Claude Code mod
auto-model
Picks the model for each prompt and each subagent (never above /model and /effort for prompts), with Jev, OpenAI or Claude as the picker, and shows a colored bar under the input, or above it in Desktop: model, effort, context, 7-day limit and agents. /auto-model on|off, /route for subagents. Subagent picking is ported from Hamza Zafar's switchboard (MIT).
Install
/plugin marketplace add Luminous13/claude-mods
/plugin install auto-model@claude-modsMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L3Network: network, drives Claude, reads env vars, reads mod state, persists state, draws
- Sees
- subagent spawns
- Draws in
PromptHintAbovePromptPane- Hooks
session.startsession.endagent.spawnturn.startturn.stepturn.completeui.rendercommand.run
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- Luminous13/claude-mods
- Folder
mods/auto-model- Marketplace
claude-mods- Author
- Nereo Valeriano
- License
- MIT
- Last updated
- 23 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is auto-model?
Picks the model for each prompt and each subagent (never above /model and /effort for prompts), with Jev, OpenAI or Claude as the picker, and shows a colored bar under the input, or above it in Desktop: model, effort, context, 7-day limit and agents. /auto-model on|off, /route for subagents. Subagent picking is ported from Hamza Zafar's switchboard (MIT). It is a mod for Claude Code, from Luminous13/claude-mods on GitHub.
What can the auto-model mod access?
Its widest reach is "network" (network, drives Claude, reads env vars, reads mod state, persists state, draws). It sees subagent spawns. It draws in PromptHint, AbovePrompt, Pane. Like any mod, it runs with your permissions.
How do I install auto-model?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add Luminous13/claude-mods and then /plugin install auto-model@claude-mods.
More pane & dashboard mods
attest-ledger
ramankrishna/attest-ledger
Shows what actually ran next to what Claude said ran: checks, stale passes, and unbacked claims.
auto-model
TomTandem/claude-auto-model
Choisit automatiquement le modèle Claude 5.5 (Haiku, Sonnet ou Opus) selon la requête, et affiche au-dessus du prompt un indicateur avec un serpent animé pendant l'attente.
attentionfarm
attentionfarm/mod
sign up or log in, an attentionfarm band above the prompt and a scrolling status line for claude code.
automatico
Nachofranco5/claude-harness
Modo automático: encadena las tareas del plan, cada una en una ventana nueva con su modelo, hasta un tope de uso. Botón sobre el prompt para prenderlo/apagarlo
attention-is-all-i-need
AH-Merii/claude-plugins
Colours what needs you at the end of Claude's replies (must-know, decide now, decide later, defaults, your actions) and pins open decisions above the prompt
babysitter
vladgermanyuk/Claude-babysitter
Watches your background agents, corrects the ones that loop, stall or error out, and reports when they are done.
Browse the most popular Claude Code mods, all pane & dashboard mods, or the skills and MCP server directories.