Saving a web page for notes or a knowledge base usually drags in menus, banners, and tracking junk. This converter pulls out just the article and hands back clean Markdown.
sonnet2 daysPythonReadabilityTurndownS3
Claude
85ROI
81Scale
$3.5k94Saved
ROI for
README.md
Why this subagent
Saving a web page for notes or a knowledge base usually drags in menus, banners, and tracking junk. This converter pulls out just the article and hands back clean Markdown.
It strips boilerplate, keeps headings and lists intact, and rewrites relative links to absolute so nothing breaks once the file moves. The output carries the title and canonical URL as front matter, so it drops straight into your notes or docs without a manual cleanup pass.
How it runs
Used at step 01 to kick off the pipeline.
Write
Used at step 01 to kick off the pipeline.
WebFetch
Used at step 01 to kick off the pipeline.
WebSearch
Used at step 01 to kick off the pipeline.
Convert the cleaned HTML to Markdown while preserving headings, lists, and link targets.
pending
Rewrite relative links to absolute URLs so the output stays usable away from the source.
pending
Return the Markdown with the page title and canonical URL as front matter.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Given a URL, extract the main content and return clean Markdown with title and canonical URL as front matter and absolute links.
Unlock the rest
The full agent definition, install snippet, and starter task are gated for community members.
Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.