Claude Code moves forward to coding despite multiple requests and reminders and configurations NOT to do this
Preflight Checklist
- [x] I have searched existing issues for similar behavior reports
- [x] This report does NOT contain sensitive information (API keys, passwords, etc.)
Type of Behavior Issue
Claude ignored my instructions or configuration
What You Asked Claude to Do
do not make any changes to code without me approving it first!
What Claude Actually Did
Claude Code constantly moves forward to coding despite multiple requests and reminders and configurations NOT to do this. Explicitly agreed in every session to follow a process where it suggests a solution, then I need to approve it before it continues to implementation. Without Claude Code sticking to this process, we frequently revert changes, poor quality, wasted time and going in circles. Needless to say this is very frustrating. This makes the model almost unusable.
Expected Behavior
Follow the process agreed and also noted in its configuration.
Files Affected
Permission Mode
I don't know / Not sure
Can You Reproduce This?
Yes, every time with the same prompt
Steps to Reproduce
_No response_
Claude Model
Sonnet
Relevant Conversation
Impact
Critical - Data loss or corrupted project
Claude Code Version
Claude Code
Platform
Anthropic API
Additional Context
_No response_
This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗