Custom Slash Commands Not Loading from Project-Level .claude/commands Directory

Status Fixed / completed
Maintainer reply ✓ Yes — ant-kurt
Activity 5 comments · opened Aug 20, 2025 · closed Aug 20, 2025
💡 Likely answer: A maintainer (ant-kurt, collaborator) responded on this thread — see the highlighted reply below.

Bug Description
Custom slash commands are broken in 1.0.84 onward. If I install 1.0.83 all my claude /commands which are install in the project level .claude/commands dir work fine. They are no longer shown in 1.0.84 and 1.0.85.

Environment Info

  • Platform: linux
  • Terminal: vte-based
  • Version: 1.0.85
  • Feedback ID: 6815bcd8-187c-43f2-b26e-bbabf59f9409

Errors

[{"error":"Error: Command failed: /home/dgnsrekt/.nvm/versions/node/v24.4.1/lib/node_modules/@anthropic-ai/claude-code/vendor/ripgrep/arm64-linux/rg --files --hidden /home/dgnsrekt/Development/ClaudeExperiment/super-claude-lite\n<jemalloc>: Unsupported system page size\n<jemalloc>: Unsupported system page size\nmemory allocation of 160 bytes failed\n\n    at genericNodeError (node:internal/errors:983:15)\n    at wrappedFn (node:internal/errors:537:14)\n    at ChildProcess.exithandler (node:child_process:417:12)\n    at ChildProcess.emit (node:events:507:28)\n    at ChildProcess.emit (node:domain:489:12)\n    at maybeClose (node:internal/child_process:1101:16)\n    at ChildProcess._handle.onexit (node:internal/child_process:305:5)","timestamp":"2025-08-20T02:08:37.092Z"},{"error":"Error: Command failed: /home/dgnsrekt/.nvm/versions/node/v24.4.1/lib/node_modules/@anthropic-ai/claude-code/vendor/ripgrep/arm64-linux/rg --files --hidden --follow --glob *.md /home/dgnsrekt/Development/ClaudeExperiment/super-claude-lite/.claude/commands\n<jemalloc>: Unsupported system page size\n<jemalloc>: Unsupported system page size\nmemory allocation of 160 bytes failed\n\n    at genericNodeError (node:internal/errors:983:15)\n    at wrappedFn (node:internal/errors:537:14)\n    at ChildProcess.exithandler (node:child_process:417:12)\n    at ChildProcess.emit (node:events:507:28)\n    at ChildProcess.emit (node:domain:489:12)\n    at maybeClose (node:internal/child_process:1101:16)\n    at ChildProcess._handle.onexit (node:internal/child_process:305:5)","timestamp":"2025-08-20T02:08:37.102Z"}]

View original on GitHub ↗

5 Comments

github-actions[bot] · 1 year ago

Found 3 possible duplicate issues:

  1. https://github.com/anthropics/claude-code/issues/2910
  2. https://github.com/anthropics/claude-code/issues/3507
  3. https://github.com/anthropics/claude-code/issues/2288

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

dgnsrekt · 1 year ago

I'm on the current version of ripgrep

dnf list | grep ripgrep
Updating and loading repositories:
Repositories loaded.
ripgrep.aarch64 14.1.1-2.fc42 fedora

dgnsrekt · 1 year ago

/home/dgnsrekt/.nvm/versions/node/v24.4.1/lib/node_modules/@anthropic-ai/claude-code/vendor/ripgrep/arm64-linux
./rg --version
<jemalloc>: Unsupported system page size
<jemalloc>: Unsupported system page size
memory allocation of 160 bytes failed
[1] 838220 IOT instruction (core dumped) ./rg --version

It looks like there is an issue with the rg that is bundled with claude-code.

ant-kurt collaborator · 1 year ago

FYI you can check claude /doctor for the status of the search functionality (including custom slash commands).

See https://docs.anthropic.com/en/docs/claude-code/troubleshooting#search-and-discovery-issues - you need to set the USE_BUILTIN_RIPGREP=0 via env var or settings.json. We switched this default to "on" recently.

github-actions[bot] · 1 year 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.