←back to thread

170 points anandchowdhary | 1 comments | | HN request time: 0s | source

Continuous Claude is a CLI wrapper I made that runs Claude Code in an iterative loop with persistent context, automatically driving a PR-based workflow. Each iteration creates a branch, applies a focused code change, generates a commit, opens a PR via GitHub's CLI, waits for required checks and reviews, merges if green, and records state into a shared notes file.

This avoids the typical stateless one-shot pattern of current coding agents and enables multi-step changes without losing intermediate reasoning, test failures, or partial progress.

The tool is useful for tasks that require many small, serial modifications: increasing test coverage, large refactors, dependency upgrades guided by release notes, or framework migrations.

Blog post about this: https://anandchowdhary.com/blog/2025/running-claude-code-in-...

Show context
jes5199 ◴[] No.45960789[source]
can it read code review comments? I've been finding that having claude write code but letting codex review PRs is a productive workflow, claude code is capable of reading the feedback left in comments and is pretty good at following the advice.
replies(2): >>45960882 #>>45962184 #
jerezzprime ◴[] No.45960882[source]
Have you tried GitHub Copilot? I've been trying it out directly in my PRs like you suggest. Works pretty well sometimes.
replies(1): >>45961458 #
jes5199 ◴[] No.45961458[source]
I find that ChatGPT’s Codex reviews - which can also be set up to happen automatically on all PRs - seem smarter than Copilot’s, and make fewer mistakes. But these things change fast, maybe Copilot caught up and I didn’t notice
replies(1): >>45972389 #
1. tinodb ◴[] No.45972389{3}[source]
No codex catches genuine bugs here that multiple reviewers would have overlooked, whilst copilot only comes with nitpicks. And codex does none of those, which is also great.