[BUG] When @-mentioning a file in skill argument, "Read file (NNN lines)" is printed, but file is not in the context.

Resolved 💬 3 comments Opened Mar 18, 2026 by ANogin Closed Apr 17, 2026

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?

In a prompt /skill with a @file, I see

❯ /skill with a @file               
  ⎿  Read file (NNN lines)

but Claude then claims it had never seen the file.

What Should Happen?

Same as with @-mentions in regular prompt - file injected into the context

Error Messages/Logs

Steps to Reproduce

  1. Execute a skill that way
  2. Ask Claude whether the file was added to the context

Claude Model

Opus

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

2.1.78

Platform

AWS Bedrock

Operating System

Ubuntu/Debian Linux

Terminal/Shell

VS Code integrated terminal

Additional Information

_No response_

View original on GitHub ↗

This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗