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 pedrohcgs/Claude-Mini --skill pdf-to-mdgit clone --depth 1 https://github.com/pedrohcgs/Claude-MiniWrote 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/pedrohcgs/claude-mini/pdf-to-md)<a href="https://agentmods.dev/skills/pedrohcgs/claude-mini/pdf-to-md"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-mini/pdf-to-md/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/pedrohcgs/claude-mini/pdf-to-md"><img src="https://agentmods.dev/badge/skills/pedrohcgs/claude-mini/pdf-to-md.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 | $0.01070 |
| Opus 5 | $0.00044 | $0.00535 |
| Sonnet 5 | $0.00017 | $0.00214 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade A, and why
pdf-to-md 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 11d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pdf-to-md — Convert any document to clean markdown
Markdown is Claude's native format. PDFs cost 2–3× more tokens and bury content under formatting artifacts. Converting first cuts token usage 50–70% with no quality loss, and improves comprehension on multi-column or table-heavy PDFs.
Inputs
$1— input file path. Supported:.pdf,.docx,.pptx,.xlsx,.html,.epub,.csv,.xml.$2— output path (optional). If omitted, writes alongside the input with the.mdextension.
Steps
1. Validate input
Check that $1 exists and identify the format from the extension.
test -f "$1" || { echo "File not found: $1" && exit 1; }
EXT="${1##*.}"
OUT="${2:-${1%.*}.md}"
2. Quick first pass with MarkItDown
markitdown handles every supported format in one call. Run it first.
markitdown "$1" > "$OUT"
If the input is not a PDF, jump to step 4 (verify). MarkItDown's output is sufficient for DOCX / PPTX / HTML / EPUB.
3. PDF triage — decide whether to fall back to OpenDataLoader-PDF
PDFs are the only format where layout matters. Inspect the MarkItDown output for failure signals:
- Output is suspiciously short for a multi-page input (e.g., < 50 words for a 5-page PDF) — extraction failed.
- Tables collapsed to single lines — column structure was lost.
- Lines from different columns interleaved — multi-column reading order broken.
- Math/equations rendered as
□□□or random characters — no semantic capture.
If any trigger fires, rerun with OpenDataLoader-PDF (PDF specialist with XY-cut++ reading order):
opendataloader "$1" -o "$OUT" --format markdown
Otherwise, the MarkItDown pass is fine — proceed to step 4.
4. Verify
Read the first 30 lines of $OUT. Confirm:
- Headers preserved as
#/##/### - Tables visible as markdown pipe tables (where applicable)
- No raw XML, PDF metadata, or
<embed>tags leaked through - Body text reads as continuous prose, not fragmented column-by-column
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.
- 11d ago First seen · 98 lines · 87 tokens per session scan A 4f0d2351da84
pdf-to-md is a skill published in the GitHub repository pedrohcgs/Claude-Mini (11 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 1,070 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
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
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.
parse-document
Convert a PDF, scan, image of a page, or office file to clean markdown through the connected Superlinked MCP edge, so the source document is not read into model context directly. Use when the user asks to read, parse, OCR, extract from, summarize, or answer questions about a document.