#!/bin/bash
# Corpus Assembly Script
# Concatenates all Markdown files into a unified corpus
# Adds file markers for traceability and uses sorted order for reproducibility

output="ardens_corpus.txt"
rm -f "$output"

find . -type f -name "*.md" | sort | while read file; do
  echo "===== $file =====" >> "$output"
  cat "$file" >> "$output"
  echo -e "\n" >> "$output"
done