anthropics / anthropics/claude-code
[Feature Request] Add dangerously skip permissions option to cloud agents
- Dominant language
- Python
- Stars
- 145k
- Forks
- 23.1k
- PR merge metrics
- PR metrics pending
Description
**Bug Description**
Would love to see dangerously skip permissions come back to cloud agents - seemingly only now have manual, accept edits, and auto - auto is overly restrictive for a cloud agent which I have given specifically fine tuned permissions for
**Environment Info**
- Platform: darwin
- Terminal: Apple_Terminal
- Version: 2.1.267
- Feedback ID: 9cd96e28-179c-4ab7-911b-a2511122d7e6
**Errors**
```json
[]
```
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by finding where cloud agent permission modes are defined and surfaced in the CLI, then compare the existing manual, accept edits, and auto options with any local dangerously-skip-permissions behavior. Done would mean cloud agents have a supported option with the requested behavior, but this likely needs maintainer guidance because it changes security-sensitive permissions.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai-infra-agents, cli, cloud, security
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 32/100