Continuous Claude

Dev tools

ai coding agent wrapper

SHOW HN2025

170points
62comments
#411of 3,837 in 2025
Top 11%of 2025 by points

How HN took it

DebatedReal support and real criticism

4 positive, 4 neutral or asking, 1 mixed, 5 critical, out of 14 comments about the project. Thread score -0.07.

Idea: 2 for, 3 againstExecution: 2 for, 0 againstPricing: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Bash script is readable

    From 1 comment
    • Kudos on making Bash readable. (https://github.com/AnandChowdhary/continuous-claude/blob/main/continuous_claude.sh)
      janaagaard on HN

Objections

  • Agent-written tests are often low quality and mock-heavy

    From 3 comments
    • > codebase with hundreds of thousands of lines of code and go from 0% to 80%+ coverage in the next few weeks I had a coworker do this with windsurf + manual driving awhile back…
      apapalns on HN
    • I agree. It is very easy to fall in the trap: "I let AI write all the tests" and then find yourself in a situation where you have an unmaintainable mess with the only way to fix…
      id00 on HN
    • I find coding agents can produce very high quality tests if and only if you give them detailed guidance and good starting examples. Ask a coding agent to build tests for a…
      simonw on HN
  • Running in a loop may be expensive

    From 1 comment
  • Not a novel idea; a bash while loop suffices

    From 1 comment
    • You can do this with a single while loop in bash. No need for this project. Search for “ralph wiggum ai coding” and find a couple of guys that share plenty of examples and nerd…
      tinodb on HN

Requests

  • Support for Codex

    From 1 comment
  • Reading and acting on code review comments

    From 1 comment
    • 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…
      jes5199 on HN

Questions

  • How it handles questions asked by Claude

    From 1 comment

Alternatives named

  • Ralph Wiggum loop approach

    From 1 comment
    • You can do this with a single while loop in bash. No need for this project. Search for “ralph wiggum ai coding” and find a couple of guys that share plenty of examples and nerd…
      tinodb on HN
  • GitHub Copilot PR reviews

    From 1 comment
    • Have you tried GitHub Copilot? I've been trying it out directly in my PRs like you suggest. Works pretty well sometimes.
      jerezzprime on HN
  • Codex reviews

    From 1 comment
    • 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…
      jes5199 on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/45938517)