3 people asked for

All time, since Oct 5.

Configurable safeguard granularity

“This is a a little annoying: is there a way to make the safeguards more fine-grained?”

What gets counted gets built. Pile on.

Paste this into your agent. It files your request, with what you need it for.

I want this: rapsheet.dev/sheets/claude-code/issues/3752/file
Follow it to file my request. Show me the text before you send.

No install. No account. Public and anonymous. The link asks your agent for one report, nothing else. What it sends

Quiet. No reports and thumbs-up in the last two weeks, down from 3 a week at the early-October peak.

Adjust safeguard strictness for academic research work. Reporters say safeguards flag their manuscript work or impose restrictions, and ask for more fine-grained control or configuration options.

Is this your request?

File my request
Where
Safety filters
Versions
2.1.268 to 2.1.289
Platforms
Linux, macOS, Windows

Not quite your request?

  1. Cyber flags on development prompts8 people

Original reports4, newest first

  1. Improve scientific accuracy and academic research access for Claude Code#102419
  2. Academic researcher access controls and documentation improvements#100319
  3. Provide configuration options for security filter sensitivity levels#99928
  4. Add configurable content policy granularity for academic/research use cases#99784

Do you work on Claude Code?

Claim its RAP Sheet to see what your users report and answer them in one place.