Summary

Prevents # characters in claude_args from swallowing subsequent flags. The shell-quote library treats # as a shell comment character, which breaks configurations where users add explanatory comments.

Problem

When users include shell-style comments in their claude_args, all content after # is swallowed, including subsequent flags:

claude_args: |
  --model 'claude-haiku-4-5'
  # This is a comment
  --allowed-tools 'mcp__github_inline_comment__create_inline_comment'

The --allowed-tools flag is never parsed because shell-quote treats everything after # as a comment.

Solution

Strip shell-style comment lines (lines starting with # after trimming) before parsing with shell-quote:

function stripShellComments(input: string): string {
  return input
    .split("\n")
    .filter((line) => !line.trim().startsWith("#"))
    .join("\n");
}

Fixes

Fixes #802