←back to thread

Show HN: Continuous Claude – run Claude Code in a loop

(github.com)
170 points anandchowdhary | 3 comments | 15 Nov 25 16:27 UTC | HN request time: 0.001s | 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
decide1000 ◴[17 Nov 25 20:52 UTC] No.45958130[source]▶
How does it handle questions asked by Claude?
replies(1): >>45958328 #
anandchowdhary ◴[17 Nov 25 21:09 UTC] No.45958328[source]▶
It sends a flag that dangerously allows Claude to just do whatever it wants and only give us the final answer. It doesn't do the back-and-forth or ask questions.
replies(2): >>45958545 #>>45962202 #
CharlesW ◴[17 Nov 25 21:29 UTC] No.45958545[source]▶
The `--dangerously-skip-permissions` flag (a.k.a. "YOLO mode") does do the back-and-forth and asks questions, so this is a bit more than that.
replies(1): >>45958713 #
1. brumar ◴[17 Nov 25 21:45 UTC] No.45958713{3}[source]▶
Yes. I did not look but most probably the non interactive mode flag is used (-p)
replies(2): >>45958955 #>>45958994 #
2. anandchowdhary ◴[17 Nov 25 22:11 UTC] No.45958955[source]▶
It does `claude -p "This is the prompt" --dangerously-skip-permissions --output-format json`
3. CharlesW ◴[17 Nov 25 22:16 UTC] No.45958994[source]▶
Oh! TIL, thank you.