Developers are divided between migrating to third-party harnesses like Pi for their customizability and control, versus staying with native tools like Claude Code due to concerns about stability, security, and vendor restrictions. The strongest disagreement centers on whether the flexibility of open-source harnesses outweighs the operational risks of manual configuration and potential Terms of Service violations.
493 readable replies · Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4anthropics
claude-code
TypeScript2025–2026
anthropics / claude-code
claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
407Distinct people
528Mentions
3Explicit recommenders
155.5KGitHub stars
What to know before exploring
What it is
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
GitHub
Where it is used
- Pictet — “A separate team successfully implemented a disaster recovery feature with Claude Code where other AI tools had failed.” Source
- Twilio — “Over 51 days, working solo with Claude Code, Carpenter built the Feature Factory: a self-learning development system that takes a brainstorm idea through a subagent pipeline to produce specs, tests, working code, and documentation.” Source
- 8 more documented examples
What people are saying
My favorite is the Claude Code bugtracker, on GitHub of course: https://github.com/anthropics/claude-code/issues There is some bot that will match your issue to some other 3…
stefan_ used a recommendation phrase. 3 indexed comments match. This is a phrase match, not a verdict.
Critical Commenters criticize Anthropic for unclear billing, auto-closing bug reports, breaking features without notice, and various usability issues in Claude Code. One commenter praises the tool as the best harness on the market.
A warning from this week’s discussion. Read the supporting reply
Also in these discussions
- openai/codex · linked in 3 of the same discussions
Mentioned in the same Hacker News threads. That is not proof they are substitutes.
This week on Hacker News
Critical
Commenters criticize Anthropic for unclear billing, auto-closing bug reports, breaking features without notice, and various usability issues in Claude Code. One commenter praises the tool as the best harness on the market.
Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4 · Supporting reply 5 · 5 discussions summarized
Nov 8–Nov 15 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/15/2026, 2:59:53 AM UTC.
The discussion centers on whether Claude Code's 'Don't Ask Again' feature is at fault for leaking secrets into public repositories or if the issue stems entirely from user negligence in committing local settings files. Conversely, defenders argue that manual review is fundamentally unsustainable at scale and that the industry must shift toward automated approval or robust sandboxing despite current flaws.
429 readable replies · Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4Read the discussion on HN. A full-thread summary is not available yet.
Showing the three threads with the most distinct people linking this repo, from 5 threads this week.
Mentions over time
HN mentions by month528 dated mentions
Observed mentions: 2025-02-24 19:48:14 UTC to 2026-10-30 14:49:33 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Feb 2025 | 2025-02-01 00:00:00 UTC | 2025-03-01 00:00:00 UTC | 6 | 1 | 5 |
| Mar 2025 | 2025-03-01 00:00:00 UTC | 2025-04-01 00:00:00 UTC | 5 | 2 | 3 |
| Apr 2025 | 2025-04-01 00:00:00 UTC | 2025-05-01 00:00:00 UTC | 2 | 0 | 2 |
| May 2025 | 2025-05-01 00:00:00 UTC | 2025-06-01 00:00:00 UTC | 2 | 0 | 2 |
| Jun 2025 | 2025-06-01 00:00:00 UTC | 2025-07-01 00:00:00 UTC | 5 | 3 | 2 |
| Jul 2025 | 2025-07-01 00:00:00 UTC | 2025-08-01 00:00:00 UTC | 13 | 4 | 9 |
| Aug 2025 | 2025-08-01 00:00:00 UTC | 2025-09-01 00:00:00 UTC | 10 | 5 | 5 |
| Sep 2025 | 2025-09-01 00:00:00 UTC | 2025-10-01 00:00:00 UTC | 10 | 1 | 9 |
| Oct 2025 | 2025-10-01 00:00:00 UTC | 2025-11-01 00:00:00 UTC | 15 | 5 | 10 |
| Nov 2025 | 2025-11-01 00:00:00 UTC | 2025-12-01 00:00:00 UTC | 12 | 5 | 7 |
| Dec 2025 | 2025-12-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 21 | 8 | 13 |
| Jan 2026 | 2026-01-01 00:00:00 UTC | 2026-02-01 00:00:00 UTC | 76 | 14 | 62 |
| Feb 2026 | 2026-02-01 00:00:00 UTC | 2026-03-01 00:00:00 UTC | 37 | 9 | 28 |
| Mar 2026 | 2026-03-01 00:00:00 UTC | 2026-04-01 00:00:00 UTC | 47 | 12 | 35 |
| Apr 2026 | 2026-04-01 00:00:00 UTC | 2026-05-01 00:00:00 UTC | 103 | 29 | 74 |
| May 2026 | 2026-05-01 00:00:00 UTC | 2026-06-01 00:00:00 UTC | 26 | 9 | 17 |
| Jun 2026 | 2026-06-01 00:00:00 UTC | 2026-07-01 00:00:00 UTC | 21 | 4 | 17 |
| Jul 2026 | 2026-07-01 00:00:00 UTC | 2026-08-01 00:00:00 UTC | 32 | 10 | 22 |
| Aug 2026 | 2026-08-01 00:00:00 UTC | 2026-09-01 00:00:00 UTC | 32 | 12 | 20 |
| Sep 2026 | 2026-09-01 00:00:00 UTC | 2026-10-01 00:00:00 UTC | 31 | 8 | 23 |
| Oct 2026 | 2026-10-01 00:00:00 UTC | 2026-11-01 00:00:00 UTC | 22 | 4 | 18 |
What Hacker News says
37 sourcesCUcube00·Feb 25, 2026
> they don’t do proper testing
They bring down production because the version string was changed incorrectly to add an extra date. That would have been picked up in even the most basic testing since the app couldn't even start.
https://news.ycombinator.com/item?id=46532075
The fix (not even a PR or commit message to explain) https://github.com/anthropics/claude-code/commit/63eefe157ac...
No root cause analysis either https://github.com/anthropics/claude-code/issues/16682#issue...
In Claude Code Remote ControlWorth noting that this is currently broken for a number of users, I'm on a Max plan and I get the message "Error: Remote Control is not enabled for your account. Contact your administrator" which isn't helpful since I'm my administrator and ... this gets recursive quickly.
There's an open issue on github for it:
https://github.com/anthropics/claude-code/issues/28098
In Claude Code Remote ControlBash tool execution failing in Claude Code
1 points · Open discussionOne-liner to get Claude Code usage stats
3 points · Open discussionyou can also judge for yourself based on the changelog https://github.com/anthropics/claude-code/blob/main/CHANGELO...
maybe we don't have AGI to prevent all bugs. but surely some of these could have been caught with some good old fashioned elbow grease and code review.
In Why is Claude an Electron app?there's currently ~6k open issues and ~20k closed ones on their issue tracker (https://github.com/anthropics/claude-code/issues). certainly a mix of duplicates / feature requests, but 'buggy mess' seems appropriate
In Why is Claude an Electron app?https://github.com/anthropics/claude-code/issues
Maybe you could look at some of those and fix them, before declaring "coding is solved"?
In Head of Claude Code: What happens after "coding is solved" [audio]Claude Code published fabricated claims to 8 platforms over 72hrs
11 points · Open discussionExcessive token usage in Claude Code
62 points · Open discussionClaude Code's compaction discards data that's still on disk
31 points · Open discussionClaude Desktop on Windows Broke MCP
3 points · Open discussionAPI Error: Claude's response exceeded the 32000 output token maximum
3 points · Open discussionInstead of having my computer be the one running Claude Code and executing tasks, I might want to prefer to offload it to my other homelab servers to execute agents for me, working pretty much like traditional CI/CD, though with LLMs working on various tasks in Docker containers, each on either the same or different codebases, each having their own branches/worktrees, submitting pull/merge requests in a self-hosted Gitea/GitLab instance or whatever.
If I don't want to sit behind something like LiteLLM or OpenRouter, I can just use the Claude Agent SDK: https://platform.claude.com/docs/en/agent-sdk/overview
However, you're not supposed to really use it with your Claude Max subscription, but instead use an API key, where you pay per token (which doesn't seem nearly as affordable, compared to the Max plan, nobody would probably mind if I run
Read the rest
it on homelab servers, but if I put it on work servers for a bit, technically I'd be in breach of the rules):
> Unless previously approved, Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products, including agents built on the Claude Agent SDK. Please use the API key authentication methods described in this document instead.
If you look at how similar integrations already work, they also reference using the API directly: https://code.claude.com/docs/en/gitlab-ci-cd#how-it-works
A simpler version is already in Claude Code and they have their own cloud thing, I'd just personally prefer more freedom to build my own: https://www.youtube.com/watch?v=zrcCS9oHjtI (though there is the possibility of using the regular Claude Code non-interactively: https://code.claude.com/docs/en/headless)
It just feels a tad more hacky than just copying an API key when you use the API directly, there is stuff like https://github.com/anthropics/claude-code/issues/21765 but also "claude setup-token" (which you probably don't want to use all that much, given the lifetime?)
You're not alone: https://github.com/anthropics/claude-code/issues/23706
In Claude Sonnet 4.6Showing the 15 most recent of 37 sources. Enable JavaScript to search and browse every indexed mention.