←back to thread

170 points anandchowdhary | 6 comments | | HN request time: 0s | source | bottom

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 ◴[] No.45958130[source]
How does it handle questions asked by Claude?
replies(1): >>45958328 #
1. anandchowdhary ◴[] 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 #
2. CharlesW ◴[] 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 #
3. brumar ◴[] No.45958713[source]
Yes. I did not look but most probably the non interactive mode flag is used (-p)
replies(2): >>45958955 #>>45958994 #
4. anandchowdhary ◴[] No.45958955{3}[source]
It does `claude -p "This is the prompt" --dangerously-skip-permissions --output-format json`
5. CharlesW ◴[] No.45958994{3}[source]
Oh! TIL, thank you.
6. stpedgwdgfhgdd ◴[] No.45962202[source]
Iteratively working is a MUST for more than trivial fixes. This continuous loop could work for trivial refactorings / maintenance tasks.