Hacker News Reader

Comment by csallen | Hacker News Reader

I believe these are all "background" agents that, by default, are meant to write code and issue pull requests without you watching/babysitting/guiding the process. I haven't used Claude Code in a while, but from what I recall, it's not that.

View on HN

If you enable it in permissions, Claude is very happy to do so. For personal fun/experimental projects (usually I give it arXiv papers to implement), I generally have a couple Claude instances (on different projects) just chugging along all day. I have them write really detailed plans at the start (50-100 steps in the implementation plan, plus actual specifications for project structure, dev practices, and what the actual goals are). I iterate on these plan documents by having Claude write QUESTIONS.md which has dev questions for me to clarify, which I fill out with answers, and then instruct Claude to update the plan docs with my answers. Then most of my interaction throughout the day is just saying something like "P18" to implement implementation plan step #18. I instruct it in CLAUDE.md to stop after each step, output what automated tests have been written for P18's features, and I require that the LLM write a demo script that I can run that shows the features, using real APIs. I'm having a great time with it.

How much do you pay monthly? What kind of service do you use thanks

I'm on the $100 max plan. The default config uses Opus up until some percent of capacity, then uses Sonnet after, which resulted in my having to wait for 30 minutes to an hour to reset usage after running them for 8-10 hours. I've since switched to configuring it to only use Sonnet, then for what I know are "big" questions, I'll run opus for just that. Since then, I have yet to hit limits, so I don't feel the need for the $200 one.

I really need to try giving it a $100 month. Really not sure it's worth it, but if i'm less concerned about throttling or cost it might be more fun, interesting, etc.

It makes a psychological difference, yeah. I'm happy now just throwing any whim at it. For instance, I've been meaning for years to fix my disks, since every new computer just has me put the old drives into it, plus the new ones. Prior to the consolidation I had Claude do, oldest was from 2007 (good job, Western Digital 20 years ago). I had Claude write a plan on how to move files my most recent spinning disks, and also redo my mounts (for organization and improving my mount flags). I had it write the plan, I went "yeah", had it write a new fstab and a script to perform the moves in the project folder, had it "ultrathink" and web search a couple times to iterate on those for improvements it could suggest. Then I reviewed them, and had it apply the changes in a Claude instance with no automatic permissions beyond reading files in the project directory, so I manually approved the system modifications each.

That's impressive. Can you share a little more about the organization of files you requested? Like for example gather photos maybe ordered by device, year and month, mp3s based on genre, year, etc.? What was the output script language? I would definitely need something like that.

Small update, i ended up purchasing. So far it's been pretty productive. I'm avoiding using it for work that i find complex or vague, as it's more difficult to explain it and constrain it to what i want than just doing it myself.

However so far it's been amazing at doing grunt work. Especially grunt work i've been avoiding. "I've" already gotten a handful of things done that i've been pushing off the a year.

One issue i have noticed is i need to figure out how to more quickly toggle the level of thinking. I've used to some Opus credits on grunt work, it would be nice if the system could just automatically use Sonnet for easier grunt stuff.

There's also a soft cap of 50 sessions per month, right?

Looks that way, but Anthropic docs vaguely say it is vague. I know I haven't hit any hard caps since only using opus manually, but I wouldn't know if I'm being throttled otherwise, or at least it isn't severe enough that I notice given they just churn in the background.

Claude Code can run in background and I don't see why it wouldn't be able to create pull requests if you gave it such a tool.

The prompts in Claude Code have specific instructions on doing pull requests.

``` grep 'gh pr ' ~/.claude/local/node_modules/@anthropic-ai/claude-code/cli.js - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting. gh pr create --title "the pr title" --body "$(cat <<'EOF' 1. Use \`gh pr view --json number,headRepository\` to get the PR number and repository info 1. If no PR number is provided in the args, use ${O4.name}("gh pr list") to show open PRs 2. If a PR number is provided, use ${O4.name}("gh pr view <number>") to get PR details 3. Use ${O4.name}("gh pr diff <number>") to get the diff ```

How to tell CC to accept everything. It’s frustrating to need to press yes yes yes yes.

Stick it in docker, '--dangerously-skip-permissions'. There's also https://github.com/possibilities/claude-composer which seems to try to address this more directly, but I've never tried it.

Read the Claude Code documentation on how to setup permissions.

Reply on news.ycombinator.com