[BUG] Slash command execution message appears twice in CLI output

Status Fixed / completed
Maintainer reply ✓ Yes — amorriscode
Activity 5 comments · opened Oct 20, 2025 · closed Nov 17, 2025
💡 Likely answer: A maintainer (amorriscode, contributor) responded on this thread — see the highlighted reply below.

Preflight Checklist

  • [x] I have searched existing issues and this hasn't been reported yet
  • [x] This is a single bug report (please file separate reports for different bugs)
  • [x] I am using the latest version of Claude Code

What's Wrong?

Description:

When invoking a custom slash command via the SlashCommand tool, the command execution message appears twice in the CLI output, creating the appearance
that the command is being processed twice.

Steps to Reproduce:

  1. Invoke a custom slash command (e.g., /create-work-item) via the SlashCommand tool
  2. Observe the CLI output

Expected Behavior:
The command execution message should appear once:
> /create-work-item is running…

Actual Behavior:
The command execution message appears twice:
> /create-work-item is running…
> /create-work-item is running…

Impact:

  • Confusing user experience (appears like duplicate processing)
  • Actual execution only happens once (no functional impact)
  • Appears to be a display/messaging issue

Context:
The duplication seems to occur between when the SlashCommand tool returns and when the command prompt expands.

What Should Happen?

Expected Behavior:
The command execution message should appear once:
> /create-work-item is running…

Error Messages/Logs

Steps to Reproduce

Steps to Reproduce:

  1. Invoke a custom slash command (e.g., /create-work-item) via the SlashCommand tool
  2. Observe the CLI output

<img width="1144" height="146" alt="Image" src="https://github.com/user-attachments/assets/e166878b-967a-4738-b16c-3557b58e03f4" />

Claude Model

Sonnet (default)

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.0.22

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

Windows Terminal

Additional Information

_No response_

View original on GitHub ↗

5 Comments

github-actions[bot] · 12 months ago

Found 1 possible duplicate issue:

  1. https://github.com/anthropics/claude-code/issues/9899

This issue will be automatically closed as a duplicate in 3 days.

  • If your issue is a duplicate, please close it and 👍 the existing issue instead
  • To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

danielmiessler · 11 months ago

Skills Exhibit Same Duplication Bug

I can confirm this bug also affects Skills (not just slash commands). When invoking any skill via the Skill tool, the execution message appears twice:

> The "Browser Automation" skill is running
  └ Allowed 1 tools for this command

> The "Browser Automation" skill is running
  └ Allowed 1 tools for this command

Environment:

  • Claude Code version: 2.0.31
  • Platform: macOS (Darwin 25.2.0)
  • Reproducible with: Every skill invocation

Pattern:

  • Message duplicates in terminal UI
  • Actual skill execution happens only once (verified via hook event logs)
  • Event logging shows proper single invocation: 1 PreToolUse + 1 PostToolUse
  • Duplication appears to be purely in the TUI rendering layer

Root Cause Analysis:
Based on investigation, the duplication occurs between the Skill tool response and the UI rendering, similar to the slash command issue described here. Skills and slash commands likely share the same message display pathway in the TUI.

Impact:

  • Cosmetic/UX issue only
  • No functional problems
  • Skills execute correctly despite duplicate messages

This suggests the fix for slash command duplication should also resolve skill message duplication.

---

Evidence screenshot available if needed. Happy to provide additional debugging information.

amorriscode contributor · 11 months ago

A fix for this will be out this week!

danielmiessler · 11 months ago

Thank you so much!

On Sun, Nov 16, 2025 at 22:58, Anthony Morris < @.*** > wrote:

amorriscode left a comment (anthropics/claude-code#9942) ( https://github.com/anthropics/claude-code/issues/9942#issuecomment-3540250918 ) A fix for this will be out this week! — Reply to this email directly, view it on GitHub ( https://github.com/anthropics/claude-code/issues/9942#issuecomment-3540250918 ) , or unsubscribe ( https://github.com/notifications/unsubscribe-auth/AAAMLXWHDKPZEHALNTOQCVD35FW2VAVCNFSM6AAAAACJUMDEOKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZTKNBQGI2TAOJRHA ). You are receiving this because you commented. Message ID: <anthropics/claude-code/issues/9942/3540250918 @ github. com>
github-actions[bot] · 10 months ago

This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.