MODS(1)

💅 MODS(1) — GPT on the command line. Built for pipelines. 💅

hey bestie! welcome to the MODS(1) manual for mods. It's literally GPT on the command line, built for pipelines — that's the vibe, no cap. 🫶

---

💖 NAME 💖

mods — GPT on the command line. Built for pipelines.

Lowkey that's the whole pitch: GPT, in your command line, made for pipelines. Iconic. 💅

---

✨ SYNOPSIS ✨

okay so run it like this, fr fr:

mods [options...] [argument...]

[options...] and [argument...] — both right there, periodt. 🌸

---

📖 DESCRIPTION 📖

The original page leaves this section empty — mystery main-character silence, honestly. Since there's no description text here, I'm not inventing extra tech lore. Just vibes and good behavior. 🫶

---

💅 OPTIONS 💅

okay so here's the full options menu, every single flag included. Flags, values, defaults, and exact details are copied character for character — no renaming, no merging, no invented deets. Let's go. ✨

• --a, --api — OpenAI compatible REST API (openai, localai, anthropic, ...). Bring-your-own-API energy, iykyk.
• --M, --ask-model — Ask which model to use via interactive prompt. The app literally asks you, bestie.
• --c, --continue — Continue from the last response or a given save title. The "or" is doing important work here.
• --C, --continue-last — Continue from the last response. That's it, that's the whole job. 💅
• --d, --delete — Deletes one or more saved conversations with the given titles or IDs. Delete responsibly, okay?
• --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. Yes, both µs and μs are in there — keep them exact! 👑
• --dirs — Print the directories in which mods stores its data. Show me the folders, icon. 🎀
• --e, --editor — Edit the prompt in your $EDITOR; only taken into account if no other args and if STDIN is a TTY. That condition is doing main character work.
• --fanciness — Your desired level of fanciness. That's literally the whole description, and honestly? Obsessed. 🦋
• --f, --format — Ask for the response to be formatted as markdown unless otherwise set. Markdown girlies rise. ✨
• --format-as — The original page lists this one with no description — mystery era. We're not inventing behavior, bestie. 🫶
• --h, --help — Show help and exit. The classic escape hatch. 🚪
• --x, --http-proxy — HTTP proxy to use for API requests. Proxy it, bestie.
• --l, --list — Lists saved conversations. A little archive tour. 🌈
• --list-roles — List the roles defined in your configuration file. Role call! 💅
• --max-retries — Maximum number of times to retry API calls. Resilience era.
• --max-tokens — Maximum number of tokens in response. Keep it capped, keep it cute.
• --mcp-disable — Disable specific MCP servers. Specific ones, not all — read the flag, bestie.
• --mcp-list — List all available MCP servers. Server inventory vibes.
• --mcp-list-tools — List all available tools from enabled MCP servers. Only the enabled ones, periodt.
• --memprofile — Write memory profiles to CWD. Literally right there in the current working directory.
• --m, --model — Default model (gpt-3.5-turbo, gpt-4, ggml-gpt4all-j...). Pick your fave. 💖
• --no-cache — Disables caching of the prompt/response. No cache, no cap.
• --no-limit — Turn off the client-side limit on the size of the input into the model. Big input energy — and yes, it's the client-side limit.
• --P, --prompt — Include the prompt from the arguments and stdin, truncate stdin to specified number of lines. Both sources plus truncation — iykyk.
• --p, --prompt-args — Include the prompt from the arguments in the response. Arguments only in this one.
• --q, --quiet — Quiet mode (hide the spinner while loading and stderr messages for success). Shhh, stealth mode. 🤫
• --r, --raw — Render output as raw text when connected to a TTY. Raw text when TTY, exactly.
• --reset-settings — Backup your old settings file and reset everything to the defaults. Backup first, then reset — don't skip the backup part.
• --R, --role — System role to use. Set the system role, bestie.
• --settings — Open settings in your $EDITOR. Your editor, your rules. 🎀
• --s, --show — Show a saved conversation with the given title or ID. Title or ID — pick your key.
• --S, --show-last — Show the last saved conversation. Last one, right there.
• --status-text — Text to show while generating. Cute little status message energy. ✨
• --stop — Up to 4 sequences where the API will stop generating further tokens. Up to 4, not infinity.
• --temp — Temperature (randomness) of results, from 0.0 to 2.0, -1.0 to disable. Randomness dial, fr.
• --theme — Theme to use in the forms; valid choices are charm, catppuccin, dracula, and base16. Theme check! 🎀
• --t, --title — Saves the current conversation with the given title. Name it and save it.
• --topk — TopK, only sample from the top K options for each subsequent token, -1 to disable. Top K, token by token.
• --topp — TopP, an alternative to temperature that narrows response, from 0.0 to 1.0, -1.0 to disable. Alternative to temp, narrowing the response.
• --v, --version — Show version and exit. Drop the version, then bounce. 💅
• --word-wrap — Wrap formatted output at specific width (default is 80). Width gang, default 80.

---

okay bye bestie — this page's footer credits mods, dated 2026-10-25, and it's the MODS(1) manual. Stay sliving. 💖✨🫶