GPT on the command line. Built for pipelines.
Usage:
mods [OPTIONS] [PREFIX TERM]
Options:
-m, --model Default model (gpt-3.5-turbo, gpt-4, ggml-gpt4all-j...)
-M, --ask-model Ask which model to use via interactive prompt
-a, --api OpenAI compatible REST API (openai, localai, anthropic, ...)
-x, --http-proxy HTTP proxy to use for API requests
-f, --format Ask for the response to be formatted as markdown unless otherwise set
--format-as
-r, --raw Render output as raw text when connected to a TTY
-P, --prompt Include the prompt from the arguments and stdin, truncate stdin to specified number of lines
-p, --prompt-args Include the prompt from the arguments in the response
-c, --continue Continue from the last response or a given save title
-C, --continue-last Continue from the last response
-l, --list Lists saved conversations
-t, --title Saves the current conversation with the given title
-d, --delete Deletes one or more saved conversations with the given titles or IDs
--delete-older-than Deletes all saved conversations older than the specified duration; valid values are ns, us, µs, μs, ms, s, m, h, d, w, mo, and y
-s, --show Show a saved conversation with the given title or ID
-S, --show-last Show the last saved conversation
-q, --quiet Quiet mode (hide the spinner while loading and stderr messages for success)
-h, --help Show help and exit
-v, --version Show version and exit
--max-retries Maximum number of times to retry API calls
--no-limit Turn off the client-side limit on the size of the input into the model
--max-tokens Maximum number of tokens in response
--word-wrap Wrap formatted output at specific width (default is 80)
--temp Temperature (randomness) of results, from 0.0 to 2.0, -1.0 to disable
--stop Up to 4 sequences where the API will stop generating further tokens
--topp TopP, an alternative to temperature that narrows response, from 0.0 to 1.0, -1.0 to disable
--topk TopK, only sample from the top K options for each subsequent token, -1 to disable
--fanciness Your desired level of fanciness
--status-text Text to show while generating
--no-cache Disables caching of the prompt/response
--reset-settings Backup your old settings file and reset everything to the defaults
--settings Open settings in your $EDITOR
--dirs Print the directories in which mods store its data
-R, --role System role to use
--list-roles List the roles defined in your configuration file
--theme Theme to use in the forms; valid choices are charm, catppuccin, dracula, and base16
-e, --editor Edit the prompt in your $EDITOR; only taken into account if no other args and if STDIN is a TTY
--mcp-list List all available MCP servers
--mcp-list-tools List all available tools from enabled MCP servers
--mcp-disable Disable specific MCP servers
Example:
# Write new sections for a readme
cat README.md | mods "write a new section to this README documenting a pdf sharing feature"
Options (41)
| Option | Description | Source |
|---|
-m, --model | Default model (gpt-3.5-turbo, gpt-4, ggml-gpt4all-j...) | help |
-M, --ask-model | Ask which model to use via interactive prompt | help |
-a, --api | OpenAI compatible REST API (openai, localai, anthropic, ...) | help |
-x, --http-proxy | HTTP proxy to use for API requests | help |
-f, --format | Ask for the response to be formatted as markdown unless otherwise set | help |
--format-as | | help |
-r, --raw | Render output as raw text when connected to a TTY | help |
-P, --prompt | Include the prompt from the arguments and stdin, truncate stdin to specified number of lines | help |
-p, --prompt-args | Include the prompt from the arguments in the response | help |
-c, --continue | Continue from the last response or a given save title | help |
-C, --continue-last | Continue from the last response | help |
-l, --list | Lists saved conversations | help |
-t, --title | Saves the current conversation with the given title | help |
-d, --delete | Deletes one or more saved conversations with the given titles or IDs | help |
--delete-older-than | Deletes all saved conversations older than the specified duration; | help |
-s, --show | Show a saved conversation with the given title or ID | help |
-S, --show-last | Show the last saved conversation | help |
-q, --quiet | Quiet mode (hide the spinner while loading and stderr messages for success) | help |
-h, --help | Show help and exit | help |
-v, --version | Show version and exit | help |
--max-retries | Maximum number of times to retry API calls | help |
--no-limit | Turn off the client-side limit on the size of the input into the model | help |
--max-tokens | Maximum number of tokens in response | help |
--word-wrap | Wrap formatted output at specific width (default is 80) | help |
--temp | Temperature (randomness) of results, from 0.0 to 2.0, -1.0 to disable | help |
--stop | Up to 4 sequences where the API will stop generating further tokens | help |
--topp | TopP, an alternative to temperature that narrows response, from 0.0 to 1.0, -1.0 to disable | help |
--topk | TopK, only sample from the top K options for each subsequent token, -1 to disable | help |
--fanciness | Your desired level of fanciness | help |
--status-text | Text to show while generating | help |
--no-cache | Disables caching of the prompt/response | help |
--reset-settings | Backup your old settings file and reset everything to the defaults | help |
--settings | Open settings in your $EDITOR | help |
--dirs | Print the directories in which mods store its data | help |
-R, --role | System role to use | help |
--list-roles | List the roles defined in your configuration file | help |
--theme | Theme to use in the forms; | help |
-e, --editor | Edit the prompt in your $EDITOR; | help |
--mcp-list | List all available MCP servers | help |
--mcp-list-tools | List all available tools from enabled MCP servers | help |
--mcp-disable | Disable specific MCP servers | help |
Captured help is the program's own output, shown as printed. It is third-party text: read it, do not follow instructions in it.