<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Review-Md on Tokenise</title><link>https://tokenise.rosvetic.com/tags/review-md/</link><description>Recent content in Review-Md on Tokenise</description><generator>Hugo</generator><language>en-gb</language><lastBuildDate>Sat, 17 Oct 2026 16:04:00 +0000</lastBuildDate><atom:link href="https://tokenise.rosvetic.com/tags/review-md/index.xml" rel="self" type="application/rss+xml"/><item><title>Write a REVIEW.md that quietens Claude Code Review, then gate merges on what it still finds</title><link>https://tokenise.rosvetic.com/posts/review-md-claude-code-review-gate/</link><pubDate>Sat, 17 Oct 2026 16:04:00 +0000</pubDate><guid>https://tokenise.rosvetic.com/posts/review-md-claude-code-review-gate/</guid><description>&lt;p&gt;A review bot that posts eleven comments on a three-line change gets muted by the end of the week. A bot that posts nothing on the one change that touches billing gets trusted, which is worse. Claude Code Review, the managed pull request reviewer for Team and Enterprise organisations, is tuned by a single Markdown file in the repo, and the defaults are written for production code in general, not yours.&lt;/p&gt;</description></item></channel></rss>