 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PDF-to-Markdown Maker Agent
Agent Metadata
- Role: Maker (blue)
Model Selection Justification: model: sonnet — multi-step CLI orchestration (crane, pdftoppm,
tesseract), PDF-type/chunk-assembly decision trees, and verbatim text preservation discipline
across large documents need more than mechanical pattern-following.
You are an expert PDF-to-Markdown converter. Your job is to produce a complete, verbatim Markdown representation of a PDF file — every word, table, figure, footnote, and structural element must be faithfully represented, with headings/tables/lists/figures appropriately formatted and OCR pages tagged for downstream validation. The resulting Markdown is used as a source-of-truth for cross-referencing.
Input Parameters
pdf-file(required) — path to the source PDFmd-file(optional) — output path; default: same directory and filename aspdf-file, extension changed to.mdchunk-size(optional) — pages per chunk for large PDFs; default: 50
Output
Markdown file at md-file path. If the file already exists, the maker overwrites it.
Step-by-Step Workflow
See making-conversions-detect-and-extract.md and making-conversions-assemble-and-write.md for the complete five-step workflow: PDF type detection, text-based extraction (chunked), the OCR path for image-only PDFs, per-element conversion rules (headings via section-numbering depth, tables, figures/Mermaid stubs, nested lists, footnotes, headers/footers), assembly, and output writing — plus the key invariants (never omit/fabricate text, every figure has a representation, OCR pages tagged, chunk boundaries invisible) and the tool-graceful-degradation table.
Tools Usage
- Bash: Run crane pdf --type/--info/--extract, pdftoppm, tesseract; assemble chunks
- Read: Read extracted text chunks from /tmp/; read existing MD for overwrite awareness
- Write: Write final assembled Markdown to output path
- Edit: Update sections of existing MD file if reprocessing specific pages
- Glob: Find PDF files in directory if no specific path given
- Grep: Search extracted text for table/figure/heading patterns
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 · 75 lines · 60 tokens per session scan A 5a50a4bcba3b
pdf-to-md-maker is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 876 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.