/convert_paths_relative
Converts absolute paths in .claude/settings.json command scripts to relative paths
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/convert_paths_relative
Context preview
What this command does when you run it.
Converts absolute paths in .claude/settings.json command scripts to relative paths
Command definition
convert_paths_relative.mdallowed-tools: Read,Bash,Edit,Write description: Converts absolute paths in .claude/settings.json command scripts to relative paths
convert_paths_relative
This command converts all absolute paths in .claude/settings.json command scripts to relative paths. It helps make the configuration more portable and easier for others to use as a starter template.
Instructions
- Get the current working directory using pwd
- Read the .claude/settings.json file
- Parse the JSON content to find all command scripts
- Identify absolute paths in the command scripts (paths that start with /)
- Convert each absolute path that points to files within the current project to a relative path
- Update the settings.json file with the converted relative paths
- Show the user what changes were made
- Handle cases where paths might be arguments to commands (e.g., python /absolute/path/script.py)
- Preserve the existing JSON formatting and structure
- Create a backup of the original settings.json before making changes
Watched how we used GPT-5 and Claude Code with nano-agents here. What? A MCP Server for experimental, small scale engineering agents with multi-provider LLM support. Why?
Other commands on nano-agent.
- /build
Implement a task directly without creating a plan first.
Open command - /convert_paths_absolute
Converts relative paths in .claude/settings.json command scripts to absolute paths
Open command - /create_worktree
Create a new git worktree for an agent to work in isolation.
Open command - /hop_evaluate_nano_agents
Using the nano-agent mcp server, execute the following nano agents with their respective prompts, models, and providers then rank the results based on the `Response Format`.
Open command - /lop_eval_1__dummy_test
- Pass the prompt into each nano-agent AS IS. Do not change the prompt in any way.
Open command - /lop_eval_2__basic_read_test
- Pass the prompt into each nano-agent AS IS. Do not change the prompt in any way. - Each agent should execute the task independently.
Open command