Scraper built and complete! Since I'm between jobs right now, I went with a job posting scraper for one of the titles I'm shooting for.
With this build, not using the WAT framework or developing skills, it was easy to see how carried away with token use this can get. not building skills and tools for the types of scrape, data cleaning or for building the output files had Claude Code running bash python for all of those, which generated on the fly has to be costly.
This scraper can easily fit into a personal tool for job-hunting I'm thinking about. Goal would be to scrape for jobs, refine results slightly, then scrape job description for key-words, employer website for context, and generate a new resume version with those keywords in ATS alignment, plus cover letter.