Claude Code mod
model-fit
After each ask you type, says what it looked like it needed and what it cost; after a simple or routine ask on a bigger model or effort than it needed, what Haiku, Sonnet or a lower effort would have cost; warns when an ask runs on too small a model or a complex one at low effort; says when the context has grown expensive and how to shrink it; ships /model-fit:baton, a handoff note for a fresh session. Optional Jev shadow labels for comparison.
Install
/plugin marketplace add a-pavithraa/claude-mods
/plugin install model-fit@my-modsMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L3Network: network, drives Claude, writes the prompt box, reads env vars, reads settings, reads the transcript, reads the prompt box, reads mod state, persists state, draws
- Sees
- every prompt
- Draws in
AbovePrompt- Hooks
session.startprompt.submitturn.startturn.stepturn.completesession.measurecommand.runui.render
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
- a-pavithraa/claude-mods
- Folder
plugins/model-fit- Marketplace
my-mods- Last updated
- 24 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is model-fit?
After each ask you type, says what it looked like it needed and what it cost; after a simple or routine ask on a bigger model or effort than it needed, what Haiku, Sonnet or a lower effort would have cost; warns when an ask runs on too small a model or a complex one at low effort; says when the context has grown expensive and how to shrink it; ships /model-fit:baton, a handoff note for a fresh session. Optional Jev shadow labels for comparison. It is a mod for Claude Code, from a-pavithraa/claude-mods on GitHub.
What can the model-fit mod access?
Its widest reach is "network" (network, drives Claude, writes the prompt box, reads env vars, reads settings, reads the transcript, reads the prompt box, reads mod state, persists state, draws). It sees every prompt. It draws in AbovePrompt. Like any mod, it runs with your permissions.
How do I install model-fit?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add a-pavithraa/claude-mods and then /plugin install model-fit@my-mods.
More context & usage mods
model-advisor
Jaroslawczyk/ClaudeModes
Suggests the cheapest fitting model, effort and mode for a prompt, and shows where the session's limits went
model-pilot
iampramod43/claude-mods
Routes a task to a fit model or a small team of subagents, shares context through a versioned artifact store, and shows it all live: radial progress, agent lanes and a data-flow graph
mk-usage
lucianokatze/mk-usage
Límites del plan de Claude (sesión 5h, semana, renovación) bajo el prompt, con estimación al reinicio; y el estado de git y GitHub (rama, cambios, sincronía, CI, versión) sobre el prompt, con commit asistido. Configurable. Sin filas extra en el pie ni tokens.
model-router
DevstateBelgium/model-router
Routes each coding subtask to the cheapest Claude model and effort that can do it reliably, logs real token cost per subagent automatically, and learns routing boundaries from verified runs.
mission-control
ShagnikPal123/mission-control
Context and usage meters, auto-resume, model router, agent cap, proof cards, context health, midnight and god modes, ship guard, Windows overlay
model-router
dickyadrian/agent-toolbelt
Logs how hard each prompt is and what every turn costs, to measure whether routing easy prompts to a cheaper model would pay off
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.