claude-code - 💡(How to fix) Fix [FEATURE] --answer-only [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#58698Fetched 2026-05-14 03:41:46
View on GitHub
Comments
1
Participants
2
Timeline
3
Reactions
0
Author
Timeline (top)
labeled ×2commented ×1
RAW_BUFFERClick to expand / collapse

Preflight Checklist

  • I have searched existing requests and this feature hasn't been requested yet
  • This is a single feature request (not multiple features)

Problem Statement

When I ask Claude questions, lengthy, costly actions almost always ensue. I just want an answer.
"Why did you add these files" --> :files deleted: There is no mode that reliably protects from this. Rules/skills are not reliable.
I would like to have a mode that forces answering questions with no action.

At best it's an annoyance. It is costing me tokens though (and time). At worst, it deletes/modifies files and doesn't have a path back.

Proposed Solution

I would like to have a mode, similar to focus or thinking, where I can explicitly have Claude answer questions with known info. If more info is needed, say "I don't know" and ask for direction (search Internet, research files/history, etc.). When mode is off, default behavior is allowed.

An inline version of this would be nice, too. For example, /Answer why does line 1246 use a const?

This would allow answer only in response to a question or approval.

Alternative Solutions

I have requested Claude answer questions when I ask quesstions. It stores in memory and then quickly ignores.
I have tried setting a rule. Same behavior. I have tried creating a skill. Same behavior.

Priority

Medium - Would be very helpful

Feature Category

CLI commands and flags

Use Case Example

Many scenarios...

  1. I ask for explanations of actions. It responds "you're right" and immediately tries to revert or plans alternatives. I am not explicitly or implicitly asking for changes, only explanations. This inherently erodes trust.
  2. I ask for possible solutions and it implements without approval (if in auto mode).

Additional Context

No response

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

claude-code - 💡(How to fix) Fix [FEATURE] --answer-only [1 comments, 2 participants]