anthropics / anthropics/claude-code
[FEATURE] Highlighted Scripting
- Dominant language
- Python
- Stars
- 145k
- Forks
- 23.1k
- PR merge metrics
- PR metrics pending
Description
### Preflight Checklist
- [x] I have searched [existing requests](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20label%3Aenhancement) and this feature hasn't been requested yet
- [x] This is a single feature request (not multiple features)
### Problem Statement
If someone is trying to be careful about what scripts they are allowing Claude to write and run, normally Claude puts up a dialog box with the script text. They can be quite involved. The important things will almost always be where they are writing (often a scratch space), that they are writing, and perhaps some other triggers like checks for code insertion. I would highlight these in blue or green to make them pop out.
### Proposed Solution
Highlight file write targets and any specific inserts (as opposed to programmatic ones) to safeguard against malicious code insertion. highlight in blue perhaps.
### Alternative Solutions
_No response_
### Priority
Critical - Blocking my work
### Feature Category
CLI commands and flags
### Use Case Example
_No response_
### Additional Context
_No response_
Contributor guide
No contributing guide indexed for this repository
Research direction
No files or tests are named. Start by locating the CLI approval dialog that displays scripts, then trace how file-write targets and explicit insert operations are represented for rendering. Done means those elements are visually highlighted without obscuring other script content, with coverage for the relevant display behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- cli, security
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100