Claude Code mod
model-advisor
Checks every prompt and asks before the task starts when a different Claude model (Haiku/Sonnet/Opus) or effort level would fit better.
Install
/plugin marketplace add rmntsv/claude-model-advisor
/plugin install model-advisor@claude-model-advisorMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: drives Claude, reads the transcript, persists state, draws
- Sees
- every prompt
- Hooks
session.startcommand.runturn.stepprompt.submit
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
- rmntsv/claude-model-advisor
- Folder
plugins/model-advisor- Marketplace
claude-model-advisor- Author
- model-advisor contributors
- License
- MIT
- Last updated
- 18 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is model-advisor?
Checks every prompt and asks before the task starts when a different Claude model (Haiku/Sonnet/Opus) or effort level would fit better. It is a mod for Claude Code, from rmntsv/claude-model-advisor on GitHub.
What can the model-advisor mod access?
Its widest reach is "writes or runs" (drives Claude, reads the transcript, persists state, draws). It sees every prompt. Like any mod, it runs with your permissions.
How do I install model-advisor?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add rmntsv/claude-model-advisor and then /plugin install model-advisor@claude-model-advisor.
More guard & safety mods
mode-gate
MarcusJellinghaus/claude-mode-gate
A Claude Code mod with switchable permission profiles: a safe baseline and named profiles you switch on and off. Bash that no active rule allows asks. For other tools the mod adds only its own rules and guards; Claude Code's own verdict applies to the rest.
model-guard
Recokioshi/claude-kit
Choose the model versions Claude and its subagents may use: /models lists the newest of each family from Anthropic's Models API (older versions one key away); block a version, or a family's new ones, and subagents, workflows and /model asking for it are refused or moved to an allowed version. One list shared by every Claude Code window on the machine; a repo can keep its own.
migration-guard
balen-abd/claude-migration-guard
Makes Claude ask before it touches your database migrations or runs destructive SQL, with the risk and what it found.
nvda-status
lbk2907/nvda-status
Claude Code for NVDA users on Windows: spoken announcements (finished, question, permission, background task), /time, /read and /quiet, a status line with working time and tokens, and a popup to answer Claude's questions from any app
mermaid-render
maxp-riot/mermaid-render
Draws the ```mermaid blocks of Claude's replies as images in the terminal, in light or dark, and opens them in Excalidraw
og-sf-org-status
oscar-guggiana-neto-neocol/claude-mods
Target Salesforce org in the status line, a panel to switch orgs per project, and a write guard for protected and production orgs
Browse the most popular Claude Code mods, all guard & safety mods, or the skills and MCP server directories.