[BUG] Commands are now apparently "skills" and are loaded into context without being invoked. This effectively removes command functionality from Claude Code

[designbyian]

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?

Previously when creating .md files in directory .claude/commands, these were interpreted at slash commands that could be invoked by the user to inject them into chat. This was useful.

In the latest version these are now loaded into context as skills. I don't understand this as skills have their own implementation and directory structure.

Because one of the useful features of commands is that they were not loaded into context, this change effectively removes the commands functionality. Using the /context command it now reports token use for "skills" in a separate section that shows the token equivalent of the full contents of all commands files, with the resulting widely varying token use based on file size. Interestingly the agent does not appear to be aware of the contents of the commands files, so perhaps the token use listed is itself a bug.

The initial prompt, however, also includes metadata for the commands as skills, example below, which increases token use even more and is not useful for commands which are invoked on demand rather than at the agent's discretion: <skill> <name>commandName</name> <description>commandName (project)</description> <location>managed</location> </skill>

Note that I am encountering this in the VS Code extension, I have not test in the CLI as presumably the behavior is the same given that it's related to config/directories.

What Should Happen?

Commands should work as described in the docs and as they have up until recently.

Error Messages/Logs

Steps to Reproduce

Have a commands directory under .claude/ populated with files

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

No response

Claude Code Version

2.0.75

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

PowerShell

Additional Information

No response

[github-actions[bot]]

---

Found 3 possible duplicate issues:

1. https://github.com/anthropics/claude-code/issues/14611
2. https://github.com/anthropics/claude-code/issues/11459
3. https://github.com/anthropics/claude-code/issues/14834

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

---

[alberduris]

Confirmed. This is also reported here and seems to be already tracked by Anthropic: https://x.com/trq212/status/2002665131264950489?s=20

[AmirL]

The same issue :(

When prompt is:

Use SlashCommand tool to run /review-pr-prompt with argument *****
⏺ /review-pr-prompt
  ⎿  Error: Execute skill: review-pr-prompt

....

> What went wrong, did you have instructions about yaml file? 

⏺ You're right to question this - I tried to use the /review-pr-prompt skill but it failed with just "Execute skill: review-pr-prompt" error, so I fell back to manually reviewing the PR.

[AmirL]

Ok,

• there is no such tool as SlashCommand tool anymore.

EDITED:

I couldn't find a way to run a custom command from the CLI. It works, though, when running Claude in interactive mode.

[RiaanDeWinnaar]

Additional Report - Skills Preloading Full Content

Confirming this issue in VS Code extension with Claude Opus 4.5.

My Context Usage Before Any Conversation

Category	Tokens	Percentage
System prompt	7.7k	3.8%
System tools	17.7k	8.8%
Skills	26k+	13%+
Free space	123.7k	61.9%

Expected vs Actual

• Expected: Skills load only name/description at startup (~30-50 tokens each)
• • Actual: Full SKILL.md content loaded for ALL skills immediately

Impact

With 30+ skills/plugins configured:

• ~26k+ tokens consumed before conversation starts
• • Complex tasks hit context limits prematurely
• • • Progressive disclosure pattern completely bypassed

Environment

• Claude Code: VS Code Extension (latest)
• • Model: claude-opus-4-5-20251101
• • • OS: Windows 11
• • • • Skills: Mix of project skills (.claude/skills/) and plugins

Related

• #14834 - /context shows full skill tokens
• • #14882 - Skills consume full count at startup
• • • #7336 - Feature request for lazy loading

[turbo-soft]

Can confirm this. I have the same issue

[surajmandalcell]

Any temporary workaround to this?

[turbo-soft]

Any temporary workaround to this?

I have created simple bash script to move skills and commands I don't plan to use to other location, and then restart the claude.

[AmirL]

Any temporary workaround to this?

I have created simple bash script to move skills and commands I don't plan to use to other location, and then restart the claude.

Do you mean you moved commands into skill dir, right?

[RiaanDeWinnaar]

Basically like running MCP and enabling them when needed. Just create a discabled_skills folder, copy skills not being used there, restart CC. But then still loads all tools from any skill you have active in the skills folder, exactly like MCP

[turbo-soft]

Basically like running MCP and enabling them when needed. Just create a discabled_skills folder, copy skills not being used there, restart CC. But then still loads all tools from any skill you have active in the skills folder, exactly like MCP

yeah exactly. That is the best we can do right now.

I have also realized drop in performance due to this bug. All unrelated commands are loaded and making it behave strange.